agentleFS
Sign inStart free
escapeboyescapeboy/claude-code-kit/llms.txt

claude-code-kit

llms.txt92 starsChanged 24 days agoMITView on GitHub

A library of skills, mods, subagents, hooks, slash commands and guides for Claude Code. Agents installing parts of it for a user should follow INSTALL.md: inspect the environment, propose a selection, install from the latest release tag without overwriting user files, then verify. Start with INSTALL.md. Raw files: https://raw.githubusercontent.com/escapeboy/claude-code-kit/<tag>/<path>. Releases: https://github.com/escapeboy/claude-code-kit/releases

We split this llms.txt into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Start with INSTALL.md. Raw files: https://raw.githubusercontent.com/escapeboy/claude-code-kit/<tag>/<path>.

    line 5

≈ “Common” is an estimate: at least 1 in 5 of the 3,225 llms.txt files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
llms.txt
# claude-code-kit

> A library of skills, mods, subagents, hooks, slash commands and guides for Claude Code. Agents installing parts of it for a user should follow INSTALL.md: inspect the environment, propose a selection, install from the latest release tag without overwriting user files, then verify.

Start with [INSTALL.md](https://github.com/escapeboy/claude-code-kit/blob/master/INSTALL.md). Raw files: `https://raw.githubusercontent.com/escapeboy/claude-code-kit/<tag>/<path>`. Releases: https://github.com/escapeboy/claude-code-kit/releases

## Install

- [INSTALL.md](https://github.com/escapeboy/claude-code-kit/blob/master/INSTALL.md): agent runbook — bundles, skill dependencies, install steps per component type, verification, updates
- [CHANGELOG.md](https://github.com/escapeboy/claude-code-kit/blob/master/CHANGELOG.md): what changed between tags

## Installable components

- [Skills](https://github.com/escapeboy/claude-code-kit/tree/master/01-global-optimization/skills): 18 skills → `~/.claude/skills/<name>/` (agent-ready, agent-team, cache-inspector, code-research, codebase-memory, company, confidence-check, continuity, ctx, decision-classify, init-project, optimize, self-improve, sprint-orchestrate, sync-features, ui-ux-review, update-docs, video-digest)
- [Mods marketplace](https://github.com/escapeboy/claude-code-kit/tree/master/17-mods/marketplace): `ai-prompts-mods`, 13 Claude Code mods (≥ 2.1.287) with tests; `company-hq` adds an optional local read-only dashboard for `/company` runs (python3 ≥ 3.9) and `sprint-orchestrate` keeps a `## Tasks` checklist it reads
- [Subagents](https://github.com/escapeboy/claude-code-kit/tree/master/10-subagents/examples): 8 agent definitions → `~/.claude/agents/`
- [Security hooks](https://github.com/escapeboy/claude-code-kit/tree/master/13-security-hardening/hooks): PreToolUse guards with tests
- [Productivity hooks](https://github.com/escapeboy/claude-code-kit/tree/master/01-global-optimization/hooks): shell-habits, package-version check, memory load
- [Slash commands](https://github.com/escapeboy/claude-code-kit/tree/master/07-custom-commands): debug, deploy, i18n, perf, qa, refactor, retro, seo, content-review
- [Global rules](https://github.com/escapeboy/claude-code-kit/tree/master/01-global-optimization/system-prompts): sections to merge into `~/.claude/CLAUDE.md`

## Guides

- [01 Global optimization](https://github.com/escapeboy/claude-code-kit/blob/master/01-global-optimization/guide.md): one-time `~/.claude/` setup
- [02 Project activation](https://github.com/escapeboy/claude-code-kit/blob/master/02-project-activation/guide.md): per-project Serena memories
- [03 Custom skills](https://github.com/escapeboy/claude-code-kit/blob/master/03-custom-skills/guide.md): writing skills
- [05 Token optimization](https://github.com/escapeboy/claude-code-kit/blob/master/05-token-optimization/guide.md)
- [06 Advanced patterns](https://github.com/escapeboy/claude-code-kit/tree/master/06-advanced-patterns): multi-agent, Agent Teams, sprint orchestration
- [10 Subagents](https://github.com/escapeboy/claude-code-kit/blob/master/10-subagents/guide.md)
- [13 Security hardening](https://github.com/escapeboy/claude-code-kit/blob/master/13-security-hardening/guide.md)
- [16 Autonomous agents](https://github.com/escapeboy/claude-code-kit/blob/master/16-autonomous-agents/guide.md): unattended runs, heartbeat
- [17 Mods](https://github.com/escapeboy/claude-code-kit/blob/master/17-mods/guide.md)

## Optional

- [09 Laravel](https://github.com/escapeboy/claude-code-kit/tree/master/09-laravel-mcp-integration), [11 Mobile](https://github.com/escapeboy/claude-code-kit/tree/master/11-mobile-development), [12 Desktop](https://github.com/escapeboy/claude-code-kit/tree/master/12-desktop-development), [14 WebMCP](https://github.com/escapeboy/claude-code-kit/tree/master/14-webmcp), [15 context-mode](https://github.com/escapeboy/claude-code-kit/blob/master/15-context-mode/guide.md), [04 Research integration](https://github.com/escapeboy/claude-code-kit/tree/master/04-research-integration)
- [01 setup-agent.md](https://github.com/escapeboy/claude-code-kit/blob/master/01-global-optimization/setup-agent.md): older all-in-one setup prompt for an empty `~/.claude/`

Download now (ZIP)

  • In this repositoryOne other file it gives its agents.

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free