How Claude Code’s scores are calculated

Point an agent at llms.txt or agent-oriented docsweight 2

2 (weight) × 5 (quality) × 0.6 (partial) = 6.0 of 20 max

• [probe] https://docs.claude.com/llms.txt“PROBE llms.txt: HTTP 200 at https://docs.claude.com/llms.txt # Anthropic Developer Documentation This file provides an overview of the Anthropic API documentation and developer res”
• [probe] https://docs.claude.com/en/docs/claude-code/overview.md“PROBE docs-md: HTTP 200 at https://docs.claude.com/en/docs/claude-code/overview.md > ## Documentation Index > Fetch the complete documentation index at: https://code.claude.com/docs/llms.txt > Use this f”
• [claimed-docs] https://claude.com/product/claude-code“Claude Code maps and explains entire codebases in a few seconds. It uses agentic search to understand project structure and dependencies without you having to manually select context files.”
• [claimed-docs] https://code.claude.com/docs/en/mcp.md“Claude Code can connect to hundreds of external tools and data sources through the Model Context Protocol (MCP)”

Run the product headlessly / in CI for automationweight 2

2 (weight) × 9 (quality) × 1.0 (full) = 18.0 of 20 max

• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“Claude Code is composable and follows the Unix philosophy. Pipe logs into it, run it in CI, or chain it with other tools”
• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“Run Claude on a schedule to automate work that repeats: morning PR reviews, overnight CI failure analysis, weekly dependency audits, or syncing docs after PRs merge.”
• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“In CI, you can automate code review and issue triage with GitHub Actions or GitLab CI/CD.”
• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“Get automatic code review on every PR | GitHub Code Review”

Plug MCP servers into this product so it can use their toolsweight 3

3 (weight) × 9 (quality) × 1.0 (full) = 27.0 of 30 max

• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“With MCP, Claude Code can read your design docs in Google Drive, update tickets in Jira, pull data from Slack, or use your own custom tooling.”
• [claimed-docs] https://code.claude.com/docs/en/mcp.md“Claude Code can connect to hundreds of external tools and data sources through the Model Context Protocol (MCP)”
• [claimed-docs] https://code.claude.com/docs/en/mcp.md“Implement features from issue trackers: "Add the feature described in JIRA issue ENG-4521 and create a PR on GitHub."”
• [claimed-docs] https://code.claude.com/docs/en/mcp.md“claude mcp add --transport http notion https://mcp.notion.com/mcp”
• [claimed-docs] https://code.claude.com/docs/en/mcp.md“Stdio servers run as local processes on your machine. They're ideal for tools that need direct system access or custom scripts.”
• [claimed-docs] https://code.claude.com/docs/en/mcp.md“You can also have Claude scaffold a server for you with the official mcp-server-dev plugin”
• [claimed-docs] https://code.claude.com/docs/en/mcp.md“an MCP server can also act as a channel that pushes messages into your session, so Claude reacts to Telegram messages, Discord chats, or webhook events while you're away”

Connect an agent via an official MCP serverweight 3

3 (weight) × 9 (quality) × 1.0 (full) = 27.0 of 30 max

• [claimed-docs] https://code.claude.com/docs/en/mcp.md“Use Claude Code as an MCP server. You can use Claude Code itself as an MCP server that other applications can connect to: claude mcp serve (Start Claude as a stdio MCP server). A stdio MCP server communicates over stdin and stdout.”
• [claimed-docs] https://code.claude.com/docs/en/mcp.md“Claude Code can connect to hundreds of external tools and data sources through the Model Context Protocol (MCP)”
• [claimed-docs] https://code.claude.com/docs/en/mcp.md“Stdio servers run as local processes on your machine. They're ideal for tools that need direct system access or custom scripts.”
• [claimed-docs] https://code.claude.com/docs/en/mcp.md“claude mcp add --transport http notion https://mcp.notion.com/mcp”

Use an official CLIweight 2

2 (weight) × 9 (quality) × 1.0 (full) = 18.0 of 20 max

• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“cd your-project claude”
• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“curl -fsSL https://claude.ai/install.sh | bash”
• [claimed-docs] https://claude.com/product/claude-code“Available for macOS, Linux, and Windows.”
• [github] https://github.com/anthropics/claude-code“Use it in your terminal, IDE, or tag @claude on Github.”
• [github] https://github.com/anthropics/claude-code“helps you code faster by executing routine tasks, explaining complex code, and handling git workflows -- all through natural language commands”
• [probe] https://code.claude.com/docs/en/setup“official CLI documented at https://code.claude.com/docs/en/setup”

Drive the product through a documented public APIweight 3

3 (weight) × 8 (quality) × 1.0 (full) = 24.0 of 30 max

• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“the Agent SDK lets you build your own agents powered by Claude Code's tools and capabilities, with full control over orchestration, tool access, and permissions.”
• [claimed-docs] https://code.claude.com/docs/en/mcp.md“Use Claude Code as an MCP server. You can use Claude Code itself as an MCP server that other applications can connect to: claude mcp serve (Start Claude as a stdio MCP server). A stdio MCP server communicates over stdin and stdout.”
• [claimed-docs] https://code.claude.com/docs/en/iam“If you've set the ANTHROPIC_API_KEY environment variable, Claude Code skips the login prompt and asks you to approve the key instead.”
• [claimed-docs] https://code.claude.com/docs/en/iam“ANTHROPIC_API_KEY environment variable. Sent as the X-Api-Key header. Use this for direct Anthropic API access with a key from the Claude Console. In interactive mode, you are prompted once to approve or decline the key, and your choice is remembered.”
• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“Claude Code is composable and follows the Unix philosophy. Pipe logs into it, run it in CI, or chain it with other tools”
• [claimed-docs] https://code.claude.com/docs/en/mcp.md“Claude Code can connect to hundreds of external tools and data sources through the Model Context Protocol (MCP)”

Issue scoped/least-privilege API credentials for an agentweight 2

2 (weight) × 4 (quality) × 0.6 (partial) = 4.8 of 20 max

• [claimed-docs] https://code.claude.com/docs/en/iam“Claude for Enterprise: adds SSO, domain capture, role-based permissions, compliance API, and managed policy settings for organization-wide Claude Code configurations.”
• [claimed-docs] https://claude.com/solutions/enterprise“Single sign-on (SSO/SAML) and domain capture”
• [claimed-docs] https://code.claude.com/docs/en/sandboxing.md“Learn how Claude Code's sandboxed Bash tool provides filesystem and network isolation for safer, more autonomous agent execution. The Bash sandbox lets Claude run most shell commands without stopping to ask permission. Instead of approving each command, you define which files and network domains commands can touch, and the operating system enforces that boundary for every Bash command and its child processes.”
• [claimed-docs] https://code.claude.com/docs/en/iam“If you've set the ANTHROPIC_API_KEY environment variable, Claude Code skips the login prompt and asks you to approve the key instead.”
• [claimed-docs] https://code.claude.com/docs/en/iam“You can sign in to your Console account without creating an API key, even when your organization doesn't let developers create them.”

Build against official SDKsweight 2

2 (weight) × 8 (quality) × 1.0 (full) = 16.0 of 20 max

• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“the Agent SDK lets you build your own agents powered by Claude Code's tools and capabilities, with full control over orchestration, tool access, and permissions.”
• [claimed-docs] https://code.claude.com/docs/en/iam“If you've set the ANTHROPIC_API_KEY environment variable, Claude Code skips the login prompt and asks you to approve the key instead.”
• [claimed-docs] https://code.claude.com/docs/en/iam“ANTHROPIC_API_KEY environment variable. Sent as the X-Api-Key header. Use this for direct Anthropic API access with a key from the Claude Console. In interactive mode, you are prompted once to approve or decline the key, and your choice is remembered.”

Subscribe to events via webhooksweight 2

2 (weight) × 4 (quality) × 0.6 (partial) = 4.8 of 20 max

• [claimed-docs] https://code.claude.com/docs/en/mcp.md“an MCP server can also act as a channel that pushes messages into your session, so Claude reacts to Telegram messages, Discord chats, or webhook events while you're away”
• [claimed-docs] https://code.claude.com/docs/en/mcp.md“an MCP server can also act as a channel that pushes messages into your session, so Claude reacts to Telegram messages, Discord chats, or webhook events while you're away.”
• [claimed-docs] https://code.claude.com/docs/en/mcp.md“Claude Code can connect to hundreds of external tools and data sources through the Model Context Protocol (MCP)”

Explore an interactive API reference with runnable examplesweight 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

Download a machine-readable API spec (OpenAPI or equivalent)weight 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

Test against a sandbox environment without touching production dataweight 1

1 (weight) × 5 (quality) × 0.6 (partial) = 3.0 of 10 max

• [claimed-docs] https://code.claude.com/docs/en/sandboxing.md“Learn how Claude Code's sandboxed Bash tool provides filesystem and network isolation for safer, more autonomous agent execution. The Bash sandbox lets Claude run most shell commands without stopping to ask permission. Instead of approving each command, you define which files and network domains commands can touch, and the operating system enforces that boundary for every Bash command and its child processes.”

Rely on versioned APIs with a documented deprecation policyweight 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

Do everything through the API that I can do in the UIweight 2

2 (weight) × 5 (quality) × 0.6 (partial) = 6.0 of 20 max

• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“the Agent SDK lets you build your own agents powered by Claude Code's tools and capabilities, with full control over orchestration, tool access, and permissions.”
• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“In CI, you can automate code review and issue triage with GitHub Actions or GitLab CI/CD.”
• [claimed-docs] https://code.claude.com/docs/en/iam“If you've set the ANTHROPIC_API_KEY environment variable, Claude Code skips the login prompt and asks you to approve the key instead.”
• [claimed-docs] https://code.claude.com/docs/en/iam“ANTHROPIC_API_KEY environment variable. Sent as the X-Api-Key header. Use this for direct Anthropic API access with a key from the Claude Console. In interactive mode, you are prompted once to approve or decline the key, and your choice is remembered.”
• [claimed-docs] https://code.claude.com/docs/en/mcp.md“Use Claude Code as an MCP server. You can use Claude Code itself as an MCP server that other applications can connect to: claude mcp serve (Start Claude as a stdio MCP server). A stdio MCP server communicates over stdin and stdout.”

Export all of my data in open formats and leaveweight 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

Read the product's source under an open licenseweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

• [community] https://news.ycombinator.com/item?id=48734373“Codex CLI is FOSS, unlike Claude Code, so Codex is less likely to do things like that, and it's one more reason to avoid Claude Code and Claude in general.”

Self-host the core productweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

• [claimed-docs] https://code.claude.com/docs/en/iam“Claude Pro or Max subscription: log in with your Claude.ai account.”
• [claimed-docs] https://code.claude.com/docs/en/iam“If you've set the ANTHROPIC_API_KEY environment variable, Claude Code skips the login prompt and asks you to approve the key instead.”
• [claimed-docs] https://code.claude.com/docs/en/iam“Individual users can log in with a claude.ai account, while teams can use Claude for Teams or Enterprise, the Claude Console, or a cloud provider”
• [community] https://news.ycombinator.com/item?id=48734373“Codex CLI is FOSS, unlike Claude Code, so Codex is less likely to do things like that, and it's one more reason to avoid Claude Code and Claude in general.”

Get AI-generated insights and suggestions from my data inside the productweight 2

2 (weight) × 7 (quality) × 1.0 (full) = 14.0 of 20 max

• [claimed-docs] https://claude.com/product/claude-code“Claude Code maps and explains entire codebases in a few seconds. It uses agentic search to understand project structure and dependencies without you having to manually select context files.”
• [claimed-docs] https://claude.com/solutions/enterprise“Claude helps security teams and developers by reviewing code for security issues, drafts patches, and explains the risk in language your whole team can act on.”
• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“Get automatic code review on every PR | GitHub Code Review”
• [claimed-docs] https://code.claude.com/docs/en/mcp.md“Find emails of 10 random users who used feature ENG-4521, based on our PostgreSQL database.”
• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“With MCP, Claude Code can read your design docs in Google Drive, update tickets in Jira, pull data from Slack, or use your own custom tooling.”
• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“Claude Code can read your design docs in Google Drive, update tickets in Jira, pull data from Slack, or use your own custom tooling.”

Set up automations that run autonomously in the backgroundweight 2

2 (weight) × 8 (quality) × 1.0 (full) = 16.0 of 20 max

• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“Run Claude on a schedule to automate work that repeats: morning PR reviews, overnight CI failure analysis, weekly dependency audits, or syncing docs after PRs merge.”
• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“Step away from your desk and keep working from your phone or any browser with Remote Control”
• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“Kick off a long-running task on the web or the Claude mobile app, then pull it into your terminal with `claude --teleport`.”
• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“Review diffs visually, run multiple sessions side by side, schedule recurring tasks, and kick off cloud sessions.”
• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“Kick off long-running tasks and check back when they're done, work on repos you don't have locally, or run multiple tasks in parallel.”
• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“Run Claude Code in your browser with no local setup. Kick off long-running tasks and check back when they're done, work on repos you don't have locally, or run multiple tasks in parallel.”
• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“In CI, you can automate code review and issue triage with GitHub Actions or GitLab CI/CD.”
• [claimed-docs] https://code.claude.com/docs/en/mcp.md“an MCP server can also act as a channel that pushes messages into your session, so Claude reacts to Telegram messages, Discord chats, or webhook events while you're away”
• [claimed-docs] https://code.claude.com/docs/en/mcp.md“an MCP server can also act as a channel that pushes messages into your session, so Claude reacts to Telegram messages, Discord chats, or webhook events while you're away.”

Delegate tasks to a built-in AI assistant inside the productweight 3

3 (weight) × 8 (quality) × 1.0 (full) = 24.0 of 30 max

• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“Describe what you want in plain language. Claude Code plans the approach, writes the code across multiple files, and verifies it works.”
• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“Claude Code works directly with git. It stages changes, writes commit messages, creates branches, and opens pull requests.”
• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“Claude Code handles the tedious tasks that eat up your day: writing tests for untested code, fixing lint errors across a project, resolving merge conflicts, updating dependencies, and writing release notes.”
• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“Claude Code plans the approach, writes the code across multiple files, and verifies it works.”
• [github] https://github.com/anthropics/claude-code“helps you code faster by executing routine tasks, explaining complex code, and handling git workflows -- all through natural language commands”
• [community] https://news.ycombinator.com/item?id=43163011“Claude is significantly better than other models at code assistant tasks, or at least in the way I use it.”
• [community] https://news.ycombinator.com/item?id=47660925“I've been using Claude Code daily for months on a project with Elixir, Rust, and Python. The worst failure mode is when it does a replace_all on a string that also appears inside a constant definition -- ended up with GROQ_URL = GROQ_URL instead of the actual URL. You absolutely can't trust it to self-verify.”
• [community] https://news.ycombinator.com/item?id=47660925“I've tried to use Claude code for a month now. It has a 100% failure rate so far. Comparing that to creating a project and just chatting with it solves nearly everything I've thrown at it, using a pro plan with Sonnet since Opus drains all tokens with one request.”

Operate the product with natural-language commandsweight 2

2 (weight) × 8 (quality) × 1.0 (full) = 16.0 of 20 max

• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“Describe what you want in plain language. Claude Code plans the approach, writes the code across multiple files, and verifies it works.”
• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“Claude Code plans the approach, writes the code across multiple files, and verifies it works.”
• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“Claude Code works directly with git. It stages changes, writes commit messages, creates branches, and opens pull requests.”
• [github] https://github.com/anthropics/claude-code“helps you code faster by executing routine tasks, explaining complex code, and handling git workflows -- all through natural language commands”
• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“Route tasks from team chat: mention @Claude in Slack with a bug report and get a pull request back”
• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“cd your-project claude”

Perform bulk operations across many items at onceweight 2

2 (weight) × 6 (quality) × 0.3 (disputed) = 3.6 of 20 max

• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“writing tests for untested code, fixing lint errors across a project, resolving merge conflicts, updating dependencies, and writing release notes”
• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“Spawn multiple Claude Code agents that work on different parts of a task simultaneously. A lead agent coordinates the work, assigns subtasks, and merges results.”
• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“Claude Code handles the tedious tasks that eat up your day: writing tests for untested code, fixing lint errors across a project, resolving merge conflicts, updating dependencies, and writing release notes.”
• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“Spawn multiple Claude Code agents that work on different parts of a task simultaneously.”
• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“Review diffs visually, run multiple sessions side by side, schedule recurring tasks, and kick off cloud sessions.”
• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“Kick off long-running tasks and check back when they're done, work on repos you don't have locally, or run multiple tasks in parallel.”
• [community] https://news.ycombinator.com/item?id=47660925“I've been using Claude Code daily for months on a project with Elixir, Rust, and Python. The worst failure mode is when it does a replace_all on a string that also appears inside a constant definition -- ended up with GROQ_URL = GROQ_URL instead of the actual URL. You absolutely can't trust it to self-verify.”

Define rules that trigger actions automatically on eventsweight 3

3 (weight) × 6 (quality) × 0.6 (partial) = 10.8 of 30 max

• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“Hooks let you run shell commands before or after Claude Code actions, like auto-formatting after every file edit or running lint before a commit.”
• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“Run Claude on a schedule to automate work that repeats: morning PR reviews, overnight CI failure analysis, weekly dependency audits, or syncing docs after PRs merge.”
• [claimed-docs] https://code.claude.com/docs/en/mcp.md“an MCP server can also act as a channel that pushes messages into your session, so Claude reacts to Telegram messages, Discord chats, or webhook events while you're away”
• [claimed-docs] https://code.claude.com/docs/en/mcp.md“an MCP server can also act as a channel that pushes messages into your session, so Claude reacts to Telegram messages, Discord chats, or webhook events while you're away.”
• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“In CI, you can automate code review and issue triage with GitHub Actions or GitLab CI/CD.”

Schedule recurring jobs or workflowsweight 2

2 (weight) × 7 (quality) × 1.0 (full) = 14.0 of 20 max

• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“Run Claude on a schedule to automate work that repeats: morning PR reviews, overnight CI failure analysis, weekly dependency audits, or syncing docs after PRs merge.”
• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“Review diffs visually, run multiple sessions side by side, schedule recurring tasks, and kick off cloud sessions.”

Version, review, and roll back my automationsweight 1

1 (weight) × 5 (quality) × 0.6 (partial) = 3.0 of 10 max

• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“Claude Code works directly with git. It stages changes, writes commit messages, creates branches, and opens pull requests.”
• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“Review diffs visually, run multiple sessions side by side, schedule recurring tasks, and kick off cloud sessions.”
• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“Create skills to package repeatable workflows your team can share, like `/review-pr` or `/deploy-staging`.”
• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“Hooks let you run shell commands before or after Claude Code actions, like auto-formatting after every file edit or running lint before a commit.”
• [claimed-docs] https://docs.claude.com/en/docs/claude-code/overview“CLAUDE.md is a markdown file you add to your project root that Claude Code reads at the start of every session. Use it to set coding standards, architecture decisions, preferred libraries, and review checklists.”