Skip to main content
command CX Codex

load_ai_docs · disler — Claude Code command: fetch docs into your project

load_ai_docs — a command that downloads documentation from AI platforms and saves it as markdown files for agents to reference locally. Use it when you want your sub-agents to have current docs without needing web access.

no license ★ 1,573 updated 2026-02-08

Install into Claude Code · Manually: put the files in place All methods and platforms ↓
.claude/commands/load_ai_docs.md
Open on GitHub

What load_ai_docs does

load_ai_docs reads a list of URLs from ai_docs/README.md, fetches the docs, and stores them as markdown files in your project. It checks whether cached versions exist and skips anything fresher than 24 hours; older files get replaced. Downloads run in parallel through the agent-docs-scraper sub-agent, which uses WebFetch and Firecrawl to handle different page types.

Once done, you get a report showing success or failure for each file. This matters when docs update often but you want agents to work with context they can access without going online.

What it helps with

  • collect documentation from multiple AI platforms into one project
  • keep local reference docs current without constant web calls
  • give sub-agents access to platform docs offline
  • track which documentation files are already cached and current

Example prompts for the agent

  • Run load_ai_docs to refresh all docs listed in ai_docs/README.md
  • Use /load_ai_docs and show me which files updated
  • Fetch the latest AI platform docs using load_ai_docs

How to install load_ai_docs

Manually: put the files in place

.claude/commands/load_ai_docs.md

Call it with /load_ai_docs. For all projects use ~/.claude/commands/

Questions about load_ai_docs

How do I install load_ai_docs in Claude Code?

Create .claude/commands/load_ai_docs.md at your project root and add the command definition with doc URLs. Claude Code picks it up automatically from that folder.

What does load_ai_docs do?

It downloads documentation from AI platform websites into local markdown files. Files younger than 24 hours are skipped; older ones are replaced. You get a report showing success or failure for each URL.

Which tools does the scraper use?

WebFetch for basic fetches and Firecrawl for complex pages. The agent-docs-scraper sub-agent runs in parallel for each URL in ai_docs/README.md.

Similar slash commands

All slash commands for Agent setup: memory, context, orchestration →

load_ai_docs by other authors comes first.

load_ai_docs disler load_ai_docs — a command that downloads documentation from specified URLs and saves it as markdown files via model-specific subagents. Designed for documentation benchmarking and testing AI model capabilities. CX Codex +1 ★ 1,573repo stars load-docs bmad-labs load-docs — a skill for Claude Code and Codex that loads entire documents and folders into the main agent's context. It reads every chunk directly and replies DONE. CX Codex +1 113installs load-llms-txt davila7 load-llms-txt loads external documentation from llms.txt or a custom source and adds project context. Useful when an agent needs reference material during coding. CX Codex +1 239installs update-docs sangrokjung update-docs rebuilds docs/CONTRIB.md and docs/RUNBOOK.md from package.json and .env.example, then reports which docs have gone stale. CX Codex +1 ★ 880repo stars load-issues NeoLabHQ load-issues — a skill for Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode that pulls all open issues from a GitHub repository and writes each one as a separate markdown file. CX Codex +1 1,200installs docs-curator First Fluke docs-curator — a subagent that detects documentation drift and updates MD files when code changes. Catches broken references, proposes patches, and keeps docs/**/*.md aligned with the codebase. CX Codex ★ 1,472repo stars update-project-docs hoangsonww update-project-docs keeps documentation in sync after changes to code, config, APIs, DB schema or interfaces. The agent runs it automatically when it modifies env vars, hooks, events, WebSocket messages or CLI commands. CX Codex +1 ★ 1,198repo stars

From the same set20

The whole set →
build build is a command that reads a plan file and applies its changes to a codebase. It asks for the file path if none is provided. CX Codex +1 ★ 1,573repo stars convert_paths_absolute convert_paths_absolute — a slash command that rewrites relative paths in .claude/settings.json as absolute ones. It helps when command scripts break because they run from the wrong directory. CX Codex +1 ★ 1,573repo stars fetch-docs-haiku45 fetch-docs-haiku45 retrieves online documentation using the Haiku model and saves it as markdown without cuts. CX Codex ★ 1,573repo stars fetch-docs-sonnet45 The fetch-docs-sonnet45 subagent retrieves documentation from a URL and writes it to a chosen file. Use it for documentation retrieval benchmarks. CX Codex ★ 1,573repo stars find_and_summarize find_and_summarize locates source files across target directories and creates concise two-sentence summaries in a YAML file. Useful for documenting modules without subagents. CX Codex +1 ★ 1,573repo stars create-worktree-subagent The create-worktree-subagent subagent creates isolated git worktrees for parallel development. Use it when the request explicitly delegates worktree creation to a subagent. CX Codex ★ 1,573repo stars docs-scraper docs-scraper — a subagent that fetches a documentation page by URL and saves it as a markdown file in ai_docs/. Handy when your agent needs a local copy of the docs. CX Codex ★ 1,573repo stars quick-plan quick-plan turns requirements into structured implementation blueprints stored in the specs/ folder. Useful before starting complex refactoring or new feature work. CX Codex +1 ★ 1,573repo stars

Project sponsors

Companies that keep this analytics open