coroboros/archivist

**The canonical Claude ecosystem reference**
Auto-synced official docs and curated Anthropic team insights, built for **deterministic local lookup** via the Claude Code CLI — no RAG, no retrieval blind spots.
- Documentation
- Using the Docs
- Recommended — Claude Code CLI (deterministic)
- Companion skill — ask-archivist
- Alternative — Claude Project (probabilistic, with limits)
- Automated Updates
- License
---
Documentation
Auto-updated mirror of the official Claude documentation, refreshed every 12h via GitHub Actions. Structure follows Claude Project Knowledge Base best practices.
Folders mirror the official upstream sitemap sections 1:1, so navigation matches platform.claude.com and code.claude.com.
| Section | Source | Link |
|---------|--------|------|
| API | platform.claude.com | docs/api |
| Agents & Tools | platform.claude.com | docs/agents-and-tools |
| Build with Claude | platform.claude.com | docs/build-with-claude |
| Manage Claude | platform.claude.com | docs/manage-claude |
| Managed Agents | platform.claude.com | docs/managed-agents |
| Test & Evaluate | platform.claude.com | docs/test-and-evaluate |
| Release Notes | platform.claude.com | docs/release-notes |
| General | platform.claude.com | docs/general |
| Claude Code | code.claude.com | docs/code |
| Insights | Curated from Anthropic team | docs/insights |
| **Cross-section topic index** | Auto-generated from H1/H2/tags | **docs/INDEX.md** |
Stay Updated
- **GitHub Releases**: Watch > Custom > Releases
---
Using the Docs
There are two ways to consume this knowledge base. They are not equivalent — pick based on the precision you need.
Recommended — Claude Code CLI (deterministic)
Claude Code reads files **directly** with Grep (full-text, deterministic) and Read (full file content). Every fact in the docs is reachable; no fact is silently dropped. Cross-references resolve dynamically because Claude can follow links across the entire mirror in one session.
This is the right path when you need surgical accuracy — writing technical docs, reviewing implementation choices against current Anthropic guidance, refining skills, cross-referencing API ↔ Code ↔ Platform guides.
Use docs/INDEX.md for cross-section topic navigation, then Grep/Read from there.
Companion skill — ask-archivist
This repo ships claude/skills/ask-archivist/SKILL.md, a companion skill that wraps the deterministic lookup workflow (INDEX Grep → section Grep → full-file Read → cite). Install it once, then ask questions in natural language — the skill auto-detects the mirror and cites the files it reads.
**Why this over the built-in claude-code-guide subagent?** Both answer the same kinds of questions, but on opposite ends of the precision/freshness tradeoff: