Claude Code scores 97/100 (Grade A), placing it among the most AI-agent-ready documentation sites evaluated. It passes 16 of 22 checks (73%), demonstrating strong support for AI coding agents. 4 items require attention to reach a perfect score.
# Agent Score Fix Report — Claude Code URL: https://code.claude.com/docs Score: 97/100 (Grade A) I need help improving the AI-readiness of the documentation at https://code.claude.com/docs. Agent Score found 1 failing checks and 3 warnings. ## Failing Checks (1) - [observability] Markdown Content Parity: 3 of 10 pages have substantive content differences between markdown and HTML (avg 13% missing) ## Warnings (3) - [content-discoverability] Llms Txt Valid: llms.txt contains parseable links but doesn't fully follow the proposed structure: https://code.claude.com/docs/llms.txt: No blockquote summary found; https://code.claude.com/llms.txt: No blockquote summary found - [page-size] Page Size Markdown: 1 of 10 pages between 50K–100K chars (max 54K) - [page-size] Page Size Html: 1 of 10 sampled pages convert to 50K–100K chars (max 54K, 0% boilerplate) ## Fix Instructions For each issue above, please: 1. Analyze the documentation site at https://code.claude.com/docs 2. Implement the specific fix 3. Verify the fix would cause the check to pass ### Common fixes: - **No llms.txt**: Create /llms.txt following https://llmstxt.org — list all doc pages in markdown format - **No .md URL support**: Configure your docs platform to serve pages at equivalent .md URLs (e.g. /docs/quickstart.md) - **No content negotiation**: Return markdown when request includes Accept: text/markdown header - **Large page size**: Reduce nav boilerplate, inline scripts, and repetitive markup - **No sitemap**: Generate /sitemap.xml listing all documentation URLs - **Auth walls**: Ensure docs pages return 200 without requiring login cookies or tokens - **No Last-Modified header**: Configure your server/CDN to include Last-Modified response headers - **Tab content hidden**: Ensure tabbed content is rendered in the HTML (not JS-only) so agents can read all variants ## Run afdocs Locally for More Detail To get deeper visibility into what's failing, run afdocs against your docs: npx afdocs https://code.claude.com/docs --fixes --verbose - **--fixes**: Adds "Fix:" lines to the output for each warn/fail check with actionable remediation steps - **-v, --verbose**: Shows per-page details (specific URLs, character counts, error codes) for checks with issues — useful for per-URL visibility into what's failing
CHECK RESULTS
How your docs scored
auth-gate-detectionAll 10 sampled pages are publicly accessible
auth-alternative-accessAll docs pages are publicly accessible; no alternative access paths needed
tabbed-content-serialization5 tab group(s) across 3 of 10 sampled pages; all serialize under 50K chars
markdown-code-fence-validityAll 181 code fences properly closed across 12 pages
section-header-quality3 page(s) with tabs found, but no section headers inside tab panels to evaluate
markdown-content-parity3 of 10 pages have substantive content differences between markdown and HTML (avg 13% missing)
llms-txt-freshnessllms.txt covers 100% of 80 sitemap doc pages
cache-header-hygieneAll 12 endpoints have appropriate cache headers
page-size-markdown1 of 10 pages between 50K–100K chars (max 54K)
page-size-html1 of 10 sampled pages convert to 50K–100K chars (max 54K, 0% boilerplate)
rendering-strategyAll 10 sampled pages contain server-rendered content
content-start-positionContent starts within first 10% on all 10 sampled pages (median 0%)
llms-txt-validllms.txt contains parseable links but doesn't fully follow the proposed structure: https://code.claude.com/docs/llms.txt: No blockquote summary found; https://code.claude.com/llms.txt: No blockquote summary found
llms-txt-existsllms.txt found at 2 location(s)
llms-txt-sizellms.txt is 15,871 characters (under 50,000 threshold)
llms-txt-links-resolveAll 10 same-origin sampled links resolve (80 total links)
llms-txt-links-markdown10/10 same-origin sampled links point to markdown content (100%)
llms-txt-directivellms.txt directive found in all 10 sampled pages, near the top of content
markdown-url-support10/10 sampled pages support .md URLs (100%)
content-negotiation10/10 sampled pages support content negotiation (100%)
http-status-codesAll 10 sampled pages return proper error codes for bad URLs
redirect-behaviorNo redirects detected across 10 sampled pages
