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.
decionisllms.txtdecionis/agent-safe-pipeline/llms-full.txt
authority boundary in front of an existing agent, API or service without changing its code -> `agentsafe proxy --upstream ` (Homebrew, Linux packages, Docker, Kubernetes, all the same runtime): https://github.com/decionis/agent-safe-pipeline/blob/master/docs/quickstart/README.md.
decionisllms.txtdecionis/agent-safe-pipeline/llms.txt
authority boundary in front of an existing agent, API or service without changing its code -> `agentsafe proxy --upstream ` (Homebrew, Linux packages, Docker, Kubernetes, all the same runtime): https://github.com/decionis/agent-safe-pipeline/blob/master/docs/quickstart/README.md.
ScottcjnReads credentialsllms.txtScottcjn/Rustchain/llms.txt
mining? Participate in the [bounty program](https://github.com/Scottcjn/rustchain-bounties) — contribute code, write documentation, find bugs, create tutorials, or review pull requests to earn RTC rewards. ### What is the RustChain
ZeroPointRepollms.txtZeroPointRepo/awesome-hermes-skills/llms.txt
repository link, the author and a one line description. Install commands sit in fenced code blocks. ## Files - [README.md](https://raw.githubusercontent.com/ZeroPointRepo/awesome-hermes-skills/main/README.md): the whole list. Headings cover the skills built into
codepawlllms.txtcodepawl/crucible/public/llms.txt
crucible-mcp` binary. Node.js 20.19 or newer and an installed Chrome are required. - Claude Code plugin, which adds the server and both skills: `/plugin marketplace add codepawl/crucible`, then `/plugin install
manojmallickllms.txtmanojmallick/sigmap/llms-full.txt
plus blast radius — importers, affected tests/routes — with a risk label. One call for a code review or a safe edit. Lists changed files shell-free. ``` Input: { base?: string, staged?: boolean
manojmallickllms.txtmanojmallick/sigmap/llms.txt
/llms-full.txt) SigMap — the deterministic, verifiable grounding layer for AI code work. The reproducible signature-and-evidence map agents, CI, and reviewers can audit, which agentic grep cannot produce
sandbaseaiReads credentialsllms.txtsandbaseai/sandbase-harness/llms.txt
/HackSing/dsh-plugins - Awesome DSH Plugins 2026: https://github.com/Herdeny/awesome-dsh-plugins-2026 - MCP Repository: https://mcprepository.com/sandbaseai/sandbase-harness - OpenAgentSkill (code-review): https://www.openagentskill.com/skills/sandbaseai-sandbase-harness-code-review - PluginBench: https://pluginbench.com/mcp/io.github.sandbaseai/sandbase-harness - DSH Hub: https://dshhub.dev/plugins/sandbase-harness - DSH Packs
aelassasReads credentialsllms.txtaelassas/bookcars/llms-full.txt
deposit filter option in `getDepositFilterValue`. ### Plurals and Grammar Some labels are constructed dynamically in code and not only in translation files: * Plural suffixes for count values (such as days
nodetool-aillms.txtnodetool-ai/nodetool/docs/llms.txt
share links. - [On-Canvas Node Editors]({{ site.url }}/node-editors): The editors inside image, prompt, and Code nodes and how edits map to node properties. - [Templates Gallery]({{ site.url }}/templates-gallery): Browse and open
kydlikebtcllms.txtkydlikebtc/awesome-jev/llms.txt
that are projects or plugins with code count as not yet indexed by pattern: nobody has recorded reading them against the patterns. `patterns_reviewed` is the date a person
alexsergivanllms.txtalexsergivan/kwant/site/llms.txt
self-hosted AI agent orchestration](https://kwant.si/features): Teams and @mention handoffs, Dev mode code review, the Idea jar, Smart Results, Goals, model failover across accounts, spaces, routines, approvals, memory
88linPipes a download into a shellllms.txt88lin/computer-repair-skill/docs/llms.txt
Read-only diagnosis — Start with narrow checks that change nothing, recording commands, exit codes, measured values, paths, service states and timestamps. Command output is evidence, and a single anomaly
gitbutlerappllms.txtgitbutlerapp/grit/docs/llms.txt
guide](https://grit-scm.com/docs/agents/index.md): Run grit from scripts and autonomous agents — JSON output, exit codes, non-interactive use, credentials, and where to read the docs. ### Getting started - [grit init
agnt-ggllms.txtagnt-gg/agnt/docs/llms-full.txt
# AGNT API Reference — llms.txt # Auto-generated flattened API documentation for LLM consumption # Source: _API-DOCUMENTATION.md
agnt-ggllms.txtagnt-gg/agnt/docs/llms.txt
filtering, webhooks, error codes, and SDK support. - [Remote API Endpoints](https://agnt.gg/docs/api/remote-endpoints): Complete endpoint reference for the Remote API. Covers Marketplace (browse, publish, install, reviews, analytics), Users & Subscriptions (register
danielrosehillllms.txtdanielrosehill/Claude-Code-Repos-Index/docs/llms.txt
Claude Workspace templates. - [Cool Claude Code Stuff](https://github.com/danielrosehill/Cool-Claude-Code-Stuff): Curated collection of Claude Code projects and resources organized by category. ## Plugins - [Adb Ops](https://github.com/danielrosehill/Claude-ADB-Ops-Plugin): ADB (Android Debug
Atharvsinh-codezllms.txtAtharvsinh-codez/ObsidianUI/public/llms-full.txt
code-execution or file-writing tools. Your coding agent applies the downloaded files in your project with your normal approval and review settings. [HTTP registry alternative](https://www.obsidianui.dev/r/registry.json) [Agent
mixpeekPipes a download into a shellllms.txtmixpeek/amux/site/llms.txt
Examples sections vs automatic inference from skill Markdown body, example templates by skill type (code review, git workflow, documentation, deploy), parameterized examples with angle-bracket placeholders, a quality table
Ikalus1988llms.txtIkalus1988/MisakaNet/docs/llms-full.txt
gateway-incompatible-with-anthropic-format-requires-openai-proxy](https://misakanet.org/lessons/internal-gateway-incompatible-with-anthropic-format-requires-openai-proxy/) - [Lesson: js-dead-code-chain-break](https://misakanet.org/lessons/js-dead-code-chain-break/) - [Lesson: json-解析失败handling-截断-格式error](https://misakanet.org/lessons/json-解析失败handling-截断
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.
