How Superpowers’s scores are calculated
The full audit trail, recomputed from the verdict data at build time through the same code that produced the leaderboard: verdict × quality × story weight per cell, cells sum to dimension scores, dimensions blend into the PA Score. Every number on the product page is reproducible from this page alone; for why the formula looks like this, see the methodology.
verdict factors: full ×1.0 · partial ×0.6 · disputed ×0.3 · none ×0.0 · n/a excluded from both sides · cell points = weight × quality × factor · cell max = weight × 10
PA Score22/100
Agent-ready 8.0 × 0.30 = 2.40
API quality 24.0 × 0.20 = 4.80
Openness 24.0 × 0.20 = 4.80
Built-in AI 36.4 × 0.15 = 5.46
Automation 30.0 × 0.15 = 4.50
(2.40 + 4.80 + 4.80 + 5.46 + 4.50) ÷ (0.30 + 0.20 + 0.20 + 0.15 + 0.15) = 21.96 ÷ 1.00 = 22.0
Scores are stored to 1 decimal; the product page’s pills round to whole numbers for display. Each dimension below shows the stories, verdicts, and cited evidence behind its number.
Agent-ready8.0/100×0.30 of the PA blend
Outside-in: can YOUR agent reach and drive this product — API, MCP, CLI, headless runs, agent docs.
Point an agent at llms.txt or agent-oriented docsweight 2
2 (weight) × 5 (quality) × 0.6 (partial) = 6.0 of 20 max
- [claimed-docs] https://raw.githubusercontent.com/obra/superpowers/HEAD/docs/porting-to-a-new-harness.md“Skills (harness-agnostic). Everything in `skills/` is the source of truth, shared verbatim by every harness.”
- [claimed-docs] https://raw.githubusercontent.com/obra/superpowers/HEAD/skills/writing-skills/SKILL.md“Codex, Copilot CLI, and Gemini CLI all also recognize `~/.agents/skills/` as a cross-runtime alias.”
- [claimed-docs] https://raw.githubusercontent.com/obra/superpowers/HEAD/skills/using-superpowers/SKILL.md“User instructions (CLAUDE.md, AGENTS.md, GEMINI.md, etc, direct requests) take precedence over skills, which in turn override default behavior.”
- [probe] https://github.com/obra/superpowers.md“PROBE docs-md: HTTP 404 at https://github.com/obra/superpowers.md”
- [probe] https://github.com/llms.txt“PROBE llms.txt: HTTP 200 at https://github.com/llms.txt # GitHub > GitHub is a developer platform for building, shipping, and maintaining software. It provides cloud-based Git”
Run the product headlessly / in CI for automationweight 2
2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max
- [claimed-docs] https://raw.githubusercontent.com/obra/superpowers/HEAD/RELEASE-NOTES.md“Requests are classified as spike, bounded, or architectural; small tasks skip the two-document ritual. Every path still stops for your approval before implementation.”
- [claimed-docs] https://raw.githubusercontent.com/obra/superpowers/HEAD/RELEASE-NOTES.md“Every path still stops for your approval before implementation.”
- [claimed-docs] https://blog.fsck.com/2025/10/09/superpowers/“If Claude thinks you're trying to start a project or task, it _should_ default into talking through a plan with you before it starts down the path of implementation.”
- [claimed-docs] https://raw.githubusercontent.com/obra/superpowers/HEAD/RELEASE-NOTES.md“When `git worktree remove` refuses because the tree holds uncommitted work, the skill stops, names the files, and asks — instead of reaching for `--force`.”
Plug MCP servers into this product so it can use their toolsweight 3
n/a — not applicable to this product: excluded from numerator and denominator
- [claimed-docs] https://raw.githubusercontent.com/obra/superpowers/HEAD/docs/porting-to-a-new-harness.md“Skills (harness-agnostic). Everything in `skills/` is the source of truth, shared verbatim by every harness.”
- [claimed-docs] https://raw.githubusercontent.com/obra/superpowers/HEAD/docs/porting-to-a-new-harness.md“This guide explains how to add support for a new harness ... so that Superpowers skills auto-trigger there the same way they do natively.”
- [github] https://github.com/obra/superpowers“Installation differs by harness. If you use more than one, install Superpowers separately for each one.”
Connect an agent via an official MCP serverweight 3
3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max
no evidence cited — the verdict rests on absence of evidence, re-checked on refresh
Use an official CLIweight 2
n/a — not applicable to this product: excluded from numerator and denominator
- [github] https://github.com/obra/superpowers“Installation differs by harness. If you use more than one, install Superpowers separately for each one.”
- [claimed-docs] https://raw.githubusercontent.com/obra/superpowers/HEAD/docs/porting-to-a-new-harness.md“Skills (harness-agnostic). Everything in `skills/` is the source of truth, shared verbatim by every harness.”
- [claimed-docs] https://claude.com/plugins/superpowers“Invoke skills with slash commands like `/brainstorming` to explore requirements and design before implementation, or `/execute-plan` to run batched implementation plans with review checkpoints.”
- [claimed-docs] https://raw.githubusercontent.com/obra/superpowers/HEAD/docs/porting-to-a-new-harness.md“This guide explains how to add support for a new harness ... so that Superpowers skills auto-trigger there the same way they do natively.”
- [claimed-docs] https://raw.githubusercontent.com/obra/superpowers/HEAD/docs/porting-to-a-new-harness.md“Everything ships through the harness's own install mechanism. Never edit the user's files.”
Drive the product through a documented public APIweight 3
3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max
no evidence cited — the verdict rests on absence of evidence, re-checked on refresh
Issue scoped/least-privilege API credentials for an agentweight 2
n/a — not applicable to this product: excluded from numerator and denominator
no evidence cited — the verdict rests on absence of evidence, re-checked on refresh
Build against official SDKsweight 2
2 (weight) × 3 (quality) × 0.6 (partial) = 3.6 of 20 max
- [claimed-docs] https://raw.githubusercontent.com/obra/superpowers/HEAD/docs/porting-to-a-new-harness.md“Skills (harness-agnostic). Everything in `skills/` is the source of truth, shared verbatim by every harness.”
- [claimed-docs] https://raw.githubusercontent.com/obra/superpowers/HEAD/docs/porting-to-a-new-harness.md“The harness must let you inject text into the model's context at the start of every session, with no per-session opt-in by your human partner.”
- [claimed-docs] https://raw.githubusercontent.com/obra/superpowers/HEAD/docs/porting-to-a-new-harness.md“Porting adds a tool-mapping reference and a bootstrap injector; it never reaches into `skills/*/SKILL.md` to swap tool names.”
- [claimed-docs] https://raw.githubusercontent.com/obra/superpowers/HEAD/docs/porting-to-a-new-harness.md“Everything ships through the harness's own install mechanism. Never edit the user's files.”
- [claimed-docs] https://raw.githubusercontent.com/obra/superpowers/HEAD/docs/testing.md“Python harness driving real tmux sessions of Claude Code / Codex / Gemini CLI, with an LLM actor and verifier judging skill compliance.”
Subscribe to events via webhooksweight 2
n/a — not applicable to this product: excluded from numerator and denominator
no evidence cited — the verdict rests on absence of evidence, re-checked on refresh
Agent-ready = 9.6 ÷ 120 × 100 = 8.0
API quality24.0/100×0.20 of the PA blend
The programmable surface once an agent is there — machine-readable spec, interactive docs, sandbox, versioning discipline.
Explore an interactive API reference with runnable examplesweight 2
n/a — not applicable to this product: excluded from numerator and denominator
no evidence cited — the verdict rests on absence of evidence, re-checked on refresh
Download a machine-readable API spec (OpenAPI or equivalent)weight 2
n/a — not applicable to this product: excluded from numerator and denominator
no evidence cited — the verdict rests on absence of evidence, re-checked on refresh
Test against a sandbox environment without touching production dataweight 1
1 (weight) × 4 (quality) × 0.6 (partial) = 2.4 of 10 max
- [claimed-docs] https://blog.fsck.com/2025/10/09/superpowers/“After you're done brainstorming, if you're in a git repo it automatically creates a worktree for the project and changes to that directory.”
- [claimed-docs] https://blog.fsck.com/2025/10/09/superpowers/“After you're done brainstorming, if you're in a git repo it automatically creates a worktree for the project and changes to that directory. This means that you can start parallel tasks on the same project that don't clobber each other.”
- [claimed-docs] https://raw.githubusercontent.com/obra/superpowers/HEAD/RELEASE-NOTES.md“When `git worktree remove` refuses because the tree holds uncommitted work, the skill stops, names the files, and asks — instead of reaching for `--force`.”
- [claimed-docs] https://raw.githubusercontent.com/obra/superpowers/HEAD/RELEASE-NOTES.md“Worktree removal no longer destroys untracked files. When `git worktree remove` refuses because the tree holds uncommitted work, the skill stops, names the files, and asks”
- [claimed-docs] https://raw.githubusercontent.com/obra/superpowers/HEAD/skills/test-driven-development/SKILL.md“NO PRODUCTION CODE WITHOUT A FAILING TEST FIRST”
Rely on versioned APIs with a documented deprecation policyweight 2
n/a — not applicable to this product: excluded from numerator and denominator
no evidence cited — the verdict rests on absence of evidence, re-checked on refresh
API quality = 2.4 ÷ 10 × 100 = 24.0
Openness24.0/100×0.20 of the PA blend
Can you leave, inspect, or self-host — data export, open source, portability.
Do everything through the API that I can do in the UIweight 2
2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max
no evidence cited — the verdict rests on absence of evidence, re-checked on refresh
Export all of my data in open formats and leaveweight 3
n/a — not applicable to this product: excluded from numerator and denominator
no evidence cited — the verdict rests on absence of evidence, re-checked on refresh
Read the product's source under an open licenseweight 2
2 (weight) × 5 (quality) × 0.6 (partial) = 6.0 of 20 max
- [github] https://github.com/obra/superpowers“Installation differs by harness. If you use more than one, install Superpowers separately for each one.”
- [claimed-docs] https://raw.githubusercontent.com/obra/superpowers/HEAD/docs/porting-to-a-new-harness.md“Skills (harness-agnostic). Everything in `skills/` is the source of truth, shared verbatim by every harness.”
- [claimed-docs] https://raw.githubusercontent.com/obra/superpowers/HEAD/docs/porting-to-a-new-harness.md“This guide explains how to add support for a new harness ... so that Superpowers skills auto-trigger there the same way they do natively.”
- [probe] https://github.com/llms.txt“PROBE llms.txt: HTTP 200 at https://github.com/llms.txt # GitHub > GitHub is a developer platform for building, shipping, and maintaining software. It provides cloud-based Git”
Self-host the core productweight 3
3 (weight) × 6 (quality) × 0.6 (partial) = 10.8 of 30 max
- [claimed-docs] https://raw.githubusercontent.com/obra/superpowers/HEAD/docs/porting-to-a-new-harness.md“Skills (harness-agnostic). Everything in `skills/` is the source of truth, shared verbatim by every harness.”
- [github] https://github.com/obra/superpowers“Installation differs by harness. If you use more than one, install Superpowers separately for each one.”
- [claimed-docs] https://raw.githubusercontent.com/obra/superpowers/HEAD/docs/porting-to-a-new-harness.md“Everything ships through the harness's own install mechanism. Never edit the user's files.”
- [claimed-docs] https://raw.githubusercontent.com/obra/superpowers/HEAD/skills/writing-skills/SKILL.md“Codex, Copilot CLI, and Gemini CLI all also recognize `~/.agents/skills/` as a cross-runtime alias.”
Openness = 16.8 ÷ 70 × 100 = 24.0
Built-in AI36.4/100×0.15 of the PA blend
Inside-out: how agentic the product itself is for its users — built-in assistants, autonomous features.
Get AI-generated insights and suggestions from my data inside the productweight 2
2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max
no evidence cited — the verdict rests on absence of evidence, re-checked on refresh
Set up automations that run autonomously in the backgroundweight 2
2 (weight) × 5 (quality) × 0.6 (partial) = 6.0 of 20 max
- [github] https://github.com/obra/superpowers“It's not uncommon for your agent to work autonomously for a couple hours at a time without deviating from the plan you put together.”
- [github] https://github.com/obra/superpowers“your agent launches a *subagent-driven-development* process, having agents work through each engineering task, inspecting and reviewing their work, and continuing forward. It's not uncommon for your agent to work autonomously for a couple hours at a time”
- [claimed-docs] https://blog.fsck.com/2025/10/09/superpowers/“this month's cool new process, where it dispatches tasks one by one to subagents to implement and then code reviews each task before continuing.”
- [claimed-docs] https://raw.githubusercontent.com/obra/superpowers/HEAD/RELEASE-NOTES.md“The review-fix loop resumes the implementer... installs a five-round circuit breaker with controller adjudication when it trips.”
Delegate tasks to a built-in AI assistant inside the productweight 3
3 (weight) × 6 (quality) × 0.6 (partial) = 10.8 of 30 max
- [github] https://github.com/obra/superpowers“your agent launches a *subagent-driven-development* process, having agents work through each engineering task, inspecting and reviewing their work, and continuing forward”
- [github] https://github.com/obra/superpowers“It's not uncommon for your agent to work autonomously for a couple hours at a time without deviating from the plan you put together.”
- [github] https://github.com/obra/superpowers“your agent launches a *subagent-driven-development* process, having agents work through each engineering task, inspecting and reviewing their work, and continuing forward. It's not uncommon for your agent to work autonomously for a couple hours at a time”
- [claimed-docs] https://blog.fsck.com/2025/10/09/superpowers/“this month's cool new process, where it dispatches tasks one by one to subagents to implement and then code reviews each task before continuing.”
- [claimed-docs] https://claude.com/plugins/superpowers“The framework includes a code-reviewer agent that evaluates implementations against plans, coding standards, and architectural principles.”
- [community] https://hn.algolia.com/api/v1/items/47623101“I personally don't like superpowers very much. My boss does. I think Claude makes more mistakes when using superpowers than when not... Just don't believe it's a silver bullet. It's still the same Claude.”
- [community] https://hn.algolia.com/api/v1/items/47623101“A recent update got rid of the subagents for the self review and now does the self review in the main agent.”
Operate the product with natural-language commandsweight 2
2 (weight) × 8 (quality) × 1.0 (full) = 16.0 of 20 max
- [github] https://github.com/obra/superpowers“it *doesn't* just jump into trying to write code. Instead, it steps back and asks you what you're really trying to do.”
- [claimed-docs] https://blog.fsck.com/2025/10/09/superpowers/“If Claude thinks you're trying to start a project or task, it _should_ default into talking through a plan with you before it starts down the path of implementation.”
- [claimed-docs] https://claude.com/plugins/superpowers“Invoke skills with slash commands like `/brainstorming` to explore requirements and design before implementation, or `/execute-plan` to run batched implementation plans with review checkpoints.”
- [claimed-docs] https://github.com/obra/superpowers-marketplace“20+ battle-tested skills; `/brainstorm`, `/write-plan`, `/execute-plan` commands; Skills-search tool for discovery; SessionStart context injection”
- [community] https://hn.algolia.com/api/v1/items/47623101“Superpowers has several skills. Its core workflow is: brainstorm to design a spec, use subagents to adversarially review its own spec/plan, then implement using TDD. The brainstorming skill is great... I do not like the separation of spec/plan; the plan often ends up being code blocks in a Markdown doc.”
- [community] https://hn.algolia.com/api/v1/items/47623101“Yeah I agree with the implementation plan not being that useful for me to read. I often just tell it to go after reading the design doc.”
Built-in AI = 32.8 ÷ 90 × 100 = 36.4
Automation30.0/100×0.15 of the PA blend
Depth of automation primitives — rules, scheduling, bulk operations, webhooks.
Perform bulk operations across many items at onceweight 2
2 (weight) × 5 (quality) × 0.6 (partial) = 6.0 of 20 max
- [claimed-docs] https://raw.githubusercontent.com/obra/superpowers/HEAD/RELEASE-NOTES.md“Small same-shape tasks batch into one dispatch, cutting subagent cost sharply on micro-task plans; batch reviews verify every file in the brief made it into the diff.”
- [claimed-docs] https://raw.githubusercontent.com/obra/superpowers/HEAD/RELEASE-NOTES.md“Small same-shape tasks batch into one dispatch, cutting subagent cost sharply on micro-task plans.”
- [claimed-docs] https://raw.githubusercontent.com/obra/superpowers/HEAD/RELEASE-NOTES.md“Small same-shape tasks batch into one dispatch, cutting subagent cost sharply on micro-task plans”
Define rules that trigger actions automatically on eventsweight 3
3 (weight) × 5 (quality) × 0.6 (partial) = 9.0 of 30 max
- [claimed-docs] https://raw.githubusercontent.com/obra/superpowers/HEAD/RELEASE-NOTES.md“**Devin CLI**: `devin plugins install obra/superpowers` now works, and skills auto-trigger at session start.”
- [claimed-docs] https://claude.com/plugins/superpowers“safeguards that trigger architectural review after three failed fix attempts”
- [claimed-docs] https://raw.githubusercontent.com/obra/superpowers/HEAD/RELEASE-NOTES.md“When `git worktree remove` refuses because the tree holds uncommitted work, the skill stops, names the files, and asks — instead of reaching for `--force`.”
- [claimed-docs] https://raw.githubusercontent.com/obra/superpowers/HEAD/RELEASE-NOTES.md“Non-catastrophic conflicts and ambiguities get a recorded ruling and work continues; only destructive or irreversible actions still stop for a human.”
- [github] https://github.com/obra/superpowers“because the skills trigger automatically, you don't need to do anything special. Your coding agent just has Superpowers.”
- [claimed-docs] https://raw.githubusercontent.com/obra/superpowers/HEAD/skills/using-superpowers/SKILL.md“Invoke relevant or requested skills BEFORE any response or action — including clarifying questions, exploring the codebase, or checking files.”
- [claimed-docs] https://raw.githubusercontent.com/obra/superpowers/HEAD/skills/writing-skills/SKILL.md“You write test cases (pressure scenarios with subagents), watch them fail (baseline behavior), write the skill (documentation), watch tests pass (agents comply), and refactor (close loopholes).”
Schedule recurring jobs or workflowsweight 2
n/a — not applicable to this product: excluded from numerator and denominator
no evidence cited — the verdict rests on absence of evidence, re-checked on refresh
Version, review, and roll back my automationsweight 1
1 (weight) × 5 (quality) × 0.6 (partial) = 3.0 of 10 max
- [claimed-docs] https://raw.githubusercontent.com/obra/superpowers/HEAD/RELEASE-NOTES.md“`sdd-workspace` now requires the plan file and resolves a per-plan directory, `.superpowers/sdd//`; ... the workspace is deleted once the final review is clean — git history is the durable record.”
- [claimed-docs] https://blog.fsck.com/2025/10/09/superpowers/“At the end of the implementation process, Claude will now offer to make a GitHub pull request, merge the worktree back to the source branch locally, or just stop.”
- [claimed-docs] https://claude.com/plugins/superpowers“The framework includes a code-reviewer agent that evaluates implementations against plans, coding standards, and architectural principles.”
- [claimed-docs] https://raw.githubusercontent.com/obra/superpowers/HEAD/RELEASE-NOTES.md“The review-fix loop resumes the implementer... installs a five-round circuit breaker with controller adjudication when it trips.”
- [claimed-docs] https://raw.githubusercontent.com/obra/superpowers/HEAD/RELEASE-NOTES.md“When `git worktree remove` refuses because the tree holds uncommitted work, the skill stops, names the files, and asks — instead of reaching for `--force`.”
Automation = 18.0 ÷ 60 × 100 = 30.0