Fetches, caches, and versions documentation from web sources to provide accurate, version-specific context for AI coding agents
View and modify doc-fetcher plugin configuration settings.
Fetch and cache documentation for a library with version-specific snapshots
Generate a Claude Code skill from cached documentation for version-specific expertise
Display all cached documentation from `~/.claude/docs` including versions, sizes, update times, and associated skills.
Check for and update outdated documentation in `~/.claude/docs`.
Detects project dependencies and suggests fetching relevant documentation automatically
Fetches and caches library documentation, then generates version-specific skills for Claude Code
Main crawling and indexing logic for documentation sites, handles sitemap parsing, content extraction, and storage
Generates Claude Code skills from cached documentation with intelligent templates and auto-activation rules
Detects and fetches AI-optimized documentation formats (llms.txt, claude.txt) from documentation sites
Uses power tools
Uses Bash, Write, or Edit tools
Runs pre-commands
Contains inline bash commands via ! syntax
Bash prerequisite issue
Uses bash pre-commands but Bash not in allowed tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Fetch, cache, and version documentation from web sources to provide accurate, version-specific context for AI coding agents.
AI coding agents frequently struggle with:
Doc Fetcher solves this by creating versioned snapshots of documentation that can be cached locally and referenced by Claude Code skills, ensuring accurate, version-specific guidance.
llms.txt and claude.txt before web crawlingpackage.json and suggests fetching relevant docsDoc Fetcher uses a global cache architecture - documentation and skills are stored in your home directory and shared across all projects:
~/.claude/
├── docs/ # Cached documentation (shared across all projects)
│ ├── nextjs/
│ │ ├── 14.2.3/ # Multiple versions supported
│ │ └── 15.0.3/
│ ├── react/
│ │ └── 18.2.0/
│ └── supabase/
│ └── 2.39.0/
└── skills/ # Generated skills (available globally)
├── nextjs-15-expert/
├── react-18-expert/
└── supabase-2-expert/
Benefits:
.claude/docs folders/plugin marketplace add squirrelsoft-dev/squirrelsoft-marketplace
/plugin install doc-fetcher@squirrelsoft-dev
git clone https://github.com/squirrelsoft-dev/doc-fetcher
cd doc-fetcher
ln -s $(pwd) ~/.claude/plugins/doc-fetcher
# Fetch latest Next.js documentation
/doc-fetcher:fetch-docs nextjs
# Fetch specific version
/doc-fetcher:fetch-docs nextjs 15.0.3
# Fetch from custom URL
/doc-fetcher:fetch-docs my-lib --url https://docs.mylib.com
# List all cached docs
/doc-fetcher:list-docs
# List docs for current project
/doc-fetcher:list-docs --project
# Update specific library
/doc-fetcher:update-docs nextjs
# Update all cached docs
/doc-fetcher:update-docs --all
# Update docs matching package.json
/doc-fetcher:update-docs --project
# Generate expert skill from cached docs
/doc-fetcher:generate-skill nextjs
# Use specific template
/doc-fetcher:generate-skill nextjs --template quick-reference
# Starting a new Next.js + Supabase project
# Fetch documentation for your stack
/doc-fetcher:fetch-docs nextjs 15.0.3
/doc-fetcher:fetch-docs react 18.2.0
/doc-fetcher:fetch-docs supabase 2.39.0
# Or automatically detect and fetch from package.json
/doc-fetcher:fetch-docs --project
# Claude now has accurate context for your entire stack
# Upgrading Next.js from 14 to 15
# Fetch new version docs
/doc-fetcher:fetch-docs nextjs 15.0.0
# Generate migration guide skill
/doc-fetcher:generate-skill nextjs --template migration-guide
# Ask Claude: "What are the breaking changes in Next.js 15?"
# Keep documentation current
# Check what needs updating
/doc-fetcher:list-docs --project
# Update all project docs
/doc-fetcher:update-docs --project
/doc-fetcher:fetch-docs <library> [version] [options]npx claudepluginhub squirrelsoft-dev/squirrelsoft-marketplace --plugin doc-fetcherMeta-development toolkit for creating Skills, Subagents, Hooks, Commands, and Plugins. Accelerates Claude Code extensibility development with intelligent generators and templates.
Comprehensive workflow automation toolkit for the complete software development lifecycle. Includes 51+ specialized agents, composable workflow commands, and intelligent orchestration for requirements gathering, planning, implementation, testing, and deployment.
Import external documentation locally - bypass AI-blocking sites via Context7, WebFetch, or Playwright
Pull docs from any URL into Claude Code. Indexes static docs sites in seconds with conditional-GET caching, then exposes them as MCP tools (fetch_url, ensure_docs, list_sources, list_indexed, grep_docs, read_doc, add_source, remove_source). Local, browser-free, no API keys.
Crawl, index, and search web documentation directly inside Claude Code. Quick mode for focused lookups, deep mode for up to 100 pages with in-memory search.
Fetch up-to-date library documentation via Context7 for accurate coding
Up-to-date and secure docs search for AI agents. Search 10,000+ libraries and lock your agent to your stack with Cabinets.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.