This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Comprehensive archive of everything Anthropic publishes for building with Claude. 3,900+ docs from 12 sources; active sources auto-updated four times daily (blog archive frozen, see Fetcher).
scripts/fetcher.py -- single-file multi-source fetcher.
Sources: code.claude.com, platform.claude.com, claude.com/docs, modelcontextprotocol.io, support.claude.com (sitemap + .md), github.com/anthropics/* (10 repos). anthropic.com blog (engineering/research/news) is a FROZEN archive as of 2026-07: the site is HTML-only and the jina.ai proxy path was removed.
Five rules keep the archive honest, all learned the hard way:
- Discovery surfaces are incomplete. Sitemaps and llms.txt undercount what a site serves, so every full run also refetches what is already on disk. Without this, 1,560 de-indexed-but-live API pages sat stale for seven weeks.
- The archive must be able to shrink. Full runs reap files whose URL is gone (404/410 or HTML shell). Only markup is deleted automatically; real markdown that died upstream is reported for a human. A >200-file reap is refused outright as an upstream outage.
- A redirect means the content belongs elsewhere. If a fetch lands on a
different path, the body in hand is the target's; writing it back to the
requested path misattributes it. That is how the 471KB
release-notes/system-prompts.mdbriefly became the 3.7KB overview it now redirects to, after upstream split it into per-model pages. - A known failure must not look like a new one.
tombstones.jsonrecords every URL confirmed gone, so a page that died once is counted quietly on later runs instead of re-reported. Only new deaths and resurrections are printed loudly, and the success rate is computed over live docs — 123 standing failures pinning it at 96.9% would hide the next real breakage. - A discovery only counts once it is a file.
discovery.jsonrecords what exists upstream thatsources.jsondoes not: unknown redirect targets, new anthropics repos, and whether each domain serves.mdat all. Printing it was not enough — the pipeline had loggedsupport.claude.com -> academy.claude.comfor weeks into an Actions log with no reader, and a human found those 725 pages by chasing a dead article. The decision agent readsgit status, so a new source now arrives as a diff.
uv run scripts/fetcher.py # Fetch everything
uv run scripts/fetcher.py --section mcp # Single section
uv run scripts/fetcher.py --tree # Show sources
uv run scripts/fetcher.py --discover # Probe for new sources
uv run scripts/fetcher.py --no-reap # Report dead pages, delete noneA full run refreshes discovery.json on its own; --discover is the manual
probe and writes the same file. Neither adds a source — that stays a human
decision. discovery.json.review is the actionable list: domains reachable
and serving markdown that nothing fetches yet. Empty is the healthy state.
Sections: claude-code, api, platform, mcp, github, support,
products, all
Source registry: sources.json
Confirmed-dead URLs: tombstones.json (self-maintaining; an entry disappears
if the URL answers again)
Sources we do NOT hold: discovery.json (self-maintaining; regenerated by
every full run)
Architecture: REFACTOR.md
When adding new sections:
- Add source to
sources.json - Add fetch logic + output path mapping to
fetcher.py - Test:
uv run scripts/fetcher.py --section <name> - Update this file's doc references below
Reference documentation files in this repository when providing guidance.
Use these paths to reference documentation when helping users:
@./content/en/docs/claude-code/overview.md- Claude Code overview and capabilities@./content/en/docs/claude-code/quickstart.md- Getting started guide@./content/en/docs/claude-code/setup.md- Installation and setup@./content/en/docs/claude-code/settings.md- Configuration and permissions setup@./content/en/docs/claude-code/common-workflows.md- Common usage patterns@./content/en/docs/claude-code/memory.md- Memory management and CLAUDE.md@./content/en/docs/claude-code/interactive-mode.md- Keyboard shortcuts and interactive features@./content/en/docs/claude-code/slash-commands.md- Available slash commands@./content/en/docs/claude-code/hooks.md- Hooks reference@./content/en/docs/claude-code/hooks-guide.md- Hooks guide@./content/en/docs/claude-code/troubleshooting.md- Problem solving@./content/en/docs/claude-code/cli-reference.md- Command line interface reference@./content/en/docs/claude-code/jetbrains.md- JetBrains IDE integration@./content/en/docs/claude-code/vs-code.md- VS Code integration@./content/en/docs/claude-code/desktop.md- Claude Code desktop app@./content/en/docs/claude-code/claude-code-on-the-web.md- Claude Code on the web@./content/en/docs/claude-code/slack.md- Claude Code in Slack@./content/en/docs/claude-code/mcp.md- Model Context Protocol@./content/en/docs/claude-code/github-actions.md- GitHub Actions integration@./content/en/docs/claude-code/gitlab-ci-cd.md- GitLab CI/CD integration@./content/en/docs/claude-code/sdk/migration-guide.md- SDK migration guide@./content/en/docs/claude-code/third-party-integrations.md- Third-party integrations@./content/en/docs/claude-code/devcontainer.md- Development containers@./content/en/docs/claude-code/security.md- Security considerations@./content/en/docs/claude-code/sandboxing.md- Sandboxed bash tool@./content/en/docs/claude-code/iam.md- Authentication and permissions@./content/en/docs/claude-code/monitoring-usage.md- OpenTelemetry monitoring@./content/en/docs/claude-code/analytics.md- Analytics and usage tracking@./content/en/docs/claude-code/costs.md- Cost management@./content/en/docs/claude-code/data-usage.md- Data usage policies@./content/en/docs/claude-code/legal-and-compliance.md- Legal and compliance@./content/en/docs/claude-code/amazon-bedrock.md- Amazon Bedrock integration@./content/en/docs/claude-code/google-vertex-ai.md- Google Vertex AI integration@./content/en/docs/claude-code/microsoft-foundry.md- Microsoft Foundry integration@./content/en/docs/claude-code/llm-gateway.md- LLM gateway configuration@./content/en/docs/claude-code/model-config.md- Model configuration@./content/en/docs/claude-code/network-config.md- Network configuration@./content/en/docs/claude-code/terminal-config.md- Terminal configuration@./content/en/docs/claude-code/output-styles.md- Output styling and formatting@./content/en/docs/claude-code/statusline.md- Status line configuration@./content/en/docs/claude-code/checkpointing.md- Session checkpointing@./content/en/docs/claude-code/headless.md- Headless mode@./content/en/docs/claude-code/plugins.md- Plugin system@./content/en/docs/claude-code/plugins-reference.md- Plugin reference@./content/en/docs/claude-code/plugin-marketplaces.md- Plugin marketplaces@./content/en/docs/claude-code/skills.md- Claude Skills@./content/en/docs/claude-code/sub-agents.md- Sub-agents@./content/CHANGELOG.md- Claude Code GitHub CHANGELOG
content/en/api/- API reference (1,500+ docs)content/en/build-with-claude/- Platform features, streaming, batchcontent/en/agents-and-tools/- Tool use, agent skills, MCP tunnelscontent/en/manage-claude/- Admin, billing, organizationscontent/en/managed-agents/- Managed agents APIcontent/en/test-and-evaluate/- Testing and evaluation
content/claude/claude-tag/- Claude Tag / Claude in Slack (65)content/claude/government/- Government offerings (38)content/claude/connectors/- Connectors, building + publishing (33)content/claude/claude-science/- Claude for Science (29)content/claude/third-party/- Bedrock, Vertex, Foundry desktop setups (28)content/claude/office-agents/- Claude for Excel, Word, PowerPoint, Outlook (12)content/claude/cowork/- Claude Cowork (6)
content/en/release-notes/system-prompts/- Claude.ai system prompts, one page per model (split from a single file upstream on 2026-08-24)content/en/models/- Per-model overviews and "what's new" pages
content/mcp/docs/- Getting started, build client/servercontent/mcp/specification/- Protocol spec versionscontent/mcp/seps/- Specification Enhancement Proposalscontent/mcp/community/- Governance, working groups
content/blog/engineering/- "Building Effective Agents", tool use, harness designcontent/blog/research/- Research paperscontent/blog/news/- Model releases, announcements
content/github/cookbooks/- 164 recipes + notebookscontent/github/skills/- 90 official Agent Skillscontent/github/plugins-official/- 266 plugin docscontent/github/courses/- 80 prompt engineering notebookscontent/github/code-action/- GitHub Actions docscontent/github/sdk-python/- Python SDK referencecontent/github/sdk-typescript/- TypeScript SDK reference
content/ 3,900+ files
en/docs/claude-code/ Claude Code + Agent SDK (198)
en/api/ API reference (1,900+)
en/build-with-claude/ Platform features
en/agents-and-tools/ Tool use, agent skills
claude/ Product docs (215)
mcp/ MCP protocol spec (373)
blog/ Engineering, research, news
github/ 10 repos (718 files)
support/ Help articles (365)
scripts/
fetcher.py Multi-source fetcher
sources.json Source registry