OpenCode vs Slate

Agent access

1. ai-native userPoint an agent at llms.txt or agent-oriented docs

   weight 2 · round to Slate
   OpenCode~partialprobed4/10

   OpenCode's own llms.txt file returns 404, so there is no dedicated llms.txt for agents, but probes show that docs pages are available in machine-readable Markdown form (.md suffix returns 200), which serves an analogous agent-oriented documentation function. There's no first-party statement about llms.txt support or explicit agent-doc pointing workflow. Missing for 10: an actual llms.txt endpoint, documentation instructing users to point agents at machine-readable docs, and confirmation that agents can consume the .md docs as intended.

   • [probe] “PROBE llms.txt: HTTP 404 at https://opencode.ai/llms.txt”
   • [probe] “PROBE docs-md: HTTP 200 at https://opencode.ai/docs/.md import { Tabs, TabItem } from "@astrojs/starlight/components" import config from "..…”

   proof ↗⚑ flag

   Slate✓fullprobed8/10

   A probe confirms Slate's docs site serves a valid llms.txt at the root with links to actual docs pages, directly satisfying the ability to point an agent at agent-oriented docs. Missing for 10: no independent/community confirmation that agents successfully consume this llms.txt in practice, and no broader agent-oriented doc format beyond the single file.

   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.randomlabs.ai/llms.txt # Slate ## Docs - [Introduction](https://docs.randomlabs.ai/en/getting-sta…”

   proof ↗⚑ flag

2. ai-native userRun the product headlessly / in CI for automation

   weight 2 · round to OpenCode
   OpenCode✓fullprobed9/10

   OpenCode explicitly supports headless/CI use via `opencode run` for non-interactive execution, `opencode serve` for a headless HTTP server with OpenAPI, `--auto` for unattended permission approval, a JS/TS SDK for programmatic control, and a first-party GitHub Actions integration triggered by PR comments. This covers CLI scripting, server automation, and CI pipelines with concrete docs and an OpenAPI endpoint confirmed live. missing for 10: independent third-party validation of CI reliability at scale (community evidence mostly covers interactive TUI use, not CI-specific automation).

   • [claimed-docs] “opencode run "Explain how closures work in JavaScript"”
   • [claimed-docs] “The opencode serve command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [claimed-docs] “The `opencode serve` command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [claimed-docs] “Start OpenCode with `--auto` to automatically approve permission requests that are not explicitly denied.”
   • [claimed-docs] “Start OpenCode with --auto to automatically approve permission requests that are not explicitly denied.”
   • [claimed-docs] “OpenCode integrates with your GitHub workflow. Mention /opencode or /oc in your comment, and OpenCode will execute tasks within your GitHub …”
   • [claimed-docs] “Mention `/opencode` or `/oc` in your comment, and OpenCode will execute tasks within your GitHub Actions runner.”
   • [claimed-docs] “The opencode JS/TS SDK provides a type-safe client for interacting with the server. Use it to build integrations and control opencode progra…”
   • [probe] “PROBE openapi: HTTP 200 at https://opencode.ai/openapi.json — contains "openapi" key”

   proof ↗⚑ flag

   Slate—none0/10

   The docs describe Slate as an interactive terminal agent (onboarding, slash commands, hotkeys, subagent cards) with a permission-bypass flag (--dangerously-skip-permissions/--yolo), but there is no mention of a headless mode, non-interactive CLI flags, exit-code/scriptable output, or CI integration examples. Missing for 10: documented headless/non-interactive invocation, CI pipeline examples, scriptable output format, and any evidence of automation use outside the interactive TUI.

   • [claimed-docs] “We support `--dangerously-skip-permissions` (alias: `--yolo`) to bypass permission prompts.”
   • [claimed-docs] “npm i -g @randomlabs/slate”
   • [claimed-docs] “Use `/sessions` to switch between existing sessions”

   proof ↗⚑ flag

3. ai-native userPlug MCP servers into this product so it can use their tools

   weight 3 · round to OpenCode
   OpenCode✓fullclaimed9/10

   OpenCode has first-party documentation dedicated to adding external tools via MCP, supporting both local and remote servers, directly matching the story. This is corroborated indirectly by community discussion of OpenCode's tool/agent ecosystem, though no hands-on account specifically tests MCP server plugging. Missing for 10: independent/hands-on confirmation specifically of MCP server usage (community evidence discusses agents/tools generally but not MCP specifically).

   • [claimed-docs] “You can add external tools to OpenCode using the _Model Context Protocol_, or MCP. OpenCode supports both local and remote servers.”
   • [claimed-docs] “You can add external tools to OpenCode using the Model Context Protocol, or MCP.”

   proof ↗⚑ flag

   Slate—none0/10

   No evidence in the pack mentions MCP servers or integrating external tool providers into Slate; the docs cover skills, permissions, orchestration, and CLI usage but never MCP support. Missing for 10: any documentation or claim about connecting/plugging in MCP servers, configuring MCP tool sources, or using MCP-provided tools.

   ⚑ flag

4. ai-native userUse an official CLI

   weight 2 · round to OpenCode
   OpenCode✓fullprobed9/10

   OpenCode ships an official CLI with documented commands (opencode run, opencode serve, init, install via curl/npm) and dedicated CLI docs, corroborated by community users who actively use it as their primary daily-driver harness. Missing for 10: independent benchmarking of CLI completeness/stability beyond anecdotal community reports (some bug complaints noted but not disputing existence of an official CLI).

   • [claimed-docs] “You can add external tools to OpenCode using the _Model Context Protocol_, or MCP. OpenCode supports both local and remote servers.”
   • [claimed-docs] “curl -fsSL https://opencode.ai/install | bash”
   • [claimed-docs] “opencode run "Explain how closures work in JavaScript"”
   • [claimed-docs] “The opencode serve command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [claimed-docs] “npm install -g opencode-ai”
   • [probe] “official CLI documented at https://opencode.ai/docs/cli/”
   • [community] “i've been using this as my primary harness for llama.cpp models, Claude, and Gemini for a few months now. the LSP integration is great.”
   • [community] “This replaced Aider for me a couple months back. I use it with Qwen 3.5 running locally when my daily limits run out on my other subscriptio…”

   proof ↗⚑ flag

   Slate✓fullprobed8/10

   Slate is delivered as an official CLI (npm-installed, terminal-based) with rich first-party docs covering install, sessions, hotkeys, shell execution, and configuration — squarely matching the 'official CLI' story for an AI-native user. Missing for 10: independent/hands-on corroboration of the CLI experience itself (community evidence found only relates to unrelated porting-quality claims, not CLI usage).

   • [claimed-docs] “npm i -g @randomlabs/slate”
   • [claimed-docs] “Use `/sessions` to switch between existing sessions”
   • [claimed-docs] “Press Tab to queue the current message so it runs after the current turn finishes.”
   • [claimed-docs] “Execute shell commands directly with `!`”
   • [claimed-docs] “Ctrl+X then N New session”
   • [probe] “official CLI documented at https://docs.randomlabs.ai/en/getting-started/quickstart”

   proof ↗⚑ flag

5. ai-native userDrive the product through a documented public API

   weight 3 · round to OpenCode
   OpenCode✓fullprobed8/10

   OpenCode ships a documented headless server (`opencode serve`) exposing an OpenAPI endpoint, confirmed live via probe (opencode-probe-3), plus a type-safe JS/TS SDK for programmatic control, and its CLI supports non-interactive scripted use (`opencode run`). missing for 10: independent third-party corroboration of SDK/API usage in production, and no evidence of versioning/stability guarantees or broader language SDK support beyond JS/TS.

   • [claimed-docs] “The opencode serve command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [claimed-docs] “The `opencode serve` command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [claimed-docs] “The opencode JS/TS SDK provides a type-safe client for interacting with the server. Use it to build integrations and control opencode progra…”
   • [claimed-docs] “The opencode JS/TS SDK provides a type-safe client for interacting with the server.”
   • [claimed-docs] “Use it to build integrations and control opencode programmatically.”
   • [claimed-docs] “opencode run "Explain how closures work in JavaScript"”
   • [probe] “PROBE openapi: HTTP 200 at https://opencode.ai/openapi.json — contains "openapi" key”
   • [claimed-docs] “Attach a terminal to an already running OpenCode backend server started via `serve` or `web` commands.”

   proof ↗⚑ flag

   Slate—none0/10

   Slate is documented as a CLI/terminal agent with configuration, skills, and hotkeys, but there is no evidence of a documented public API for programmatic/agentic access—the OpenAPI probe returned 404 across all candidate paths and no SDK or REST/API docs are mentioned anywhere in the pack.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.randomlabs.ai/openapi.json, https://docs.randomlabs.ai/swagger.json, https://docs.rando…”
   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.randomlabs.ai/llms.txt # Slate ## Docs - [Introduction](https://docs.randomlabs.ai/en/getting-sta…”

   proof ↗⚑ flag

6. ai-native userIssue scoped/least-privilege API credentials for an agent

   weight 2 · round to OpenCode
   OpenCode~partialclaimed3/10

   OpenCode's permission config lets you restrict which actions (edit, bash, etc.) an agent may auto-run, prompt for, or block, and enterprise SSO integration centralizes access to an internal AI gateway — both are adjacent to least-privilege agent control, but neither is a mechanism for issuing scoped API credentials/keys specifically to an agent. missing for 10: explicit scoped API-key/credential issuance for agents, credential expiry/rotation, per-agent key scoping documentation, independent verification of this capability.

   • [claimed-docs] “OpenCode uses the `permission` config to decide whether a given action should run automatically, prompt you, or be blocked.”
   • [claimed-docs] “Start OpenCode with `--auto` to automatically approve permission requests that are not explicitly denied.”
   • [claimed-docs] “This centralized config can integrate with your SSO provider and ensures all users access only your internal AI gateway.”

   proof ↗⚑ flag

   Slate—none0/10

   Slate is a coding-agent CLI; its evidence only covers permission settings (allow/ask/deny) for tool actions, not issuance of scoped/least-privilege API credentials or tokens for agents. No mention of credential/token scoping, API key generation, or IAM-style access control.

   • [claimed-docs] “Each permission key maps to an action ("allow", "ask", or "deny"), or a pattern object for fine-grained control.”
   • [claimed-docs] “We support `--dangerously-skip-permissions` (alias: `--yolo`) to bypass permission prompts.”

   proof ↗⚑ flag

7. ai-native userBuild against official SDKs

   weight 2 · round to OpenCode
   OpenCode✓fullprobed8/10

   OpenCode documents a dedicated JS/TS SDK ('type-safe client for interacting with the server... use it to build integrations and control opencode programmatically') plus a headless server mode (`opencode serve`) exposing an OpenAPI endpoint, confirmed live by probe (openapi.json returns valid schema). This gives AI-native users official, documented programmatic access beyond the CLI/TUI. Missing for 10: independent hands-on developer reports of building against the SDK, and broader multi-language SDK coverage beyond JS/TS.

   • [claimed-docs] “The opencode JS/TS SDK provides a type-safe client for interacting with the server. Use it to build integrations and control opencode progra…”
   • [claimed-docs] “Use it to build integrations and control opencode programmatically.”
   • [claimed-docs] “The opencode JS/TS SDK provides a type-safe client for interacting with the server.”
   • [claimed-docs] “The opencode serve command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [claimed-docs] “The `opencode serve` command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [probe] “PROBE openapi: HTTP 200 at https://opencode.ai/openapi.json — contains "openapi" key”

   proof ↗⚑ flag

   Slate—none0/10

   The evidence pack covers Slate's CLI, skills, configuration, and orchestration features but contains no mention of an official SDK (Python/TypeScript/etc.) for building applications on top of Slate, and the OpenAPI probe returned 404s across all candidate paths. Missing for 10: any documented SDK package, API reference, or programmatic interface for building against Slate.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.randomlabs.ai/openapi.json, https://docs.randomlabs.ai/swagger.json, https://docs.rando…”
   • [claimed-docs] “npm i -g @randomlabs/slate”

   proof ↗⚑ flag

Agentic features

1. ai-native userGet AI-generated insights and suggestions from my data inside the product

   weight 2 · round to OpenCode
   OpenCode✓fullcommunity7/10

   OpenCode's plan/explore agents let users get AI-generated code analysis and suggested changes without modifying the codebase, directly matching the story of AI-generated insights over the user's data (their code) (opencode-docs-7, opencode-docs-60, opencode-docs-61). Community mentions confirm active use of the agent for analysis/harness work (opencode-comm-1, opencode-comm-3). Missing for 10: independent examples of insight quality/output, and no evidence of insights beyond code (e.g., broader data analytics).

   • [claimed-docs] “Use the plan agent to analyze code and review suggestions without making any code changes.”
   • [claimed-docs] “This agent is useful when you want the LLM to analyze code, suggest changes, or create plans without making any actual modifications to your…”
   • [claimed-docs] “A fast, read-only agent for exploring codebases. Cannot modify files.”
   • [community] “I really like how their subagents work, as a bonus I get to choose which model is in which agent.”
   • [community] “i've been using this as my primary harness for llama.cpp models, Claude, and Gemini for a few months now. the LSP integration is great.”

   proof ↗⚑ flag

   Slate~partialcommunity4/10

   Slate is a coding-agent CLI whose evidence shows it can analyze a codebase and produce suggestions (e.g., generating an ARCH.md with improvement ideas), which maps loosely to 'AI-generated insights from data' but only in the narrow sense of source code, not general data analysis. Community evidence also raises skepticism about the real quality of generated output (e.g., criticism of a ported-code example as low quality/unverified). Missing for 10: evidence of insights/suggestions over non-code datasets, dashboards or analytics-style outputs, and independent validation of suggestion quality.

   • [claimed-docs] “Please review the architecture of my entire codebase creating an ARCH.md and then give me ways I can improve it.”
   • [community] “Blog post claimed porting a library with one sentence, but critic noted it was JS->TS (trivial rename) not Python->TS, excluded tests/exampl…”
   • [community] “"Why trumpet code that is so ready for the garbage that you wouldn't even bother to publish it" - skepticism about the quality/usefulness of…”

   proof ↗⚑ flag

2. ai-native userSet up automations that run autonomously in the background

   weight 2 · round to OpenCode
   OpenCode~partialcommunity6/10

   OpenCode ships a documented GitHub Actions integration where mentioning /opencode or /oc in a comment triggers it to autonomously work in a new branch and submit a PR, plus a headless `serve` mode and `--auto` permission flag that let it run unattended, supporting background automations. However there's no dedicated scheduling/cron mechanism, and community evidence flags reliability issues (stuck sessions, tool-call failures) that undercut confidence in unattended runs. missing for 10: scheduled/triggered automation beyond GitHub comment mentions, independent evidence of long-running unattended background jobs succeeding reliably.

   • [claimed-docs] “Ask OpenCode to fix an issue or implement a feature. And it will work in a new branch and submits a PR with all the changes.”
   • [claimed-docs] “Mention `/opencode` or `/oc` in your comment, and OpenCode will execute tasks within your GitHub Actions runner.”
   • [claimed-docs] “OpenCode integrates with your GitHub workflow. Mention /opencode or /oc in your comment, and OpenCode will execute tasks within your GitHub …”
   • [claimed-docs] “This will walk you through installing the GitHub app, creating the workflow, and setting up secrets.”
   • [claimed-docs] “Start OpenCode with `--auto` to automatically approve permission requests that are not explicitly denied.”
   • [claimed-docs] “The `opencode serve` command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [community] “There are random bugs with loading/restoring state of the session; Model/Provider selection switch across sessions/projects is often annoyin…”
   • [community] “I've been trying various harnesses like Pi, OpenCode, Qwen Code, and Nanocoder. A common problem I keep running into is failed tool calls, r…”

   proof ↗⚑ flag

   Slate~partialclaimed5/10

   Slate supports background subagents, parallel task orchestration, and built-in workflows like goal/deep-research that run while the user keeps interacting, which shows some autonomous background execution. However, this is task-level parallelism within an active session, not scheduled or trigger-based automations that run independently of user presence. missing for 10: evidence of scheduled/cron-like automations, persistent background jobs surviving session end, or trigger-based (event-driven) autonomous runs without an active user session.

   • [claimed-docs] “Those agents show up as a grid of inline subagent cards, one per agent.”
   • [claimed-docs] “While one or more agents run in the background, you can keep talking with Slate: plan next steps, queue up additional tasks, or spin up more…”
   • [claimed-docs] “`goal` and `deep-research` are built-in programs. They are user-visible workflows, not something you need to author before using Slate.”

   proof ↗⚑ flag

3. ai-native userDelegate tasks to a built-in AI assistant inside the product

   weight 3 · round to OpenCode
   OpenCode✓fullcommunity9/10

   OpenCode's core function is exactly this: an AI coding agent you delegate tasks to via CLI/TUI/IDE/desktop ('opencode run "Explain how closures work..."'), with multiple agent personas (build, plan, explore) and multi-session parallel delegation, richly documented and corroborated by extensive hands-on community use as a daily coding harness. Missing for 10: no independent benchmark of delegation reliability across all model backends (some community reports of failed tool calls/edits with local models).

   • [claimed-docs] “OpenCode is an open source AI coding agent. It's available as a terminal-based interface, desktop app, or IDE extension.”
   • [claimed-docs] “opencode run "Explain how closures work in JavaScript"”
   • [claimed-docs] “**Multi-session** Start multiple agents in parallel on the same project”
   • [claimed-docs] “Multi-session Start multiple agents in parallel on the same project”
   • [claimed-docs] “You can use the **Tab** key to switch between primary agents during a session.”
   • [claimed-docs] “This agent is useful when you want the LLM to analyze code, suggest changes, or create plans without making any actual modifications to your…”
   • [community] “i've been using this as my primary harness for llama.cpp models, Claude, and Gemini for a few months now. the LSP integration is great.”
   • [community] “This replaced Aider for me a couple months back. I use it with Qwen 3.5 running locally when my daily limits run out on my other subscriptio…”
   • [community] “Claude is much better in OpenCode then in Claude Code, OpenCode is just better than Claude Code. Claude Code feels like a complete mess to u…”

   proof ↗⚑ flag

   Slate✓fullcommunity7/10

   Slate is a CLI-based AI assistant where users delegate whole tasks (e.g., 'review architecture and write ARCH.md') and it spins up parallel subagents, orchestration programs like goal/deep-research, and long multi-hour sessions per first-party docs. Community evidence (comm-1/2/3) raises skepticism about output quality/novelty but does not contradict the core delegation mechanism itself. Missing for 10: independent hands-on validation that delegated multi-agent tasks reliably complete as advertised.

   • [claimed-docs] “Parallelize working and orchestration of many tasks at once.”
   • [claimed-docs] “Please review the architecture of my entire codebase creating an ARCH.md and then give me ways I can improve it.”
   • [claimed-docs] “Those agents show up as a grid of inline subagent cards, one per agent.”
   • [claimed-docs] “While one or more agents run in the background, you can keep talking with Slate: plan next steps, queue up additional tasks, or spin up more…”
   • [claimed-docs] “`goal` and `deep-research` are built-in programs. They are user-visible workflows, not something you need to author before using Slate.”
   • [community] “"Why trumpet code that is so ready for the garbage that you wouldn't even bother to publish it" - skepticism about the quality/usefulness of…”

   proof ↗⚑ flag

4. ai-native userOperate the product with natural-language commands

   weight 2 · round to OpenCode
   OpenCode✓fullcommunity9/10

   OpenCode's core interface is natural-language driven: the CLI example `opencode run "Explain how closures work in JavaScript"` and TUI/desktop/IDE modes are all built around conversational prompts to an AI agent that then edits code, opens branches, and submits PRs. Community usage (comm-1, comm-3, comm-4, comm-11) confirms this is how real users operate it day-to-day as their primary coding harness. Missing for 10: no independent benchmark specifically validating breadth of natural-language command coverage beyond docs/anecdotes.

   • [claimed-docs] “opencode run "Explain how closures work in JavaScript"”
   • [claimed-docs] “OpenCode is an open source AI coding agent. It's available as a terminal-based interface, desktop app, or IDE extension.”
   • [claimed-docs] “Ask OpenCode to fix an issue or implement a feature. And it will work in a new branch and submits a PR with all the changes.”
   • [community] “i've been using this as my primary harness for llama.cpp models, Claude, and Gemini for a few months now. the LSP integration is great.”
   • [community] “This replaced Aider for me a couple months back. I use it with Qwen 3.5 running locally when my daily limits run out on my other subscriptio…”
   • [community] “Claude is much better in OpenCode then in Claude Code, OpenCode is just better than Claude Code. Claude Code feels like a complete mess to u…”

   proof ↗⚑ flag

   Slate✓fullclaimed7/10

   Docs show Slate is driven primarily via natural-language prompts (e.g. the quickstart example 'Please review the architecture of my entire codebase...') alongside slash-commands, shell escapes, and file references, indicating natural-language is the core interaction mode for an AI-native agent CLI. Missing for 10: independent/hands-on confirmation that complex natural-language commands are reliably parsed and executed as intended (community evidence only discusses code-porting quality, not NL command usage itself).

   • [claimed-docs] “Please review the architecture of my entire codebase creating an ARCH.md and then give me ways I can improve it.”
   • [claimed-docs] “Execute shell commands directly with `!`”
   • [claimed-docs] “Use `@filename` references”
   • [claimed-docs] “Use `/sessions` to switch between existing sessions”
   • [claimed-docs] “`goal` and `deep-research` are built-in programs. They are user-visible workflows, not something you need to author before using Slate.”

   proof ↗⚑ flag

Api quality

1. ai-native userDownload a machine-readable API spec (OpenAPI or equivalent)

   weight 2 · round to OpenCode
   OpenCode✓fullprobed9/10

   The docs explicitly state that `opencode serve` runs a headless HTTP server exposing an OpenAPI endpoint, and a live probe confirms a downloadable machine-readable OpenAPI spec at https://opencode.ai/openapi.json. This directly satisfies the story of downloading a machine-readable API spec. Missing for 10: independent/community corroboration of using this OpenAPI spec in practice.

   • [claimed-docs] “The opencode serve command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [claimed-docs] “The `opencode serve` command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [probe] “PROBE openapi: HTTP 200 at https://opencode.ai/openapi.json — contains "openapi" key”

   proof ↗⚑ flag

   Slate—none0/10

   Slate's docs site was directly probed for an OpenAPI/swagger spec at standard locations and all returned 404, and no documentation anywhere mentions a machine-readable API spec for AI-native consumption.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.randomlabs.ai/openapi.json, https://docs.randomlabs.ai/swagger.json, https://docs.rando…”

   proof ↗⚑ flag

2. ai-native userRely on versioned APIs with a documented deprecation policy

   weight 2 · round drawn
   OpenCode—none0/10

   OpenCode does expose programmatic surfaces (the JS/TS SDK, `opencode serve` HTTP server, and an OpenAPI spec at openapi.json), so an API-versioning/deprecation-policy axis is applicable. However, none of the evidence mentions API version numbers, backward-compatibility guarantees, or any documented deprecation policy/process for the SDK or server API.

   • [claimed-docs] “The opencode JS/TS SDK provides a type-safe client for interacting with the server. Use it to build integrations and control opencode progra…”
   • [claimed-docs] “The opencode serve command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [claimed-docs] “The `opencode serve` command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [probe] “PROBE openapi: HTTP 200 at https://opencode.ai/openapi.json — contains "openapi" key”

   proof ↗⚑ flag

   Slate—none0/10

   Slate is a CLI coding agent product; no evidence of any versioned public API, API reference, or deprecation policy documentation exists—openapi probes returned 404 and no docs mention API versioning or deprecation. Absence of evidence for this applicable axis (a product could plausibly document API stability) yields 'none'.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.randomlabs.ai/openapi.json, https://docs.randomlabs.ai/swagger.json, https://docs.rando…”

   proof ↗⚑ flag

1. ai-native userPerform bulk operations across many items at once

   weight 2 · round to Slate
   OpenCode~partialclaimed4/10

   OpenCode's CLI (`opencode run`), SDK, and headless `opencode serve` provide programmatic hooks that could be scripted to loop over many files/tasks, and 'multi-session' lets multiple agents run in parallel on a project — but there is no documented first-class 'bulk operation' feature (e.g. batch refactor, mass file edit) or example of applying one command across many items at once. Missing for 10: explicit bulk/batch operation feature, documentation or examples of running the same task across many files/repos, independent evidence of successful large-scale batch use.

   • [claimed-docs] “**Multi-session** Start multiple agents in parallel on the same project”
   • [claimed-docs] “Multi-session Start multiple agents in parallel on the same project”
   • [claimed-docs] “The opencode JS/TS SDK provides a type-safe client for interacting with the server. Use it to build integrations and control opencode progra…”
   • [claimed-docs] “Use it to build integrations and control opencode programmatically.”
   • [claimed-docs] “The opencode serve command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [claimed-docs] “opencode run "Explain how closures work in JavaScript"”

   proof ↗⚑ flag

   Slate~partialclaimed6/10

   Docs describe running many agents in parallel and orchestrating multiple tasks simultaneously (grid of subagent cards, spinning up more agents to parallelize work), which supports bulk-style operations across many items. However, there's no independent corroboration of this working at scale and no detail on failure handling, limits, or item-level bulk operations (e.g., bulk file edits/refactors) beyond task orchestration. Missing for 10: independent/hands-on verification of large-scale parallel task execution, concrete examples of bulk item processing (files/records), and failure/error handling details at scale.

   • [claimed-docs] “Parallelize working and orchestration of many tasks at once.”
   • [claimed-docs] “Those agents show up as a grid of inline subagent cards, one per agent.”
   • [claimed-docs] “While one or more agents run in the background, you can keep talking with Slate: plan next steps, queue up additional tasks, or spin up more…”
   • [claimed-docs] “`goal` and `deep-research` are built-in programs. They are user-visible workflows, not something you need to author before using Slate.”

   proof ↗⚑ flag

2. ai-native userDefine rules that trigger actions automatically on events

   weight 3 · round to OpenCode
   OpenCode~partialclaimed5/10

   OpenCode supports some automatic rule-triggered behavior: GitHub integration lets a PR/issue comment mention (`/opencode` or `/oc`) automatically trigger the agent to execute tasks in a GitHub Actions runner, and the `permission` config lets you define rules for auto-approving, prompting, or blocking specific tool actions. This covers event-triggered automation in a narrow sense, but there's no general-purpose, user-defined event/rule engine (e.g., file-change hooks, cron-like triggers, custom event listeners) described in the docs. Missing for 10: a general automation/hooks system beyond GitHub comment mentions and permission gating, and independent evidence confirming reliability of these triggers in practice.

   • [claimed-docs] “Mention `/opencode` or `/oc` in your comment, and OpenCode will execute tasks within your GitHub Actions runner.”
   • [claimed-docs] “OpenCode integrates with your GitHub workflow. Mention /opencode or /oc in your comment, and OpenCode will execute tasks within your GitHub …”
   • [claimed-docs] “This will walk you through installing the GitHub app, creating the workflow, and setting up secrets.”
   • [claimed-docs] “OpenCode uses the `permission` config to decide whether a given action should run automatically, prompt you, or be blocked.”
   • [claimed-docs] “OpenCode uses the permission config to decide whether a given action should run automatically, prompt you, or be blocked.”
   • [claimed-docs] “For most permissions, you can use an object to apply different actions based on the tool input.”

   proof ↗⚑ flag

   Slate—none0/10

   Slate's docs describe agent rules for permissions/behavior ordering (docs-15, docs-20) and orchestration of parallel agents (docs-12, docs-13), but there is no evidence of user-defined rules that trigger actions automatically on external events (e.g., file changes, webhooks, schedule, git events). This is a plausible axis for a coding agent (many support hooks/triggers), so absence of evidence yields none rather than na.

   • [claimed-docs] “Slate by default respects agent rules in the following order”
   • [claimed-docs] “Each permission key maps to an action ("allow", "ask", or "deny"), or a pattern object for fine-grained control.”

   proof ↗⚑ flag

3. ai-native userSchedule recurring jobs or workflows

   weight 2 · round drawn
   OpenCode—none0/10

   No evidence of any scheduling, cron-like, or recurring workflow trigger capability; OpenCode's docs cover CLI, agents, MCP, permissions, SDK, GitHub Actions triggers, and server mode but none describe scheduling or recurring automation. missing for 10: any scheduler/cron feature, recurring job configuration, or workflow trigger on a schedule.

   ⚑ flag

   Slate—none0/10

   Slate is a coding-agent CLI with orchestration/parallel-agent features and sessions, but nothing in the evidence describes scheduling recurring jobs or workflows (e.g., cron-like triggers, timed recurring runs). Orchestration docs cover on-demand parallelization, not recurrence.

   • [claimed-docs] “Those agents show up as a grid of inline subagent cards, one per agent.”
   • [claimed-docs] “While one or more agents run in the background, you can keep talking with Slate: plan next steps, queue up additional tasks, or spin up more…”
   • [claimed-docs] “`goal` and `deep-research` are built-in programs. They are user-visible workflows, not something you need to author before using Slate.”

   proof ↗⚑ flag

4. ai-native userVersion, review, and roll back my automations

   weight 1 · round drawn
   OpenCode—none0/10

   Evidence covers agent creation, permissions, sessions, and sharing, but there is no documentation or community mention of versioning automations, reviewing change history, or rolling back agent/workflow configurations — session share links are for reference/debugging, not version control or rollback.

   • [claimed-docs] “**Share links** Share a link to any session for reference or to debug”
   • [claimed-docs] “Share links Share a link to any session for reference or to debug”
   • [claimed-docs] “OpenCode uses the `permission` config to decide whether a given action should run automatically, prompt you, or be blocked.”
   • [claimed-docs] “This command will guide you through creating a new agent with a custom system prompt and permission configuration.”

   proof ↗⚑ flag

   Slate—none0/10

   Evidence shows session management (/sessions, /workspace) and built-in 'programs' like goal/deep-research, but nothing about versioning automations, reviewing history of changes, or rolling back to prior states of an automation/workflow. Missing for 10: any documentation of version history, diffing, or rollback mechanisms for automations/workflows.

   • [claimed-docs] “Use `/sessions` to switch between existing sessions”
   • [claimed-docs] “Use `/workspace` to open the workspace manager, where you can review and remove workspace directories.”
   • [claimed-docs] “`goal` and `deep-research` are built-in programs. They are user-visible workflows, not something you need to author before using Slate.”

   proof ↗⚑ flag

Background execution

1. ai-native userHave a cloud agent build, test, and demo a feature end-to-end for my review

   weight 2 · round to OpenCode
   OpenCode~partialclaimed6/10

   OpenCode's GitHub integration lets it work in a new branch and submit a PR autonomously when mentioned via `/opencode` in GitHub Actions, and its share-links/session feature lets a reviewer inspect the agent's work — together covering 'build' and 'demo for review' in a cloud context. However, there is no explicit documentation of an automated testing step as part of this workflow, and the 'cloud agent' aspect relies on self-hosted GitHub Actions runners rather than a dedicated managed cloud agent service. Missing for 10: explicit test-execution/validation step in the PR workflow, and a first-party fully-hosted cloud agent (not just Actions-runner based) with demo artifacts.

   • [claimed-docs] “Ask OpenCode to fix an issue or implement a feature. And it will work in a new branch and submits a PR with all the changes.”
   • [claimed-docs] “Mention `/opencode` or `/oc` in your comment, and OpenCode will execute tasks within your GitHub Actions runner.”
   • [claimed-docs] “OpenCode integrates with your GitHub workflow. Mention /opencode or /oc in your comment, and OpenCode will execute tasks within your GitHub …”
   • [claimed-docs] “**Share links** Share a link to any session for reference or to debug”
   • [claimed-docs] “Share links Share a link to any session for reference or to debug”
   • [claimed-docs] “**Multi-session** Start multiple agents in parallel on the same project”

   proof ↗⚑ flag

   Slate!disputedcontradicted4/10

   Slate's docs claim orchestration of parallel background subagents and being 'one of the few agents capable of performing integration tests manually,' suggesting it could build and test a feature autonomously, but no docs mention a 'demo' output or cloud-hosted execution environment. Community hands-on critique of an actual Slate-produced port directly contradicts the build/test claim: reviewers found the work excluded tests/examples and provided no verifiable repo, undermining confidence that Slate reliably builds+tests end-to-end for review. Missing for 10: evidence of cloud/remote execution infra, an explicit demo-generation feature, and independent confirmation that test suites are actually run and pass.

   • [claimed-docs] “Those agents show up as a grid of inline subagent cards, one per agent.”
   • [claimed-docs] “While one or more agents run in the background, you can keep talking with Slate: plan next steps, queue up additional tasks, or spin up more…”
   • [claimed-docs] “Slate is one of the few agents capable of performing integration tests manually.”
   • [community] “Blog post claimed porting a library with one sentence, but critic noted it was JS->TS (trivial rename) not Python->TS, excluded tests/exampl…”
   • [community] “"Why trumpet code that is so ready for the garbage that you wouldn't even bother to publish it" - skepticism about the quality/usefulness of…”

   proof ↗⚑ flag

2. developerDelegate longer-running coding tasks to run in the background in an isolated cloud environment

   weight 3 · round to OpenCode
   OpenCode~partialclaimed5/10

   OpenCode documents GitHub integration where mentioning /opencode or /oc triggers it to work in a new branch and submit a PR, executing tasks inside the GitHub Actions runner (an isolated cloud environment), which supports background delegation of coding tasks. However, there's no dedicated general-purpose 'cloud agent' product, persistent cloud session management, or evidence of handling arbitrarily long-running tasks outside the GitHub Actions context. missing for 10: a dedicated hosted/cloud sandbox environment independent of GitHub Actions, evidence of long-running task monitoring/resumption in the cloud, and independent hands-on confirmation of this workflow succeeding.

   • [claimed-docs] “Ask OpenCode to fix an issue or implement a feature. And it will work in a new branch and submits a PR with all the changes.”
   • [claimed-docs] “Mention `/opencode` or `/oc` in your comment, and OpenCode will execute tasks within your GitHub Actions runner.”
   • [claimed-docs] “OpenCode integrates with your GitHub workflow. Mention /opencode or /oc in your comment, and OpenCode will execute tasks within your GitHub …”
   • [claimed-docs] “This will walk you through installing the GitHub app, creating the workflow, and setting up secrets.”

   proof ↗⚑ flag

   Slate—none0/10

   Slate's docs describe subagents running 'in the background' locally while you keep chatting and orchestration/parallelization of tasks, but there is no mention of an isolated cloud environment, remote execution sandbox, or delegation to a hosted service — everything described appears to run within the local CLI session. This axis is applicable to coding agent tools generally, but no evidence supports a cloud-isolated background execution capability for Slate.

   • [claimed-docs] “Those agents show up as a grid of inline subagent cards, one per agent.”
   • [claimed-docs] “While one or more agents run in the background, you can keep talking with Slate: plan next steps, queue up additional tasks, or spin up more…”
   • [claimed-docs] “Slate works with you across long, multi-hour sessions.”
   • [claimed-docs] “Parallelize working and orchestration of many tasks at once.”

   proof ↗⚑ flag

3. developerConfigure a reproducible cloud environment with the dependencies and setup steps my repository needs

   weight 2 · round drawn
   OpenCode—none0/10

   The evidence shows OpenCode as a terminal/IDE agent with GitHub PR automation and a headless `serve` mode, but nothing describes a mechanism for developers to declare a reproducible cloud environment (base image, dependencies, setup scripts) that the agent provisions before running. Missing for 10: any devcontainer/config-file spec for cloud sandbox provisioning, dependency installation steps, or documented cloud execution environment configuration.

   • [claimed-docs] “Ask OpenCode to fix an issue or implement a feature. And it will work in a new branch and submits a PR with all the changes.”
   • [claimed-docs] “The opencode serve command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [claimed-docs] “This centralized config can integrate with your SSO provider and ensures all users access only your internal AI gateway.”

   proof ↗⚑ flag

   Slate—none0/10

   Slate's docs describe a local CLI agent (npm install, terminal sessions, permissions, skills, orchestration) but contain no mention of provisioning or configuring a reproducible cloud environment, dependency setup, or devcontainer-style configuration for a repository. This is a fair capability to ask of an autonomous coding agent, but no evidence shows Slate supports it.

   • [claimed-docs] “npm i -g @randomlabs/slate”
   • [claimed-docs] “Slate by default respects agent rules in the following order”
   • [claimed-docs] “Each permission key maps to an action ("allow", "ask", or "deny"), or a pattern object for fine-grained control.”

   proof ↗⚑ flag

Parallel agents

1. ai-native userLaunch fleets of autonomous agents that work in parallel on different tasks for hours or days

   weight 2 · round to Slate
   OpenCode~partialcommunity6/10

   OpenCode documents multi-session support ('Start multiple agents in parallel on the same project'), subagents with per-agent model choice, and GitHub Actions integration where mentioning /opencode lets it execute unattended tasks and open PRs — all pointing toward parallel, semi-autonomous agent operation. However, there is no explicit documentation or evidence of orchestrating large 'fleets' of agents or of sustained autonomous operation over hours/days, and community reports note agents 'randomly stuck, especially for long/nested sessions,' undercutting long-horizon reliability. Missing for 10: dedicated fleet-management/orchestration tooling, explicit hours/days-long autonomous run support, and independent confirmation of stable long-running parallel agent execution.

   • [claimed-docs] “**Multi-session** Start multiple agents in parallel on the same project”
   • [claimed-docs] “Multi-session Start multiple agents in parallel on the same project”
   • [community] “I really like how their subagents work, as a bonus I get to choose which model is in which agent.”
   • [claimed-docs] “Mention `/opencode` or `/oc` in your comment, and OpenCode will execute tasks within your GitHub Actions runner.”
   • [claimed-docs] “OpenCode integrates with your GitHub workflow. Mention /opencode or /oc in your comment, and OpenCode will execute tasks within your GitHub …”
   • [claimed-docs] “The `opencode serve` command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [community] “There are random bugs with loading/restoring state of the session; Model/Provider selection switch across sessions/projects is often annoyin…”

   proof ↗⚑ flag

   Slate~partialcommunity7/10

   Docs describe genuine parallel agent orchestration (grid of subagent cards, spinning up more agents while others run in background) and explicitly support multi-hour sessions, matching much of the story. However, evidence only confirms 'multi-hour' not multi-day autonomy, and community commentary raises skepticism about output quality/novelty without directly refuting the parallel-agent mechanics themselves. Missing for 10: confirmation of multi-day unattended runs, independent hands-on validation of fleet-scale parallel task completion.

   • [claimed-docs] “Slate works with you across long, multi-hour sessions.”
   • [claimed-docs] “Parallelize working and orchestration of many tasks at once.”
   • [claimed-docs] “Those agents show up as a grid of inline subagent cards, one per agent.”
   • [claimed-docs] “While one or more agents run in the background, you can keep talking with Slate: plan next steps, queue up additional tasks, or spin up more…”
   • [community] “Commenter compared the approach to 'Ralph as a service' referencing an existing agentic coding technique (ghuntley.com/ralph), suggesting Sl…”

   proof ↗⚑ flag

2. developerRun several task attempts in parallel and compare results before choosing one

   weight 1 · round to Slate
   OpenCode~partialcommunity4/10

   OpenCode documents 'multi-session' support to start multiple agents in parallel on the same project (opencode-docs-17/38) and share links to sessions for reference/debugging (opencode-docs-18/37), which enables running parallel work and inspecting different sessions. However, there is no documented feature for running multiple attempts at the *same* task specifically to compare outcomes and pick a winner (e.g., no diff/compare UI or attempt-ranking workflow), and community threads discuss general session-state bugs rather than this comparison workflow. Missing for 10: explicit same-task multi-attempt spawning, a built-in comparison/diff view across attempts, and evidence of choosing/merging the best result.

   • [claimed-docs] “**Multi-session** Start multiple agents in parallel on the same project”
   • [claimed-docs] “Multi-session Start multiple agents in parallel on the same project”
   • [claimed-docs] “**Share links** Share a link to any session for reference or to debug”
   • [claimed-docs] “Share links Share a link to any session for reference or to debug”
   • [community] “You can start a service via 'opencode serve', it can be accessed from anywhere and has great experience on mobile except a few bugs... The W…”

   proof ↗⚑ flag

   Slate~partialclaimed6/10

   Slate's orchestration docs show multiple subagents running in parallel as a grid of cards while the user keeps working, directly supporting parallel task execution (docs-12, docs-13). However, there's no explicit documentation of a compare/diff view or a 'choose winning attempt' workflow for reconciling multiple parallel results into one choice. Missing for 10: explicit comparison/selection UI or workflow for multiple attempts of the same task, and independent/hands-on confirmation of this specific use case.

   • [claimed-docs] “Those agents show up as a grid of inline subagent cards, one per agent.”
   • [claimed-docs] “While one or more agents run in the background, you can keep talking with Slate: plan next steps, queue up additional tasks, or spin up more…”
   • [claimed-docs] “`goal` and `deep-research` are built-in programs. They are user-visible workflows, not something you need to author before using Slate.”

   proof ↗⚑ flag

Scheduled automation

1. ai-native userSet up always-on agents that run on schedules or triggers to maintain and fix my software autonomously

   weight 2 · round drawn
   OpenCode—none0/10

   OpenCode documents CLI/TUI/desktop agents, permission automation, GitHub Actions integration triggered by comments, and a headless server/SDK, but there is no evidence of scheduling (cron-like) or event-trigger-based always-on autonomous agents that proactively maintain/fix software without a user or PR-comment invocation. The GitHub integration is triggered by manual mentions, not autonomous scheduled monitoring. Missing for 10: scheduled/cron-based agent runs, event-driven triggers beyond manual mentions, autonomous 'always-on' background maintenance capability.

   • [claimed-docs] “Ask OpenCode to fix an issue or implement a feature. And it will work in a new branch and submits a PR with all the changes.”
   • [claimed-docs] “Mention `/opencode` or `/oc` in your comment, and OpenCode will execute tasks within your GitHub Actions runner.”
   • [claimed-docs] “OpenCode integrates with your GitHub workflow. Mention /opencode or /oc in your comment, and OpenCode will execute tasks within your GitHub …”
   • [claimed-docs] “The `opencode serve` command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [claimed-docs] “OpenCode uses the `permission` config to decide whether a given action should run automatically, prompt you, or be blocked.”
   • [claimed-docs] “Start OpenCode with `--auto` to automatically approve permission requests that are not explicitly denied.”

   proof ↗⚑ flag

   Slate—none0/10

   Slate's docs describe parallel subagent orchestration within a live session (background agents you keep talking to, spin up more agents to parallelize tasks) but there is no evidence of scheduling, event/webhook triggers, or persistent always-on agents that run autonomously outside an active session to maintain/fix software over time.

   • [claimed-docs] “Those agents show up as a grid of inline subagent cards, one per agent.”
   • [claimed-docs] “While one or more agents run in the background, you can keep talking with Slate: plan next steps, queue up additional tasks, or spin up more…”
   • [claimed-docs] “`goal` and `deep-research` are built-in programs. They are user-visible workflows, not something you need to author before using Slate.”

   proof ↗⚑ flag

Debugging

1. developerDebug issues and troubleshoot using natural-language queries

   weight 2 · round to OpenCode
   OpenCode✓fullcommunity7/10

   OpenCode is a terminal/IDE-based coding agent that takes natural-language queries (e.g. `opencode run "Explain how closures work..."`), can explore/read codebases via a dedicated read-only agent, and auto-loads LSPs so it can surface diagnostics/errors while chatting, all of which supports NL-driven debugging and troubleshooting; community users confirm using it as a daily 'harness' with good LSP integration for real work. missing for 10: no dedicated 'debug' or troubleshooting workflow docs, and community reports of failed tool calls/unreliable file edits with some models introduce real-world friction.

   • [claimed-docs] “opencode run "Explain how closures work in JavaScript"”
   • [claimed-docs] “A fast, read-only agent for exploring codebases.”
   • [claimed-docs] “A fast, read-only agent for exploring codebases. Cannot modify files.”
   • [claimed-docs] “LSP enabled Automatically loads the right LSPs for the LLM”
   • [community] “i've been using this as my primary harness for llama.cpp models, Claude, and Gemini for a few months now. the LSP integration is great.”
   • [community] “I've been trying various harnesses like Pi, OpenCode, Qwen Code, and Nanocoder. A common problem I keep running into is failed tool calls, r…”

   proof ↗⚑ flag

   Slate~partialclaimed5/10

   Slate's docs show it operates via natural-language prompts, executes shell commands (`!`), references files (`@filename`), and can run integration tests and review codebase architecture in NL form, which implies it could be used for debugging and troubleshooting queries. However there is no explicit example, workflow, or documentation section dedicated to debugging/troubleshooting via natural language, and community evidence is skeptical/unrelated to this specific capability. Missing for 10: explicit debugging-focused examples or docs, independent verification that NL-based debugging works well, dedicated troubleshooting workflow beyond generic agent capabilities.

   • [claimed-docs] “Execute shell commands directly with `!`”
   • [claimed-docs] “Use `@filename` references”
   • [claimed-docs] “Slate is one of the few agents capable of performing integration tests manually.”
   • [claimed-docs] “Please review the architecture of my entire codebase creating an ARCH.md and then give me ways I can improve it.”

   proof ↗⚑ flag

Feature implementation

1. developerTurn a tracked issue into a complete pull request end-to-end

   weight 3 · round to OpenCode
   OpenCode✓fullclaimed7/10

   Docs explicitly state OpenCode can be asked to fix an issue or implement a feature, working in a new branch and submitting a PR with all changes, and it integrates with GitHub Actions via /opencode mentions to run tasks end-to-end. This directly covers issue-to-PR automation, though evidence is vendor-documented only without independent hands-on confirmation of the full issue-to-PR flow succeeding. Missing for 10: independent/community verification of a successful end-to-end issue-to-PR run, and detail on how issue tracking (e.g., linking to GitHub issues specifically) is handled beyond the GitHub Actions integration.

   • [claimed-docs] “Ask OpenCode to fix an issue or implement a feature. And it will work in a new branch and submits a PR with all the changes.”
   • [claimed-docs] “OpenCode integrates with your GitHub workflow. Mention /opencode or /oc in your comment, and OpenCode will execute tasks within your GitHub …”
   • [claimed-docs] “This will walk you through installing the GitHub app, creating the workflow, and setting up secrets.”
   • [claimed-docs] “Mention `/opencode` or `/oc` in your comment, and OpenCode will execute tasks within your GitHub Actions runner.”

   proof ↗⚑ flag

   Slate—none0/10

   The evidence pack covers Slate's session management, orchestration, skills, and permissions but contains no mention of issue-tracker integration (e.g., GitHub issues) or automated pull-request creation/submission. Without evidence of ingesting a tracked issue and producing a PR end-to-end, this capability is unshown.

   ⚑ flag

2. developerDescribe a feature or bug in plain language and have the agent implement or fix it across multiple files

   weight 3 · round to OpenCode
   OpenCode✓fullcommunity8/10

   OpenCode is explicitly a coding agent that takes plain-language instructions and edits code, with docs describing it fixing issues/implementing features and submitting PRs (opencode-docs-12), a CLI for prompting tasks (opencode-docs-22), and permission/auto-approve config for autonomous multi-file changes (opencode-docs-13/14). Community reports corroborate real-world multi-file coding use, with several users calling it their primary harness replacing Aider/Claude Code (opencode-comm-1, opencode-comm-3, opencode-comm-4, opencode-comm-11, opencode-comm-14), though some report unreliable file edits with certain local models and failed tool calls in general (opencode-comm-10, opencode-comm-12). Missing for 10: independent benchmark data on multi-file edit accuracy, and resolution of the reported local-model editing reliability issues.

   • [claimed-docs] “OpenCode is an open source AI coding agent. It's available as a terminal-based interface, desktop app, or IDE extension.”
   • [claimed-docs] “Ask OpenCode to fix an issue or implement a feature. And it will work in a new branch and submits a PR with all the changes.”
   • [claimed-docs] “OpenCode uses the `permission` config to decide whether a given action should run automatically, prompt you, or be blocked.”
   • [claimed-docs] “Start OpenCode with `--auto` to automatically approve permission requests that are not explicitly denied.”
   • [claimed-docs] “opencode run "Explain how closures work in JavaScript"”
   • [community] “I really like how their subagents work, as a bonus I get to choose which model is in which agent.”
   • [community] “i've been using this as my primary harness for llama.cpp models, Claude, and Gemini for a few months now. the LSP integration is great.”
   • [community] “This replaced Aider for me a couple months back. I use it with Qwen 3.5 running locally when my daily limits run out on my other subscriptio…”
   • [community] “Claude is much better in OpenCode then in Claude Code, OpenCode is just better than Claude Code. Claude Code feels like a complete mess to u…”
   • [community] “OpenCode is awesome. Claude Code is nothing special at all. Last month I switched to just using OpenCode with a Codex $200/mo subscription, …”
   • [community] “I haven't been able to successfully get their CLI to reliably edit files when using local models, anybody else having the same problem?”
   • [community] “I've been trying various harnesses like Pi, OpenCode, Qwen Code, and Nanocoder. A common problem I keep running into is failed tool calls, r…”

   proof ↗⚑ flag

   Slate!disputedcontradicted5/10

   Docs imply broad multi-file code work (e.g. the quickstart example asks Slate to review an entire codebase and produce ARCH.md, plus orchestration features for parallelizing tasks across files/agents), suggesting Slate can act on plain-language requests across a codebase. However, independent community scrutiny of a specific real-world claim (a 'ported library' from one sentence) found it was actually a trivial JS->TS rename, excluded tests, lacked a verifiable repo, and drew explicit skepticism about the quality/usefulness of the generated code — concretely contradicting the marketed multi-file code-generation capability. Missing for 10: first-party documentation of a genuine multi-file bug-fix/feature-implementation workflow with verifiable before/after results, and independent hands-on confirmation that resolves the community dispute.

   • [claimed-docs] “Please review the architecture of my entire codebase creating an ARCH.md and then give me ways I can improve it.”
   • [claimed-docs] “While one or more agents run in the background, you can keep talking with Slate: plan next steps, queue up additional tasks, or spin up more…”
   • [claimed-docs] “Parallelize working and orchestration of many tasks at once.”
   • [community] “Blog post claimed porting a library with one sentence, but critic noted it was JS->TS (trivial rename) not Python->TS, excluded tests/exampl…”
   • [community] “"Why trumpet code that is so ready for the garbage that you wouldn't even bother to publish it" - skepticism about the quality/usefulness of…”

   proof ↗⚑ flag

Maintenance automation

1. developerHave the agent write tests, fix lint errors, resolve merge conflicts, and update dependencies for me

   weight 3 · round to OpenCode
   OpenCode~partialcommunity6/10

   OpenCode is documented as a general-purpose coding agent that can edit files, run shell commands, and even autonomously fix issues and submit PRs (opencode-docs-12, opencode-docs-58), which implies it can perform tasks like writing tests, fixing lint, resolving conflicts, and updating deps as generic coding actions. However, none of the docs explicitly call out test-writing, lint-fixing, merge-conflict resolution, or dependency updates as named capabilities, and community reports note reliability gaps such as failed tool calls and unreliable file edits especially with local models (opencode-comm-10, opencode-comm-12). Missing for 10: explicit documentation or hands-on evidence of test generation, lint-fix workflows, merge-conflict resolution, and dependency-update automation.

   • [claimed-docs] “Ask OpenCode to fix an issue or implement a feature. And it will work in a new branch and submits a PR with all the changes.”
   • [claimed-docs] “OpenCode integrates with your GitHub workflow. Mention /opencode or /oc in your comment, and OpenCode will execute tasks within your GitHub …”
   • [claimed-docs] “OpenCode uses the `permission` config to decide whether a given action should run automatically, prompt you, or be blocked.”
   • [community] “i've been using this as my primary harness for llama.cpp models, Claude, and Gemini for a few months now. the LSP integration is great.”
   • [community] “This replaced Aider for me a couple months back. I use it with Qwen 3.5 running locally when my daily limits run out on my other subscriptio…”
   • [community] “I haven't been able to successfully get their CLI to reliably edit files when using local models, anybody else having the same problem?”
   • [community] “I've been trying various harnesses like Pi, OpenCode, Qwen Code, and Nanocoder. A common problem I keep running into is failed tool calls, r…”

   proof ↗⚑ flag

   Slate~partialcommunity3/10

   Slate is documented as a general-purpose coding agent with shell execution, file editing, permissioning, and orchestration of multiple sub-agents (random-labs-docs-9, random-labs-docs-13, random-labs-docs-16), which implies it could perform tasks like running tests or lint/dependency commands, but the evidence never explicitly documents test-writing, lint-fixing, merge-conflict resolution, or dependency updates as capabilities. Community commentary raises quality concerns about generated code but doesn't specifically address these tasks. Missing for 10: explicit documentation or examples of writing/fixing tests, resolving lint errors, resolving merge conflicts, and updating dependencies.

   • [claimed-docs] “Execute shell commands directly with `!`”
   • [claimed-docs] “While one or more agents run in the background, you can keep talking with Slate: plan next steps, queue up additional tasks, or spin up more…”
   • [claimed-docs] “Slate is one of the few agents capable of performing integration tests manually.”
   • [community] “"Why trumpet code that is so ready for the garbage that you wouldn't even bother to publish it" - skepticism about the quality/usefulness of…”

   proof ↗⚑ flag

Multimodal generation

1. ai-native userGenerate a working app from a sketch, image, or PDF design

   weight 2 · round drawn
   OpenCode—none0/10

   OpenCode's evidence pack shows a terminal/IDE-based coding agent with text prompts, MCP, agents, and CLI/SDK, but there is no mention anywhere of image, sketch, or PDF design input being converted into a working app — no vision/multimodal input capability is documented.

   ⚑ flag

   Slate—none0/10

   The evidence describes Slate as a terminal-based CLI agent for coding sessions, orchestration, skills, and permissions, but nothing in the docs or community evidence mentions accepting sketches, images, or PDF designs as input to generate an app. missing for 10: any mention of image/sketch/PDF input, multimodal design-to-code capability, or UI mockup ingestion.

   • [claimed-docs] “npm i -g @randomlabs/slate”
   • [claimed-docs] “Please review the architecture of my entire codebase creating an ARCH.md and then give me ways I can improve it.”
   • [claimed-docs] “Skills are markdown instruction packages that give the agent domain-specific knowledge and behavior.”
   • [claimed-docs] “description: "Create distinctive, production-grade frontend interfaces."”

   proof ↗⚑ flag

Codebase mapping

1. developerUnderstand how a codebase fits together to find where to start making changes

   weight 3 · round to OpenCode
   OpenCode✓fullcommunity7/10

   OpenCode ships a dedicated read-only 'explore' agent for scanning codebases and a 'plan' agent that analyzes code and proposes changes without modifying files, backed by automatic LSP loading for the right language context and skills that surface repo-specific instructions; community notes call the LSP integration 'great' for understanding code. Missing for 10: no dedicated codebase-mapping/visualization feature, no independent benchmark of comprehension quality, and no first-hand user account describing successful architecture-level onboarding via these agents.

   • [claimed-docs] “A fast, read-only agent for exploring codebases.”
   • [claimed-docs] “A fast, read-only agent for exploring codebases. Cannot modify files.”
   • [claimed-docs] “Use the plan agent to analyze code and review suggestions without making any code changes.”
   • [claimed-docs] “This agent is useful when you want the LLM to analyze code, suggest changes, or create plans without making any actual modifications to your…”
   • [claimed-docs] “LSP enabled Automatically loads the right LSPs for the LLM”
   • [claimed-docs] “Agent skills let OpenCode discover reusable instructions from your repo or home directory. Skills are loaded on-demand via the native `skill…”
   • [community] “i've been using this as my primary harness for llama.cpp models, Claude, and Gemini for a few months now. the LSP integration is great.”

   proof ↗⚑ flag

   Slate~partialclaimed5/10

   The quickstart example explicitly shows Slate producing an ARCH.md architecture review of an entire codebase with improvement suggestions, directly supporting codebase-understanding use cases, and @filename references plus workspace management help navigate a repo. However there's no dedicated codebase-mapping/search feature (e.g., symbol index, dependency graph) documented beyond this one example, and no independent evidence confirming quality of such architecture summaries. missing for 10: dedicated code-navigation/search tooling, independent validation of architecture-summary accuracy, more than a single example of codebase-understanding workflow.

   • [claimed-docs] “Please review the architecture of my entire codebase creating an ARCH.md and then give me ways I can improve it.”
   • [claimed-docs] “Use `@filename` references”
   • [claimed-docs] “Use `/workspace` to open the workspace manager, where you can review and remove workspace directories.”

   proof ↗⚑ flag

2. developerHave the agent map and explain an entire unfamiliar codebase without manually selecting context files

   weight 3 · round drawn
   OpenCode~partialcommunity6/10

   OpenCode ships a dedicated read-only 'explore' agent explicitly for exploring codebases and a plan agent for analyzing code without edits, plus automatic LSP loading that gives it broader code awareness without manual file picking. However there's no documented feature for generating a full repo map/summary or explicit 'explain this whole codebase' workflow beyond agent tool use (e.g. grep/glob/read), and no independent hands-on evidence confirming it successfully maps a large unfamiliar codebase end-to-end. Missing for 10: explicit repo-map/codebase-summary feature, hands-on/independent confirmation of whole-codebase explanation without manual context selection.

   • [claimed-docs] “A fast, read-only agent for exploring codebases.”
   • [claimed-docs] “A fast, read-only agent for exploring codebases. Cannot modify files.”
   • [claimed-docs] “This agent is useful when you want the LLM to analyze code, suggest changes, or create plans without making any actual modifications to your…”
   • [claimed-docs] “LSP enabled Automatically loads the right LSPs for the LLM”
   • [claimed-docs] “opencode run "Explain how closures work in JavaScript"”
   • [community] “i've been using this as my primary harness for llama.cpp models, Claude, and Gemini for a few months now. the LSP integration is great.”

   proof ↗⚑ flag

   Slate~partialcommunity6/10

   Docs show Slate's quickstart example explicitly demonstrates asking it to 'review the architecture of my entire codebase' and generate an ARCH.md without manual file selection, and it has orchestration/subagent features for broad exploration. However there's no independent/hands-on verification that this codebase-mapping actually works well on large unfamiliar repos, and community evidence raises quality skepticism about other generated outputs. missing for 10: independent hands-on validation of full-codebase mapping accuracy, evidence of handling very large/unfamiliar codebases without manual curation, detail on how context is auto-selected under the hood.

   • [claimed-docs] “Please review the architecture of my entire codebase creating an ARCH.md and then give me ways I can improve it.”
   • [claimed-docs] “Those agents show up as a grid of inline subagent cards, one per agent.”
   • [claimed-docs] “While one or more agents run in the background, you can keep talking with Slate: plan next steps, queue up additional tasks, or spin up more…”
   • [community] “"Why trumpet code that is so ready for the garbage that you wouldn't even bother to publish it" - skepticism about the quality/usefulness of…”

   proof ↗⚑ flag

Context management

1. developerHave the agent build and recall memory automatically across sessions

   weight 2 · round drawn
   OpenCode—none0/10

   No evidence in the pack describes any persistent memory feature that automatically builds or recalls context/knowledge across separate sessions; docs cover sessions, sharing, agents, MCP, skills, and permissions, but nothing about automatic cross-session memory persistence or recall.

   ⚑ flag

   Slate—none0/10

   Docs describe session switching (/sessions), long multi-hour session support, and diagnostic context attachment, but there is no evidence of automatic cross-session memory building or recall — sessions appear to be manually selected/switched contexts, not an automatic memory system. Missing for higher verdict: any documentation of persistent memory storage, automatic recall of past codebase context, or memory summarization across sessions.

   • [claimed-docs] “Slate works with you across long, multi-hour sessions.”
   • [claimed-docs] “Use `/sessions` to switch between existing sessions”
   • [claimed-docs] “Slate automatically attaches relevant diagnostic information (OS, version, session context) to your report.”

   proof ↗⚑ flag

2. developerInclude multiple project directories in a single session for broader context

   weight 2 · round to Slate
   OpenCode—none0/10

   The evidence shows a permission flag (`external_directory`) that lets tool calls touch paths outside the working directory, but there is no documentation or community report describing a way to add multiple project directories into a single session for combined context. Multi-session and multi-agent features are about running parallel sessions, not merging directories into one context.

   • [claimed-docs] “Use external_directory to allow tool calls that touch paths outside the working directory where OpenCode was started.”
   • [claimed-docs] “**Multi-session** Start multiple agents in parallel on the same project”
   • [claimed-docs] “Multi-session Start multiple agents in parallel on the same project”

   proof ↗⚑ flag

   Slate~partialclaimed6/10

   Docs mention a `/workspace` manager for reviewing and removing 'workspace directories' (plural), implying support for multiple project directories in one session, but there's no detailed documentation on how directories are added or how context is merged across them, and no independent/hands-on confirmation. Missing for 10: explicit instructions/examples for adding multiple directories, and independent verification that broader multi-directory context actually works in practice.

   • [claimed-docs] “Use `/workspace` to open the workspace manager, where you can review and remove workspace directories.”

   proof ↗⚑ flag

3. developerAdd a project instructions file to set coding standards and conventions the agent follows

   weight 3 · round to Slate
   OpenCode~partialclaimed5/10

   OpenCode's docs mention an `opencode init` step to set up a project (docs-21/39/56) and 'Agent skills' that let OpenCode discover reusable instructions from a repo or home directory (docs-8/28), which suggests some mechanism for project-level guidance, but no evidence explicitly describes a dedicated instructions/config file (e.g., AGENTS.md) for coding standards and conventions. Missing for 10: explicit documentation of a project instructions file format, guidance on writing coding-standards content into it, and independent/hands-on confirmation that the agent actually follows such a file.

   • [claimed-docs] “initialize OpenCode for the project by running the following command.”
   • [claimed-docs] “Next, initialize OpenCode for the project by running the following command.”
   • [claimed-docs] “initialize OpenCode for the project by running the following command”
   • [claimed-docs] “Agent skills let OpenCode discover reusable instructions from your repo or home directory. Skills are loaded on-demand via the native `skill…”
   • [claimed-docs] “Agent skills let OpenCode discover reusable instructions from your repo or home directory.”

   proof ↗⚑ flag

   Slate~partialclaimed6/10

   Docs confirm Slate 'respects agent rules' in a defined precedence order and supports Skills (markdown instruction packages, including Claude Code-compatible `.claude/skills/` paths), which cover project-level conventions/instructions, but there's no explicit example of a single top-level 'instructions file' analogous to AGENTS.md/CLAUDE.md being demonstrated end-to-end. missing for 10: explicit naming/format of the project instructions file, a worked example showing the agent following custom conventions from it, and independent/community confirmation it works as documented.

   • [claimed-docs] “Slate by default respects agent rules in the following order”
   • [claimed-docs] “Skills are markdown instruction packages that give the agent domain-specific knowledge and behavior.”
   • [claimed-docs] “`.claude/skills/` | Claude Code compatibility”

   proof ↗⚑ flag

Issue diagnosis

1. developerReproduce issues, narrow down root causes, and verify fixes

   weight 3 · round to OpenCode
   OpenCode~partialcommunity5/10

   OpenCode's general coding-agent capabilities (shell/tool execution, LSP integration, a read-only 'explore' agent, and a 'plan' agent for analysis without changes) imply support for investigating bugs and iterating on fixes, and community feedback confirms strong LSP-based codebase navigation. However, there is no explicit documentation of a reproduce/debug/verify workflow, test running, or root-cause tooling, and community reports cite failed tool calls and agents getting stuck on long sessions, undermining reliability for this exact workflow. Missing for 10: explicit debugging/test-execution documentation, first-party guidance on reproducing bugs or verifying fixes, and independent hands-on confirmation of successful root-cause workflows.

   • [claimed-docs] “A fast, read-only agent for exploring codebases.”
   • [claimed-docs] “This agent is useful when you want the LLM to analyze code, suggest changes, or create plans without making any actual modifications to your…”
   • [claimed-docs] “A fast, read-only agent for exploring codebases. Cannot modify files.”
   • [community] “i've been using this as my primary harness for llama.cpp models, Claude, and Gemini for a few months now. the LSP integration is great.”
   • [community] “I've been trying various harnesses like Pi, OpenCode, Qwen Code, and Nanocoder. A common problem I keep running into is failed tool calls, r…”
   • [community] “There are random bugs with loading/restoring state of the session; Model/Provider selection switch across sessions/projects is often annoyin…”

   proof ↗⚑ flag

   Slate~partialclaimed4/10

   Slate documents shell execution (`!`), file references, and being 'one of the few agents capable of performing integration tests manually,' which are plausible building blocks for debugging workflows, but there's no explicit documentation of a reproduce→diagnose→verify-fix workflow. Missing for 10: explicit debugging/root-cause-analysis workflow documentation, evidence of test-driven verification loops, and independent hands-on confirmation that Slate helps developers actually reproduce and fix bugs.

   • [claimed-docs] “Slate is one of the few agents capable of performing integration tests manually.”
   • [claimed-docs] “Execute shell commands directly with `!`”
   • [claimed-docs] “Use `@filename` references”
   • [claimed-docs] “While one or more agents run in the background, you can keep talking with Slate: plan next steps, queue up additional tasks, or spin up more…”

   proof ↗⚑ flag

Marketplace

1. developerEquip the agent with custom skills to perform specialized tasks

   weight 1 · round to OpenCode
   OpenCode✓fullcommunity8/10

   OpenCode has a dedicated 'Agent Skills' feature that lets it discover reusable, on-demand instructions from repo or home directory via a native `skill` tool, directly matching the custom-skills story, and this is corroborated by community praise for its subagents/customizability. Missing for 10: no independent hands-on report specifically testing custom skill authoring/loading, and no detail on skill packaging/sharing ecosystem.

   • [claimed-docs] “Agent skills let OpenCode discover reusable instructions from your repo or home directory. Skills are loaded on-demand via the native `skill…”
   • [claimed-docs] “Agent skills let OpenCode discover reusable instructions from your repo or home directory.”
   • [community] “I really like how their subagents work, as a bonus I get to choose which model is in which agent.”

   proof ↗⚑ flag

   Slate✓fullclaimed7/10

   Slate has a documented Skills system: markdown instruction packages that give the agent domain-specific knowledge/behavior, with example skill definitions and compatibility with Claude Code's `.claude/skills/` format, letting developers equip the agent with custom specialized capabilities. Missing for 10: independent/hands-on verification that custom skills work as documented, and more detail on skill authoring/discovery beyond the single example.

   • [claimed-docs] “Skills are markdown instruction packages that give the agent domain-specific knowledge and behavior.”
   • [claimed-docs] “description: "Create distinctive, production-grade frontend interfaces."”
   • [claimed-docs] “`.claude/skills/` | Claude Code compatibility”

   proof ↗⚑ flag

2. engineering-leadIntegrate third-party partner-built agent apps into my workflows

   weight 1 · round to OpenCode
   OpenCode~partialclaimed5/10

   OpenCode supports MCP (local/remote servers) to add external tools, has an SDK/headless server for programmatic integrations, and GitHub Actions integration—these enable connecting third-party agent apps/tools into workflows. However, there's no evidence of a curated partner marketplace or vendor-vetted third-party 'agent apps' ecosystem beyond generic MCP/tool integration. missing for 10: a documented partner/marketplace ecosystem of pre-built third-party agent apps, case studies of integrating named partner agents, and independent verification of such integrations working smoothly.

   • [claimed-docs] “You can add external tools to OpenCode using the _Model Context Protocol_, or MCP. OpenCode supports both local and remote servers.”
   • [claimed-docs] “You can add external tools to OpenCode using the _Model Context Protocol_, or MCP.”
   • [claimed-docs] “The opencode JS/TS SDK provides a type-safe client for interacting with the server. Use it to build integrations and control opencode progra…”
   • [claimed-docs] “The opencode serve command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [claimed-docs] “OpenCode integrates with your GitHub workflow. Mention /opencode or /oc in your comment, and OpenCode will execute tasks within your GitHub …”

   proof ↗⚑ flag

   Slate—none0/10

   Slate is a coding CLI agent focused on subagents, skills, sessions, and model orchestration; there is no evidence of an ecosystem for integrating third-party partner-built agent apps (e.g., a marketplace, app store, or partner integration framework). Skills compatibility with Claude Code is mentioned but that is file-format compatibility, not partner app integration.

   • [claimed-docs] “Skills are markdown instruction packages that give the agent domain-specific knowledge and behavior.”
   • [claimed-docs] “`.claude/skills/` | Claude Code compatibility”

   proof ↗⚑ flag

Team knowledge

1. engineering-leadCreate a shared workspace from my docs and repos as a common source of truth for the team

   weight 1 · round drawn
   OpenCode—none0/10

   OpenCode offers session share links, repo-based 'agent skills', and enterprise SSO/config, but there is no evidence of a dedicated shared workspace feature that ingests both docs and repos into a common, persistent team source of truth — these are separate, ad-hoc mechanisms rather than a unified workspace.

   ⚑ flag

   Slate—none0/10

   Slate is a CLI coding agent focused on individual sessions, workspaces (local directories), skills, and orchestration of subagents—there is no evidence of a shared team workspace or collaborative source-of-truth feature built from docs and repos. The 'workspace' concept here refers to local directory management (/workspace), not a shared team hub.

   • [claimed-docs] “Use `/workspace` to open the workspace manager, where you can review and remove workspace directories.”
   • [claimed-docs] “Slate by default respects agent rules in the following order”
   • [claimed-docs] “Skills are markdown instruction packages that give the agent domain-specific knowledge and behavior.”

   proof ↗⚑ flag

Tool integration

1. developerConnect the agent to workflow tools like Jira, Slack, and Google Drive to extend its context

   weight 3 · round to OpenCode
   OpenCode~partialclaimed5/10

   OpenCode supports MCP for adding external tools (local and remote servers), which is the generic mechanism by which one could connect Jira/Slack/Google Drive-type integrations, but there is no direct first-party or community evidence of specific Jira, Slack, or Google Drive connectors or integrations. missing for 10: named first-party or community-verified MCP servers/integrations for Jira, Slack, or Google Drive specifically, and any evidence of workflow-tool context extension beyond generic MCP support.

   • [claimed-docs] “You can add external tools to OpenCode using the _Model Context Protocol_, or MCP. OpenCode supports both local and remote servers.”
   • [claimed-docs] “You can add external tools to OpenCode using the Model Context Protocol, or MCP.”
   • [claimed-docs] “You can add external tools to OpenCode using the _Model Context Protocol_, or MCP.”

   proof ↗⚑ flag

   Slate—none0/10

   No evidence anywhere in the docs pack mentions integrations with Jira, Slack, Google Drive, or any workflow tools/MCP connectors; the docs focus on CLI usage, sessions, skills, and permissions with no mention of external tool connectivity.

   ⚑ flag

2. developerKick off agent tasks directly from GitHub, GitLab, Linear, or Slack

   weight 2 · round to OpenCode
   OpenCode~partialclaimed4/10

   OpenCode has documented GitHub integration where mentioning /opencode or /oc in a comment triggers tasks in GitHub Actions, including issue-to-PR workflows, but there is no evidence of native GitLab, Linear, or Slack integrations for kicking off agent tasks. missing for 10: GitLab integration, Linear integration, Slack integration, independent hands-on confirmation of the GitHub Actions flow working reliably.

   • [claimed-docs] “Ask OpenCode to fix an issue or implement a feature. And it will work in a new branch and submits a PR with all the changes.”
   • [claimed-docs] “Mention `/opencode` or `/oc` in your comment, and OpenCode will execute tasks within your GitHub Actions runner.”
   • [claimed-docs] “OpenCode integrates with your GitHub workflow. Mention /opencode or /oc in your comment, and OpenCode will execute tasks within your GitHub …”
   • [claimed-docs] “This will walk you through installing the GitHub app, creating the workflow, and setting up secrets.”

   proof ↗⚑ flag

   Slate—none0/10

   No evidence of any integration with GitHub, GitLab, Linear, or Slack for triggering agent tasks; Slate's documentation covers CLI usage, sessions, skills, and configuration but nothing about ecosystem/platform triggers.

   ⚑ flag

Cross device continuity

1. developerStart a task on one device and continue it later from another device or browser

   weight 2 · round to OpenCode
   OpenCode~partialcommunity6/10

   OpenCode supports remote/headless usage via `opencode serve` plus a TUI that can connect to a remote backend, share links for sessions, and a WebUI that can connect to multiple backends from anywhere (including mobile), which enables cross-device continuation of a session. However, this requires manual server setup rather than seamless native cloud sync, and community reports note bugs restoring session state and provider/model selection issues across sessions. missing for 10: first-party seamless cross-device sync without self-hosting a server, official mobile app, and clear documentation/evidence of resuming full task state (not just session sharing) across devices.

   • [claimed-docs] “This allows using the TUI with a remote OpenCode backend.”
   • [claimed-docs] “**Share links** Share a link to any session for reference or to debug”
   • [claimed-docs] “The opencode serve command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [community] “You can start a service via 'opencode serve', it can be accessed from anywhere and has great experience on mobile except a few bugs... The W…”
   • [community] “There are random bugs with loading/restoring state of the session; Model/Provider selection switch across sessions/projects is often annoyin…”

   proof ↗⚑ flag

   Slate—none0/10

   Docs show session management within Slate (e.g. `/sessions` to switch sessions, `Ctrl+X N` for new session) but only describe local session switching, not any cloud sync or cross-device/browser continuation mechanism. Slate appears to be a terminal-only CLI tool with no mention of a browser interface or account-based sync for resuming tasks elsewhere.

   • [claimed-docs] “Use `/sessions` to switch between existing sessions”
   • [claimed-docs] “Ctrl+X then N New session”
   • [claimed-docs] “npm i -g @randomlabs/slate”

   proof ↗⚑ flag

Ide integration

1. developerChat with the coding assistant directly inside my IDE for contextual help

   weight 3 · round to OpenCode
   OpenCode✓fullcommunity8/10

   OpenCode ships an IDE extension and integrates directly in VS Code/Cursor with in-editor shortcuts (split terminal view, file-reference insertion) for contextual chat, and community users confirm using it as their daily coding harness with LSP integration inside editors. Missing for 10: independent hands-on review specifically of the IDE-extension chat UX (most community feedback is TUI/CLI-focused) and no screenshots/deep detail on in-IDE chat UI beyond shortcuts.

   • [claimed-docs] “OpenCode integrates with VS Code, Cursor, or any IDE that supports a terminal. Just run `opencode` in the terminal to get started.”
   • [claimed-docs] “Any editor Available as a terminal interface, desktop app, and IDE extension”
   • [claimed-docs] “Use Cmd+Esc (Mac) or Ctrl+Esc (Windows/Linux) to open OpenCode in a split terminal view”
   • [claimed-docs] “Use Cmd+Option+K (Mac) or Alt+Ctrl+K (Linux/Windows) to insert file references.”
   • [community] “i've been using this as my primary harness for llama.cpp models, Claude, and Gemini for a few months now. the LSP integration is great.”
   • [community] “This replaced Aider for me a couple months back. I use it with Qwen 3.5 running locally when my daily limits run out on my other subscriptio…”

   proof ↗⚑ flag

   Slate~partialclaimed6/10

   Slate is documented as a terminal-based coding agent with session management, `@filename` references, shell execution, and workspace context — providing contextual chat help that developers can run alongside their editor in a terminal. However, there is no evidence of a native IDE extension/panel (e.g., VS Code/JetBrains plugin) that embeds Slate directly inside the IDE UI itself. missing for 10: dedicated IDE extension/panel integration, evidence of in-editor chat UI beyond terminal, independent corroboration of IDE workflow usage.

   • [claimed-docs] “Use `/sessions` to switch between existing sessions”
   • [claimed-docs] “Execute shell commands directly with `!`”
   • [claimed-docs] “Use `@filename` references”
   • [claimed-docs] “Use `/workspace` to open the workspace manager, where you can review and remove workspace directories.”
   • [claimed-docs] “Ctrl+X then N New session”

   proof ↗⚑ flag

Session management

1. developerReview diffs visually and run multiple sessions side by side in a desktop app

   weight 2 · round to OpenCode
   OpenCode~partialclaimed5/10

   OpenCode has a documented desktop app with tabs (opencode-docs-19) and multi-session support to run multiple agents in parallel (opencode-docs-17/38), plus session share links; existence of the desktop app is also confirmed on GitHub (opencode-gh-1). However, there is no evidence describing a visual diff-review UI in the desktop app specifically — docs focus on TUI/terminal split views and file references rather than a diff viewer. Missing for 10: explicit documentation or screenshots of a visual diff/code-review interface in the desktop app, and independent/hands-on confirmation of side-by-side session usage in that app.

   • [claimed-docs] “Introducing tabs for desktop. Available on macOS, Windows, and Linux.”
   • [claimed-docs] “**Multi-session** Start multiple agents in parallel on the same project”
   • [claimed-docs] “Multi-session Start multiple agents in parallel on the same project”
   • [github] “OpenCode is also available as a desktop application.”
   • [claimed-docs] “Any editor Available as a terminal interface, desktop app, and IDE extension”

   proof ↗⚑ flag

   Slate—none0/10

   Slate is documented as a terminal/CLI tool (npm install, terminal-background onboarding, hotkeys, `/sessions` switching, subagent grid) with no mention of a desktop GUI or visual diff review; session switching is terminal-based, not side-by-side desktop windows. Missing for 10: any evidence of a desktop application, a visual diff viewer, or GUI-based side-by-side session comparison.

   • [claimed-docs] “npm i -g @randomlabs/slate”
   • [claimed-docs] “Onboarding asks for your terminal background, multiline input preference, and model source: your ChatGPT/Codex subscription, SuperGrok subsc…”
   • [claimed-docs] “Use `/sessions` to switch between existing sessions”
   • [claimed-docs] “Those agents show up as a grid of inline subagent cards, one per agent.”
   • [claimed-docs] “Ctrl+X then N New session”

   proof ↗⚑ flag

2. engineering-leadManage multiple agent-driven coding sessions from one unified workspace

   weight 2 · round drawn
   OpenCode✓fullcommunity8/10

   OpenCode explicitly supports multi-session workflows ('Start multiple agents in parallel on the same project'), tabs for desktop, share links for sessions, and a headless server that a WebUI can connect to across multiple backends, which community evidence corroborates ('WebUI... can connect to multiple OpenCode backends at once'). This directly matches an engineering-lead managing multiple agent sessions from one unified workspace. Missing for 10: no first-party documentation of team/organization-level oversight (e.g., viewing/managing sessions started by other engineers) and some reported bugs in session state restoration temper reliability.

   • [claimed-docs] “**Multi-session** Start multiple agents in parallel on the same project”
   • [claimed-docs] “Introducing tabs for desktop. Available on macOS, Windows, and Linux.”
   • [claimed-docs] “**Share links** Share a link to any session for reference or to debug”
   • [claimed-docs] “Multi-session Start multiple agents in parallel on the same project”
   • [claimed-docs] “Share links Share a link to any session for reference or to debug”
   • [claimed-docs] “The opencode serve command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [community] “You can start a service via 'opencode serve', it can be accessed from anywhere and has great experience on mobile except a few bugs... The W…”
   • [community] “There are random bugs with loading/restoring state of the session; Model/Provider selection switch across sessions/projects is often annoyin…”

   proof ↗⚑ flag

   Slate✓fullclaimed8/10

   Docs describe first-class multi-session/multi-agent workspace features: `/sessions` to switch sessions, `/workspace` manager, new-session hotkey, and orchestration showing a grid of inline subagent cards while continuing to chat, queue tasks, or spin up more parallel agents — directly matching the engineering-lead's need to manage multiple concurrent agent sessions from one place. Missing for 10: independent/hands-on verification of this workspace at scale and any lead-specific team-management features beyond individual session switching.

   • [claimed-docs] “Use `/sessions` to switch between existing sessions”
   • [claimed-docs] “Use `/workspace` to open the workspace manager, where you can review and remove workspace directories.”
   • [claimed-docs] “Those agents show up as a grid of inline subagent cards, one per agent.”
   • [claimed-docs] “While one or more agents run in the background, you can keep talking with Slate: plan next steps, queue up additional tasks, or spin up more…”
   • [claimed-docs] “Ctrl+X then N New session”

   proof ↗⚑ flag

Terminal workflow

1. developerRun a coding agent locally from my terminal

   weight 3 · round to OpenCode
   OpenCode✓fullprobed9/10

   OpenCode is explicitly a terminal-based coding agent, installable via curl/npm, run with `opencode` command in any terminal, with rich CLI docs and confirmed hands-on community usage as a daily local terminal harness. Missing for 10: no independent benchmark/security audit fully vetting the terminal experience beyond anecdotal reports (some report TUI compatibility bugs on specific setups).

   • [claimed-docs] “OpenCode is an open source AI coding agent. It's available as a terminal-based interface, desktop app, or IDE extension.”
   • [claimed-docs] “OpenCode integrates with VS Code, Cursor, or any IDE that supports a terminal. Just run `opencode` in the terminal to get started.”
   • [claimed-docs] “curl -fsSL https://opencode.ai/install | bash”
   • [claimed-docs] “opencode run "Explain how closures work in JavaScript"”
   • [claimed-docs] “OpenCode integrates with VS Code, Cursor, or any IDE that supports a terminal.”
   • [probe] “official CLI documented at https://opencode.ai/docs/cli/”
   • [community] “i've been using this as my primary harness for llama.cpp models, Claude, and Gemini for a few months now. the LSP integration is great.”
   • [community] “This replaced Aider for me a couple months back. I use it with Qwen 3.5 running locally when my daily limits run out on my other subscriptio…”

   proof ↗⚑ flag

   Slate✓fullprobed8/10

   Slate ships as a global npm CLI (`npm i -g @randomlabs/slate`) that runs interactively in the terminal, with documented terminal-native features like hotkeys, shell command execution (`!`), file references (`@filename`), session management (`/sessions`), and configuration via `slate.json` — all consistent with a locally-run terminal coding agent. Missing for 10: independent hands-on confirmation of local terminal usage (community evidence only discusses porting-quality skepticism, not terminal operation itself) and no evidence of offline/non-terminal fallback limitations.

   • [claimed-docs] “npm i -g @randomlabs/slate”
   • [claimed-docs] “Onboarding asks for your terminal background, multiline input preference, and model source: your ChatGPT/Codex subscription, SuperGrok subsc…”
   • [claimed-docs] “Use `/sessions` to switch between existing sessions”
   • [claimed-docs] “Press Tab to queue the current message so it runs after the current turn finishes.”
   • [claimed-docs] “Execute shell commands directly with `!`”
   • [claimed-docs] “Use `@filename` references”
   • [claimed-docs] “Ctrl+X then N New session”
   • [probe] “official CLI documented at https://docs.randomlabs.ai/en/getting-started/quickstart”

   proof ↗⚑ flag

2. developerRun the agent non-interactively in scripts for workflow automation

   weight 2 · round to OpenCode
   OpenCode✓fullclaimed8/10

   The `opencode run` CLI command explicitly supports non-interactive one-shot execution (e.g. `opencode run "Explain how closures work"`), and `--auto` flag auto-approves permissions for unattended runs, plus `opencode serve` exposes a headless HTTP/OpenAPI server and JS/TS SDK for scripted/programmatic control, all fitting workflow automation. Missing for 10: independent hands-on evidence of non-interactive scripting reliability/CI use, and no dedicated exit-code/output-format docs for pipeline integration.

   • [claimed-docs] “opencode run "Explain how closures work in JavaScript"”
   • [claimed-docs] “Start OpenCode with `--auto` to automatically approve permission requests that are not explicitly denied.”
   • [claimed-docs] “Start OpenCode with --auto to automatically approve permission requests that are not explicitly denied.”
   • [claimed-docs] “The `opencode serve` command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [claimed-docs] “The opencode JS/TS SDK provides a type-safe client for interacting with the server. Use it to build integrations and control opencode progra…”
   • [claimed-docs] “Attach a terminal to an already running OpenCode backend server started via `serve` or `web` commands.”

   proof ↗⚑ flag

   Slate—none0/10

   The evidence shows Slate is a CLI-based interactive agent (npm install, onboarding, in-session commands like /sessions, !, @filename) but nowhere documents a non-interactive/headless mode, flags for scripted execution, or CI/automation usage; --dangerously-skip-permissions bypasses prompts but is not shown as enabling scripted/non-interactive invocation. Missing for 10: documentation of a non-interactive/print/exec mode, exit-code or piping behavior, or any CI/scripting examples.

   • [claimed-docs] “npm i -g @randomlabs/slate”
   • [claimed-docs] “We support `--dangerously-skip-permissions` (alias: `--yolo`) to bypass permission prompts.”
   • [probe] “official CLI documented at https://docs.randomlabs.ai/en/getting-started/quickstart”

   proof ↗⚑ flag

1. ai-native userDo everything through the API that I can do in the UI

   weight 2 · round to OpenCode
   OpenCode~partialprobed6/10

   OpenCode ships a headless server (`opencode serve`) exposing a documented OpenAPI spec (confirmed live at openapi.json) plus a JS/TS SDK explicitly for 'building integrations and controlling opencode programmatically,' and the TUI/WebUI can drive a remote backend — community confirms this works day-to-day including from mobile. However, no evidence explicitly enumerates full feature parity (e.g., agent skill management, permission config, enterprise SSO settings) as exposed via the API/SDK, and there's no independent audit confirming 1:1 UI/API parity. missing for 10: explicit parity documentation covering all UI-only features (skills, permission prompts, enterprise SSO), independent verification of full API coverage.

   • [claimed-docs] “The opencode JS/TS SDK provides a type-safe client for interacting with the server. Use it to build integrations and control opencode progra…”
   • [claimed-docs] “Use it to build integrations and control opencode programmatically.”
   • [claimed-docs] “The opencode serve command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [probe] “PROBE openapi: HTTP 200 at https://opencode.ai/openapi.json — contains "openapi" key”
   • [claimed-docs] “This allows using the TUI with a remote OpenCode backend.”
   • [community] “You can start a service via 'opencode serve', it can be accessed from anywhere and has great experience on mobile except a few bugs... The W…”

   proof ↗⚑ flag

   Slate—none0/10

   No evidence of any public API for Slate — the openapi.json/swagger.json probes returned 404s and no docs reference programmatic endpoints; Slate is documented purely as a CLI/terminal agent with slash-commands, hotkeys, and config files, not an API-driven product with UI/API parity.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.randomlabs.ai/openapi.json, https://docs.randomlabs.ai/swagger.json, https://docs.rando…”
   • [probe] “official CLI documented at https://docs.randomlabs.ai/en/getting-started/quickstart”
   • [claimed-docs] “npm i -g @randomlabs/slate”

   proof ↗⚑ flag

2. ai-native userExport all of my data in open formats and leave

   weight 3 · round drawn
   OpenCode—none0/10

   No evidence describes an explicit data-export feature or open-format portability guarantee for OpenCode; while it is open-source and stores config/sessions locally, there's no documented 'export all my data and leave' capability, and community threads even note telemetry sent to OpenCode's own servers with no way to disable it (opencode-comm-2), undercutting a clean data-portability story.

   • [community] “OpenCode is sending telemetry to their own servers, even when you're using your own locally hosted models. There are no environment variable…”
   • [claimed-docs] “**Share links** Share a link to any session for reference or to debug”
   • [claimed-docs] “Share links Share a link to any session for reference or to debug”

   proof ↗⚑ flag

   Slate—none0/10

   No evidence in the docs or elsewhere describes any data export functionality, open-format export, or data portability mechanism for Slate. Sessions, workspace history, and configurations appear stored locally but no documented export/leave path is mentioned. Missing for 10: any documentation of export commands, data format specifications, or account/data portability guarantees.

   ⚑ flag

3. ai-native userRead the product's source under an open license

   weight 2 · round to OpenCode
   OpenCode✓fullcommunity7/10

   OpenCode's docs explicitly describe it as "open source" and a public GitHub repo exists (opencode-gh-1), and community members confirm they read and learned from the actual source code (opencode-comm-6), corroborating that the source is genuinely accessible. missing for 10: explicit citation of the license name/type (e.g., MIT/Apache) in the evidence pack, and a first-party statement pointing to the license file itself.

   • [claimed-docs] “OpenCode is an open source AI coding agent. It's available as a terminal-based interface, desktop app, or IDE extension.”
   • [github] “OpenCode is also available as a desktop application.”
   • [community] “OpenCode source code is even more awesome. I have learned so much from the way they have organized tools, agents, settings and prompts. mode…”

   proof ↗⚑ flag

   Slate—none0/10

   No evidence of an open-source license or public source repository for Slate; the CLI is distributed via npm install with no mention of source availability. missing for 10: open-source license declaration, public source repo link, license file/OSS registry evidence.

   ⚑ flag

4. ai-native userSelf-host the core product

   weight 3 · round to OpenCode
   OpenCode✓fullprobed8/10

   OpenCode is open source and installable via CLI, with a documented `opencode serve` headless HTTP server exposing an OpenAPI endpoint, plus SDK and remote/TUI client support, enabling full self-hosting of the core agent; community evidence confirms real-world self-hosted use ('opencode serve' accessible remotely) though also flags security hardening gaps around the server. missing for 10: independent audit confirming production-grade self-hosted security, and clearer official self-hosting/deployment guide beyond the serve command docs.

   • [claimed-docs] “curl -fsSL https://opencode.ai/install | bash”
   • [claimed-docs] “The opencode serve command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [claimed-docs] “The `opencode serve` command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.”
   • [claimed-docs] “Attach a terminal to an already running OpenCode backend server started via `serve` or `web` commands.”
   • [claimed-docs] “The opencode JS/TS SDK provides a type-safe client for interacting with the server. Use it to build integrations and control opencode progra…”
   • [probe] “PROBE openapi: HTTP 200 at https://opencode.ai/openapi.json — contains "openapi" key”
   • [community] “You can start a service via 'opencode serve', it can be accessed from anywhere and has great experience on mobile except a few bugs... The W…”
   • [community] “When server is enabled, any web page served from localhost/127.0.0.1 can execute code; any local process can execute code without authentica…”

   proof ↗⚑ flag

   Slate—none0/10

   No evidence anywhere in the docs of Slate being open-source or offering a self-hosted deployment option; it's installed via npm as a CLI that connects to model subscriptions/credits, implying a hosted/service model rather than self-hostable core infrastructure. Missing for 10: any mention of self-hosting instructions, open-source repo, or on-prem deployment option.

   • [claimed-docs] “npm i -g @randomlabs/slate”
   • [claimed-docs] “Onboarding asks for your terminal background, multiline input preference, and model source: your ChatGPT/Codex subscription, SuperGrok subsc…”

   proof ↗⚑ flag

Authentication

1. developerAuthenticate with an API key instead of an account login

   weight 2 · round to OpenCode
   OpenCode✓fullclaimed8/10

   OpenCode explicitly supports configuring API keys for any LLM provider as an alternative to logging in via account-based options like GitHub Copilot or ChatGPT Plus/Pro, giving developers a direct API-key auth path rather than requiring account login. Missing for 10: independent hands-on confirmation of the API key setup flow itself and details on key storage/security beyond docs claims.

   • [claimed-docs] “With OpenCode you can use any LLM provider by configuring their API keys.”
   • [claimed-docs] “**GitHub Copilot** Log in with GitHub to use your Copilot account”
   • [claimed-docs] “**ChatGPT Plus/Pro** Log in with OpenAI to use your ChatGPT Plus or Pro account”
   • [claimed-docs] “OpenCode Zen is a list of tested and verified models provided by the OpenCode team.”

   proof ↗⚑ flag

   Slate—none0/10

   No evidence pack mentions API key authentication as an alternative to account login; onboarding docs only describe choosing a model source (ChatGPT/Codex, SuperGrok, or Slate credits subscription), not API-key auth. No mention of an API key mechanism anywhere, and the openapi probe returned 404s, giving no indication of an API-key based auth path.

   • [claimed-docs] “Onboarding asks for your terminal background, multiline input preference, and model source: your ChatGPT/Codex subscription, SuperGrok subsc…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.randomlabs.ai/openapi.json, https://docs.randomlabs.ai/swagger.json, https://docs.rando…”

   proof ↗⚑ flag

2. engineering-leadAuthenticate through an enterprise identity or cloud platform for compliance and scalability

   weight 2 · round to OpenCode
   OpenCode~partialclaimed6/10

   OpenCode has a documented enterprise config that integrates with SSO and enforces a centralized internal AI gateway, directly addressing enterprise identity/compliance needs, and supports login via GitHub Copilot/OpenAI accounts. However, there's no independent corroboration of this enterprise SSO feature in practice, no detail on supported identity providers (SAML/OIDC specifics), and community discussion focuses on telemetry/security concerns rather than confirming enterprise auth workflows. Missing for 10: independent/hands-on validation of SSO integration, details on supported IdPs, and evidence of enterprise customers actually using this for compliance/scalability.

   • [claimed-docs] “This centralized config can integrate with your SSO provider and ensures all users access only your internal AI gateway.”
   • [claimed-docs] “**GitHub Copilot** Log in with GitHub to use your Copilot account”
   • [claimed-docs] “**ChatGPT Plus/Pro** Log in with OpenAI to use your ChatGPT Plus or Pro account”

   proof ↗⚑ flag

   Slate—none0/10

   No evidence of SSO/SAML/OIDC enterprise identity integration or cloud-platform authentication for compliance; onboarding only mentions choosing a model source (ChatGPT/Codex, SuperGrok, or Slate credits), not enterprise identity federation.

   • [claimed-docs] “Onboarding asks for your terminal background, multiline input preference, and model source: your ChatGPT/Codex subscription, SuperGrok subsc…”

   proof ↗⚑ flag

3. developerSign in with my existing product subscription plan to use the coding agent

   weight 2 · round drawn
   OpenCode✓fullcommunity8/10

   OpenCode docs explicitly support signing in with existing subscriptions—GitHub Copilot and ChatGPT Plus/Pro—rather than requiring separate API keys, and community comments confirm using subscriptions (e.g., Codex $200/mo) inside OpenCode. Missing for 10: independent hands-on verification of the Copilot/ChatGPT login flow itself and broader coverage of other subscription providers beyond these two.

   • [claimed-docs] “**GitHub Copilot** Log in with GitHub to use your Copilot account”
   • [claimed-docs] “**ChatGPT Plus/Pro** Log in with OpenAI to use your ChatGPT Plus or Pro account”
   • [claimed-docs] “GitHub Copilot Log in with GitHub to use your Copilot account”
   • [claimed-docs] “ChatGPT Plus/Pro Log in with OpenAI to use your ChatGPT Plus or Pro account”
   • [community] “OpenCode is awesome. Claude Code is nothing special at all. Last month I switched to just using OpenCode with a Codex $200/mo subscription, …”

   proof ↗⚑ flag

   Slate✓fullclaimed8/10

   Docs explicitly state onboarding lets you choose your model source as your existing ChatGPT/Codex subscription or SuperGrok subscription (in addition to Slate credits), directly matching the story of signing in with an existing subscription plan to use the agent. Missing for 10: independent/hands-on confirmation that subscription sign-in actually works end-to-end and any detail on limitations of that mode vs credits.

   • [claimed-docs] “Onboarding asks for your terminal background, multiline input preference, and model source: your ChatGPT/Codex subscription, SuperGrok subsc…”

   proof ↗⚑ flag

4. developerSign in with a personal account to get free-tier access without managing API keys

   weight 1 · round to OpenCode
   OpenCode✓fullcommunity7/10

   OpenCode's docs explicitly offer 'Log in with GitHub to use your Copilot account' and 'Log in with OpenAI to use your ChatGPT Plus or Pro account,' letting a developer authenticate with an existing personal subscription instead of managing provider API keys, and OpenCode Zen is noted to include a free coding model. Missing for 10: independent/hands-on user reports specifically confirming this login flow (community comments focus on API keys/local models, not the Copilot/ChatGPT login path), and clarity on any usage limits tied to the free tier.

   • [claimed-docs] “**GitHub Copilot** Log in with GitHub to use your Copilot account”
   • [claimed-docs] “**ChatGPT Plus/Pro** Log in with OpenAI to use your ChatGPT Plus or Pro account”
   • [claimed-docs] “GitHub Copilot Log in with GitHub to use your Copilot account”
   • [claimed-docs] “ChatGPT Plus/Pro Log in with OpenAI to use your ChatGPT Plus or Pro account”
   • [community] “OpenCode source code is even more awesome. I have learned so much from the way they have organized tools, agents, settings and prompts. mode…”

   proof ↗⚑ flag

   Slate~partialclaimed4/10

   Docs show onboarding lets users choose a model source including an existing ChatGPT/Codex or SuperGrok subscription instead of managing API keys, implying account-based auth is supported, but there's no explicit mention of a free tier or of signing in with a personal Slate account for free credits without a paid subscription. Missing for 10: explicit free-tier account sign-in flow, confirmation that 'Slate credits' option requires no payment, and any account-based (not subscription-based) login mechanism.

   • [claimed-docs] “Onboarding asks for your terminal background, multiline input preference, and model source: your ChatGPT/Codex subscription, SuperGrok subsc…”

   proof ↗⚑ flag

Model choice

1. developerLet the tool automatically pick the best model for each task

   weight 1 · round to Slate
   OpenCode—none0/10

   Evidence shows OpenCode supports many providers/models and lets users manually assign a model per agent or switch via Tab, but nothing indicates the tool automatically selects the optimal model for a given task — community feedback even confirms model/provider choice is manual and sometimes annoying to manage across sessions.

   • [community] “I really like how their subagents work, as a bonus I get to choose which model is in which agent.”
   • [community] “There are random bugs with loading/restoring state of the session; Model/Provider selection switch across sessions/projects is often annoyin…”
   • [claimed-docs] “You can use the Tab key to switch between primary agents during a session.”
   • [claimed-docs] “75+ LLM providers through Models.dev, including local models”

   proof ↗⚑ flag

   Slate~partialclaimed6/10

   Docs explicitly claim Slate 'automatically selects the right model for the job' and also allow developers to set preferred default models per slot via `/models` or `slate.json`, suggesting a hybrid automatic+manual approach relevant to pricing/limits tradeoffs. However, there's no detail on the selection logic, cost-awareness, or independent verification that auto-selection actually optimizes for task/price. Missing for 10: independent hands-on confirmation of auto-selection quality, explanation of selection criteria (cost vs capability), and evidence of pricing-limit awareness in model choice.

   • [claimed-docs] “Slate automatically selects the right model for the job.”
   • [claimed-docs] “Set preferred default models for each slot with the `/models` dialog or `slate.json` under `models`.”

   proof ↗⚑ flag

2. developerChoose which underlying AI model powers my session from multiple providers

   weight 2 · round to OpenCode
   OpenCode✓fullcommunity9/10

   OpenCode explicitly supports configuring any LLM provider via API keys, lists 75+ providers through Models.dev including local models, offers a curated OpenCode Zen model list, and supports logging in with GitHub Copilot or ChatGPT Plus/Pro accounts. Community evidence corroborates real-world use with multiple providers (Claude, Gemini, local llama.cpp, Qwen) and per-agent model selection. Missing for 10: some community reports note model/provider switching across sessions can be buggy or annoying, a minor UX caveat.

   • [claimed-docs] “With OpenCode you can use any LLM provider by configuring their API keys.”
   • [claimed-docs] “OpenCode Zen is a list of tested and verified models provided by the OpenCode team.”
   • [claimed-docs] “75+ LLM providers through Models.dev, including local models”
   • [claimed-docs] “Any model 75+ LLM providers through Models.dev, including local models”
   • [claimed-docs] “**GitHub Copilot** Log in with GitHub to use your Copilot account”
   • [claimed-docs] “**ChatGPT Plus/Pro** Log in with OpenAI to use your ChatGPT Plus or Pro account”
   • [community] “I really like how their subagents work, as a bonus I get to choose which model is in which agent.”
   • [community] “i've been using this as my primary harness for llama.cpp models, Claude, and Gemini for a few months now. the LSP integration is great.”
   • [community] “This replaced Aider for me a couple months back. I use it with Qwen 3.5 running locally when my daily limits run out on my other subscriptio…”
   • [community] “There are random bugs with loading/restoring state of the session; Model/Provider selection switch across sessions/projects is often annoyin…”

   proof ↗⚑ flag

   Slate~partialclaimed6/10

   Docs confirm model source can be chosen at onboarding (ChatGPT/Codex, SuperGrok, or Slate credits) and that default models per 'slot' can be set via `/models` or slate.json, showing multi-provider flexibility. However, this is framed around subscription/credit sources rather than a clear list of many independent model providers, and there's no independent/hands-on verification of switching providers mid-session. missing for 10: independent corroboration of provider switching, a full list of supported model providers, and confirmation this works reliably in practice.

   • [claimed-docs] “Onboarding asks for your terminal background, multiline input preference, and model source: your ChatGPT/Codex subscription, SuperGrok subsc…”
   • [claimed-docs] “Set preferred default models for each slot with the `/models` dialog or `slate.json` under `models`.”

   proof ↗⚑ flag

1. ai-native userChoose where my data is stored (region/residency)

   weight 2 · round drawn
   OpenCode—none0/10

   No evidence anywhere in the pack of a region/residency selection feature for data storage; OpenCode's docs focus on provider choice, self-hosting, and enterprise SSO, none of which address data residency. In fact, community reports indicate telemetry is always sent to OpenCode's own servers with no way to disable it, further suggesting the user lacks control over where certain data goes.

   • [community] “OpenCode is sending telemetry to their own servers, even when you're using your own locally hosted models. There are no environment variable…”

   proof ↗⚑ flag

   Slate—none0/10

   Slate is a CLI coding agent tool; the evidence pack contains no mention of data residency, region selection, or storage location controls. Missing for 10: any documentation of data residency options, regional storage configuration, or compliance controls.

   ⚑ flag

2. ai-native userPrevent my data from being used to train AI models

   weight 3 · round drawn
   OpenCode—none0/10

   The evidence pack contains no documentation of any setting, policy, or opt-out mechanism for preventing user data/code from being used to train AI models (OpenCode's docs focus on providers, agents, permissions, IDE integration, etc., none addressing training-data usage). Community evidence actually suggests the opposite direction of concern: telemetry is sent to OpenCode's own servers even with locally-hosted models with no way to disable it, which further undermines confidence that user data is protected from being retained/used.

   • [community] “OpenCode is sending telemetry to their own servers, even when you're using your own locally hosted models. There are no environment variable…”

   proof ↗⚑ flag

   Slate—none0/10

   No evidence in the pack addresses data-training opt-out, privacy policy, or any control over model training use; the documentation covers CLI usage, orchestration, and skills but nothing about data privacy posture. Missing for 10: any privacy policy statement, opt-out settings, or data usage terms regarding AI training.

   ⚑ flag

3. ai-native userControl data retention and deletion

   weight 2 · round drawn
   OpenCode—none0/10

   No documentation describes any data retention or deletion controls, and community evidence indicates the opposite: OpenCode sends telemetry to its own servers even with local models, with no environment variables or flags to disable it, suggesting no user-facing data controls exist.

   • [community] “OpenCode is sending telemetry to their own servers, even when you're using your own locally hosted models. There are no environment variable…”

   proof ↗⚑ flag

   Slate—none0/10

   No evidence pack items mention data retention policies, deletion controls, or privacy settings for user data/sessions; docs cover workspace management and permissions but not data retention/deletion. Missing for 10: any documentation of data retention periods, deletion mechanisms, or export/erase controls.

   ⚑ flag

4. ai-native userOpt out of telemetry and usage tracking

   weight 2 · round to OpenCode
   OpenCode!disputedcontradicted2/10

   OpenCode's docs make no mention of a telemetry opt-out setting, and a community report explicitly states OpenCode sends telemetry to its own servers even with locally hosted models, with no environment variables, flags, or config options to disable it. This is a first-party-vs-hands-on-evidence conflict: no documented opt-out mechanism exists, and independent evidence claims none is available. missing for 10: any official docs describing a telemetry toggle/opt-out, first-party acknowledgment of telemetry collection, and any evidence the reported issue was fixed.

   • [community] “OpenCode is sending telemetry to their own servers, even when you're using your own locally hosted models. There are no environment variable…”
   • [claimed-docs] “OpenCode uses the `permission` config to decide whether a given action should run automatically, prompt you, or be blocked.”

   proof ↗⚑ flag

   Slate—none0/10

   No evidence pack item mentions telemetry, usage tracking, analytics, or an opt-out setting anywhere in Slate's docs or community coverage; the closest item (diagnostic attachment on bug reports) doesn't address general telemetry opt-out. Missing for 10: any mention of telemetry collection, a privacy policy, or a documented opt-out flag/setting.

   • [claimed-docs] “Slate automatically attaches relevant diagnostic information (OS, version, session context) to your report.”

   proof ↗⚑ flag

Data governance

1. engineering-leadOpt out of having my code and prompts used for AI model training

   weight 1 · round drawn
   OpenCode—none0/10

   No documentation exists describing a training-data opt-out or data-use policy for prompts/code; in fact community evidence indicates OpenCode sends telemetry to its own servers with no way to disable it, even when using local models, suggesting the opposite of user control over data usage.

   • [community] “OpenCode is sending telemetry to their own servers, even when you're using your own locally hosted models. There are no environment variable…”

   proof ↗⚑ flag

   Slate—none0/10

   No evidence in the pack addresses data usage, training opt-out, or privacy policy for prompts/code submitted to Slate or its model providers.

   ⚑ flag

Pr review

1. developerHave the agent stage changes, write commit messages, create branches, and open pull requests

   weight 3 · round to OpenCode
   OpenCode~partialclaimed6/10

   Docs explicitly describe GitHub integration where OpenCode 'will work in a new branch and submits a PR with all the changes' and can execute tasks via mentions in GitHub Actions, covering branch creation and PR opening; permission config also governs whether actions like git operations auto-run or prompt. However, there's no explicit mention of staging changes or generating commit messages as a distinct capability, and no independent/community evidence corroborates the PR-creation workflow in practice. missing for 10: explicit documentation of commit message generation/staging step, independent hands-on verification of the branch+PR workflow.

   • [claimed-docs] “Ask OpenCode to fix an issue or implement a feature. And it will work in a new branch and submits a PR with all the changes.”
   • [claimed-docs] “OpenCode integrates with your GitHub workflow. Mention /opencode or /oc in your comment, and OpenCode will execute tasks within your GitHub …”
   • [claimed-docs] “Mention `/opencode` or `/oc` in your comment, and OpenCode will execute tasks within your GitHub Actions runner.”
   • [claimed-docs] “OpenCode uses the `permission` config to decide whether a given action should run automatically, prompt you, or be blocked.”
   • [claimed-docs] “This will walk you through installing the GitHub app, creating the workflow, and setting up secrets.”

   proof ↗⚑ flag

   Slate—none0/10

   No evidence in the pack mentions git operations like staging, committing, branching, or opening pull requests; documentation covers sessions, orchestration, skills, permissions, and CLI setup but not any git/PR workflow. Absence of evidence for this applicable capability means the verdict is none.

   ⚑ flag

2. developerInspect diffs and run checks to catch problems before merging

   weight 3 · round to OpenCode
   OpenCode~partialclaimed4/10

   OpenCode offers a read-only 'plan' agent for reviewing suggested changes without applying them and a permission system that can prompt before actions run, plus GitHub PR/Actions integration for submitting changes — these provide some review-safety scaffolding. However there is no documented diff-viewing UI or built-in test/lint/check-running capability before merge. Missing for 10: explicit diff inspection tooling, integrated test/lint/CI check execution, and independent evidence that these safety mechanisms actually prevent bad merges.

   • [claimed-docs] “Use the plan agent to analyze code and review suggestions without making any code changes.”
   • [claimed-docs] “This agent is useful when you want the LLM to analyze code, suggest changes, or create plans without making any actual modifications to your…”
   • [claimed-docs] “A fast, read-only agent for exploring codebases. Cannot modify files.”
   • [claimed-docs] “OpenCode uses the `permission` config to decide whether a given action should run automatically, prompt you, or be blocked.”
   • [claimed-docs] “Ask OpenCode to fix an issue or implement a feature. And it will work in a new branch and submits a PR with all the changes.”
   • [claimed-docs] “Mention `/opencode` or `/oc` in your comment, and OpenCode will execute tasks within your GitHub Actions runner.”

   proof ↗⚑ flag

   Slate~partialclaimed3/10

   Slate's docs mention it can perform integration tests manually (random-labs-docs-16), implying some check-running capability, but there is no evidence of diff inspection, git diff review, PR-style change summaries, or pre-merge validation workflows. missing for 10: diff/change inspection UI or command, explicit pre-merge check/test running workflow, and any corroborating hands-on evidence of catching problems before merge.

   • [claimed-docs] “Slate is one of the few agents capable of performing integration tests manually.”

   proof ↗⚑ flag

Safe execution

1. engineering-leadControl which external tools and integrations the agent is allowed to access

   weight 2 · round to OpenCode
   OpenCode✓fullclaimed8/10

   OpenCode's permission system lets leads set actions to auto-run, prompt, or block per tool/input, and MCP servers (external tools) are explicitly added/configured (docs-4/23/41). Enterprise config also lets orgs force use of an internal AI gateway and SSO, further restricting what integrations agents can reach (docs-33/50). Missing for 10: independent/hands-on confirmation that permission rules reliably block disallowed MCP tool calls in practice, and finer detail on allow/deny lists for specific external tool names beyond the general permission object.

   • [claimed-docs] “OpenCode uses the `permission` config to decide whether a given action should run automatically, prompt you, or be blocked.”
   • [claimed-docs] “Start OpenCode with `--auto` to automatically approve permission requests that are not explicitly denied.”
   • [claimed-docs] “OpenCode uses the permission config to decide whether a given action should run automatically, prompt you, or be blocked.”
   • [claimed-docs] “Start OpenCode with --auto to automatically approve permission requests that are not explicitly denied.”
   • [claimed-docs] “For most permissions, you can use an object to apply different actions based on the tool input.”
   • [claimed-docs] “Use external_directory to allow tool calls that touch paths outside the working directory where OpenCode was started.”
   • [claimed-docs] “You can add external tools to OpenCode using the _Model Context Protocol_, or MCP. OpenCode supports both local and remote servers.”
   • [claimed-docs] “You can add external tools to OpenCode using the Model Context Protocol, or MCP.”
   • [claimed-docs] “You can add external tools to OpenCode using the _Model Context Protocol_, or MCP.”
   • [claimed-docs] “This centralized config can integrate with your SSO provider and ensures all users access only your internal AI gateway.”
   • [claimed-docs] “Through the central config, OpenCode can integrate with your organization’s SSO provider for authentication.”

   proof ↗⚑ flag

   Slate~partialclaimed6/10

   Slate's configuration docs describe a permission system where each permission key maps to allow/ask/deny actions or fine-grained pattern objects, which supports controlling what tools/actions the agent can perform, and a `--yolo` flag exists to bypass these prompts entirely. However there's no explicit documentation of controlling specific external integrations (e.g., MCP servers, API connectors) or org/team-level lockdown for an engineering lead specifically. Missing for 10: explicit external-integration/MCP allowlist docs, engineering-lead/team-level enforcement (vs individual config), and independent verification that permission enforcement can't be trivially bypassed.

   • [claimed-docs] “Each permission key maps to an action ("allow", "ask", or "deny"), or a pattern object for fine-grained control.”
   • [claimed-docs] “We support `--dangerously-skip-permissions` (alias: `--yolo`) to bypass permission prompts.”

   proof ↗⚑ flag

2. engineering-leadHave the agent operate inside a sandbox when interacting with code, tools, and network resources

   weight 2 · round drawn
   OpenCode—none0/10

   OpenCode's documentation only describes a permission system (auto-approve/prompt/block) and an 'external_directory' toggle for path access — not an isolated sandbox for code execution, tool calls, or network access. Community evidence (opencode-comm-18) even flags that the local server mode allows any local process or webpage to execute code without authentication, the opposite of sandboxed isolation, and there is no first-party claim of container/VM-based sandboxing to dispute.

   • [claimed-docs] “OpenCode uses the `permission` config to decide whether a given action should run automatically, prompt you, or be blocked.”
   • [claimed-docs] “Start OpenCode with `--auto` to automatically approve permission requests that are not explicitly denied.”
   • [claimed-docs] “Use external_directory to allow tool calls that touch paths outside the working directory where OpenCode was started.”
   • [community] “When server is enabled, any web page served from localhost/127.0.0.1 can execute code; any local process can execute code without authentica…”

   proof ↗⚑ flag

   Slate—none0/10

   The evidence shows a permission system (allow/ask/deny actions) and a --yolo flag to bypass prompts, but there is no mention of sandboxed execution, containerization, or network isolation for the agent's code/tool interactions. missing for 10: any documentation of sandbox/container execution, network isolation controls, or filesystem confinement mechanisms.

   • [claimed-docs] “Each permission key maps to an action ("allow", "ask", or "deny"), or a pattern object for fine-grained control.”
   • [claimed-docs] “We support `--dangerously-skip-permissions` (alias: `--yolo`) to bypass permission prompts.”

   proof ↗⚑ flag

Security checks

1. engineering-leadSee license and public-code matching references for AI-suggested code

   weight 1 · round drawn
   OpenCode—none0/10

   No evidence of any license or public-code matching/attribution feature for AI-suggested code in OpenCode's docs or community reports; the product focuses on agent workflows, permissions, and MCP integration but nothing about code provenance or license scanning.

   ⚑ flag

   Slate—none0/10

   No evidence anywhere in the pack mentions license compliance checks, public-code/OSS matching, or provenance references for AI-suggested code; the docs cover orchestration, skills, permissions, and CLI usage but nothing about code provenance/license scanning.

   ⚑ flag

2. developerGet contextual explanations and automatic fixes for security vulnerabilities

   weight 2 · round drawn
   OpenCode—none0/10

   OpenCode is a general coding agent with plan/explore/build agents and permission controls, but no evidence describes any security-vulnerability scanning, contextual vulnerability explanations, or automatic security fix generation as a feature. Community evidence even highlights unresolved security reports and vulnerabilities in OpenCode itself, not a capability to detect/fix vulnerabilities in user code.

   ⚑ flag

   Slate—none0/10

   No evidence in the pack mentions security vulnerability detection, explanations, or automatic fixes; documentation covers session management, orchestration, skills, and configuration but nothing about security review or vulnerability remediation. Missing for 10: any mention of vulnerability scanning, security explanations, or auto-fix capability.

   ⚑ flag