How real projects summarise themselves for language models.
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.
larcane97Pipes a download into a shellllms.txtlarcane97/clausona/site/llms.txt
skills`, `clausona mcp`, `clausona hooks` and the dashboard's Extensions screen list the skills, MCP servers and hooks that each Claude Code and Codex account loads in a project
MrPunyapalllms.txtMrPunyapal/laravel-auditor/docs/llms-full.txt
collectors** | 11 read-only tools that provide deterministic Laravel facts (routes, models, schema, etc.) | | **MCP server** | A bridge that lets a supported AI agent call the context tools directly | | **Finding
MrPunyapalllms.txtMrPunyapal/laravel-auditor/docs/llms.txt
focused verification and DSA reviews. - https://mrpunyapal.github.io/laravel-auditor/mcp: Register the Laravel Auditor stdio MCP server and the structured context tools it exposes. - https://mrpunyapal.github.io/laravel-auditor/rules: The evidence-first audit catalog
open-agent-ai-securityllms.txtopen-agent-ai-security/praxen/llms.txt
Applications 2026, OWASP Top 10 for Agentic AI Applications 2026, OWASP's secure MCP server development guidance, and the six-category RAISE maturity framework. ## Docs - [Overview](https://open-agent-ai-security.github.io/praxen/guide/index.html): what
skulitomllms.txtskulitom/Pixelbolt/llms.txt
animations, texture atlases, CSS and a Canvas player through a CLI or local stdio MCP server. Example output: [a library scene drawn and animated with Pixelbolt](https://raw.githubusercontent.com/skulitom/Pixelbolt/main/showcase/gallery/library.gif). Claude
sema-lispllms.txtsema-lisp/sema/playground/llms.txt
topic. - [Model Context Protocol](https://sema-lang.com/docs/mcp): install and use the native `sema mcp` server, including notebook and user-defined `deftool` tools. - [AI Catalog](https://sema-lang.com/.well-known/ai-catalog.json): canonical machine-readable
ofershapllms.txtofershap/real-browser-mcp/llms.txt
real-browser-mcp > Local MCP server + Chrome extension that connects AI coding agents to the user's real Chrome: existing tabs, cookies, SSO, and logins. Not a headless browser
ThreatRecallllms.txtThreatRecall/zettelforge/docs/llms.txt
Agent](how-to/integrate-llm-agent.md): Agent integration via `get_context()`, `ZettelForgeRetriever` (LangChain), or the MCP server ## Tutorials - [Quickstart](tutorials/01-quickstart.md): First memory stored in under 5 minutes - [Ingest a CTI Report](tutorials/02-first-cti-report.md
oldskultxollms.txtoldskultxo/aictx/docs/llms-full.txt
teams, with secret redaction on portable artifacts. - MCP: includes a local Model Context Protocol (MCP) server that exposes repo-local continuity as MCP tools, resources, and prompts. - Plugins: ships plugin
Synthesys-Labllms.txtSynthesys-Lab/agentize/docs/llms.txt
Create custom plugins to extend Claude Code with slash commands, agents, hooks, Skills, and MCP servers. - [Plugins reference](https://code.claude.com/docs/en/plugins-reference.md): Complete technical reference for Claude Code plugin system, including
ThinkEx-OSSllms.txtThinkEx-OSS/thinkex/public/llms.txt
research, and creation. Use the product documentation for supported behavior. ThinkEx currently exposes an MCP server for agent integrations; it does not publish a general-purpose REST API, OpenAPI specification
whobot-aiPipes a download into a shellllms.txtwhobot-ai/openclaw-whobot-skill/docs/llms-full.txt
ClawHub 条目 `openclaw-whobot-skill` 是基于知识库的问答 Skill，没有业务操作能力。新版装好后请在 OpenClaw 中停用或卸载旧版，避免同一句话触发两个 Skill。 专用仓库里保留的 `mcp-server/` 和 `references/knowledge.md` 属于旧版知识库，与新版 CLI 流程无关，不需要安装。 --- # Cursor Cursor 的 Agent 会在启动时发现 Skill，并根据描述自动选用
monteslullms.txtmonteslu/vibe-eyes/llms.txt
vibe-eyes > MCP server that lets LLMs "see" browser games by converting canvas content to vectorized SVG and collecting debug info (console logs, errors, exceptions). ## Architecture ``` Browser (canvas game) → vibe
undergroundrapllms.txtundergroundrap/UEFN-TOOLBELT/llms.txt
/WO-004 hardening. That is Toolbelt's own > surface, not Epic's official UEFN MCP server. ## What this is UEFN Toolbelt is an open-source (AGPL-3.0) tool suite for UEFN
ZeroPointRepollms.txtZeroPointRepo/awesome-grok-bot/llms.txt
Grok Bot skills, plugins, and MCP servers > Curated directory of skills, plugins, MCP servers and self-hosted alternatives for Grok Bot, the always-on AI teammate from xAI/SpaceXAI and Cursor
ariffazilllms.txtariffazil/arifOS/llms.txt
machine decision metrics ## A2A Protocol — Peer-to-Peer Collaboration In addition to MCP (which handles direct client-server data and tool access), the arifOS federation utilizes the **Agent-to-Agent
ariffazilllms.txtariffazil/arifOS/static/llms-full.txt
SEAL = all floors passed. See Nine-Signal doctrine for Dwibahasa label semantics. - `status: healthy`: MCP server is responding. Does not certify individual tool accuracy. --- ## Tool Namespace Exposure **Current public tool
Kanevryllms.txtKanevry/session-orchestrator/site/llms.txt
covered by CI. Native Windows use is untested; shell hooks and the optional MCP server need WSL or Git Bash. Optional telemetry is off until consent. By default, session-start
Rtur2003llms.txtRtur2003/Claude-Code-Promts-Skills/llms.txt
lifecycle automation: ./prompts/english/agents/hooks-automation-prompt.md - Build an agent programmatically (Agent SDK): ./prompts/english/workflows/agent-sdk-guide.md - Evaluate skills, plugins, MCP servers, and agent toolkits: ./prompts/english/workflows/ecosystem-discovery-guide.md ## Building software (project-type prompts) - Web frontend: ./prompts/english/project-types/web-development-prompt.md - API: ./prompts/english/project-types/api-development-prompt.md - Full
cloud-ru-techllms.txtcloud-ru-tech/mcp-server-mattermost/llms.txt
Mattermost MCP Server > MCP server providing 37 tools for Mattermost integration: > channels, messages, reactions, threads, users, teams, files, and bookmarks. ## Docs - [Quick Start](https://raw.githubusercontent.com/cloud-ru-tech/mcp-server-mattermost/main/docs/quickstart.md): Installation, local token setup
A markdown file at a website's root that gives language models a short guide to the site and links to the pages worth reading.
The same idea with the content included, so an agent can read the documentation in one request.
Agents and tools that fetch documentation on someone's behalf. It's a proposal, not a standard, and support varies.
Start with a one-line summary, then sections of links with a sentence each. The examples here show what real projects do.
