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.
ifBarsllms.txtifBars/blender-agent-studio/llms.txt
ifBars/blender-agent-studio codex plugin add blender-agent-studio@blender-agent-studio ``` Install in Claude Code: ```bash claude plugin marketplace add ifBars/blender-agent-studio claude plugin install blender-agent-studio@blender-agent-studio ``` After
dykyi-romanllms.txtdykyi-roman/awesome-claude-code/llms.txt
/acc:generate-test ` | Generate tests for file/folder | | `/acc:audit-test ` | Audit test quality | | `/acc:code-review [branch] [level]` | Multi-level code review | | `/acc:bug-fix ` | Automated bug diagnosis
supernovae-stllms.txtsupernovae-st/nika/llms.txt
Ends with the current limits. - [docs/usage/conversational-session.md](docs/usage/conversational-session.md): Bare `nika` on a terminal — describe · clarify · review · save (`yes`) · run (`run it`) · inspect (`/proof`). Provider keys come from the environment (DeepSeek example
Calibre-Labsllms.txtCalibre-Labs/reforge-ai-evals/llms.txt
governance, experience) and release thresholds, v1 from the PRD and v2 from trace codes - [Trace review app skill](https://github.com/Calibre-Labs/reforge-ai-evals/blob/main/skills/trace-review-app/SKILL.md): build a one-file trace review
arthjeanllms.txtarthjean/paneflow/llms.txt
access. - Auto-submit is opt-in; the default product loop is human-reviewed prompt prefill. - Keep all code changes cross-platform across Linux, macOS, and Windows
MikkoParkkolallms.txtMikkoParkkola/trvl/llms.txt
/usr/local/bin trvl ## MCP Server Setup (for AI assistants) Command: trvl mcp Transport: stdio Claude Code: claude mcp add trvl --transport stdio -- trvl mcp Claude Desktop: Add {"mcpServers":{"trvl":{"command":"trvl
escapeboyllms.txtescapeboy/claude-code-kit/llms.txt
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
sfrangulovPipes a download into a shellllms.txtsfrangulov/claude-code-handbook-ru/llms-full.txt
install superpowers@claude-plugins-official ``` В наборе 14 связанных скиллов (TDD, brainstorming, systematic-debugging, code-review, planning, parallel-agents, subagent-driven-development и другие). Добавлять сторонний маркетплейс больше не нужно
vouchdevllms.txtvouchdev/vouch/llms.txt
Claude Code wiring step if applicable. ## Host integrations - [openclaw.plugin.json](https://raw.githubusercontent.com/vouchdev/vouch/main/openclaw.plugin.json): OpenClaw plugin manifest. Declares the MCP server, the four bundled slash commands, the trust boundary (review-gated writes
hyperb1issPipes a download into a shellllms.txthyperb1iss/lucidity-mcp/docs/llms-full.txt
from the community! Please review our [contributing guidelines](https://github.com/modelcontextprotocol/.github/blob/main/CONTRIBUTING.md) for details on how to submit changes. All contributors must adhere to our [Code of Conduct](https://github.com/modelcontextprotocol/.github/blob/main/CODE_OF_CONDUCT.md).
ridgesaiReads credentialsllms.txtridgesai/ridges/llms.txt
contract. The documented mining workflow submits code for platform evaluation and does not require operating a public miner server or renting a GPU. Reviewed against public documentation and repository source
vitaecontextllms.txtvitaecontext/vitaecontext/llms-full.txt
include: - Shared bundle - Claude Code - Codex - Gemini CLI - Antigravity CLI - OpenCode - Cursor - Windsurf - Roo Code - IBM Bob - Grok Provider behavior is not identical. Some environments use native skill loading. Some
adelinamartllms.txtadelinamart/robrain/llms.txt
pricing. Decisions are captured passively from coding sessions (no tagging) and shared across Claude Code, Cursor, GitHub Copilot, Codex CLI, Hermes, and eve agents — decide in one tool, remembered
akutishevskyllms.txtakutishevsky/nutrition-mcp/public/llms.txt
them again by name, track macros, water, body weight and body measurements, review nutrition history, and import an existing food diary from another app — entirely through conversation, with no separate
FranciscoThiesenllms.txtFranciscoThiesen/mirror_bridge/llms-full.txt
--- # FILE: README.md --- # Mirror Bridge **Write C++ once, bind everywhere — automatically.** [](https://github.com/FranciscoThiesen/mirror_bridge/actions/workflows/test.yml)
jorgerosalllms.txtjorgerosal/wordpress-skills/docs/llms.txt
Code: https://jorgerosal.github.io/wordpress-skills/guides/wordpress-release-engineering-checklist.html ## What this repository contains - Claude Code plugin skills for WordPress code review - Parallel Codex skill wrappers for the same WordPress domains - Slash commands for full reviews
gizmaxReads credentialsllms.txtgizmax/Sandcastle/llms-full.txt
real limit. ALWAYS pair an acp step with deterministic verification (a `code` step running `git diff`) plus a review: `stopReason: end_turn` means the turn ended, not that the task
ThreeMoonsLabReads credentialsllms.txtThreeMoonsLab/agents-shipgate/llms-full.txt
tool calls, LLM calls, or network access. - **Host-configuration review:** `agents-shipgate diff` shows what a change does to declared coding-agent configuration — `.claude/settings.json`, `.mcp.json`, hooks, Codex, Cursor
ThreeMoonsLabllms.txtThreeMoonsLab/agents-shipgate/llms.txt
install agents-shipgate`. - Install with uv: `uv tool install agents-shipgate`. - Review a coding-agent configuration change from the PR branch: `agents-shipgate diff` (add `--base origin/ ` when
trustablllms.txttrustabl/agent-reliability-analyzer/llms.txt
flags, exit codes, output formats. - [ARCHITECTURE](https://raw.githubusercontent.com/trustabl/agent-reliability-analyzer/main/ARCHITECTURE.md): the implementer's reference — package layout, the scan pipeline (recon → inventory → policy selection → analysis → scoring → review), the data model, the rules
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.
