How real projects summarise themselves for language models.
dziksullms.txtdziksu/StructSmith/public/llms.txt
distributing StructSmith. ## Optional - [Contributing guide](https://raw.githubusercontent.com/dziksu/StructSmith/main/CONTRIBUTING.md): Development workflow and contribution requirements. - [Security policy](https://raw.githubusercontent.com/dziksu/StructSmith/main/SECURITY.md): Supported versions and responsible vulnerability reporting
jmrplensllms.txtjmrplens/libgen-mcp/llms-full.txt
# libgen-mcp — Full Reference > Version 2.0.1 | 4 tools | 4 prompts ## Tools libgen-mcp exposes
jmrplensllms.txtjmrplens/libgen-mcp/llms.txt
call invokes, and an operator may export telemetry to a collector of their own - [Security policy](https://github.com/jmrplens/libgen-mcp/blob/main/SECURITY.md): Threat model and how to report a vulnerability privately - [Headless install
kymucollms.txtkymuco/chatgpt-web-adapter/llms.txt
Provider matrix](https://github.com/kymuco/chatgpt-web-adapter/blob/main/docs/providers.md) - [Agent integration](https://github.com/kymuco/chatgpt-web-adapter/blob/main/docs/agent_integration.md) - [Architecture](https://github.com/kymuco/chatgpt-web-adapter/blob/main/docs/architecture.md) - [Security](https://github.com/kymuco/chatgpt-web-adapter/blob/main/SECURITY.md) ## Current proven product surfaces - ChatGPT: production/default conversational runtime; text, continuation, proven rich
maojiebcllms.txtmaojiebc/majia-guanyuan/llms.txt
entry: https://github.com/maojiebc/majia-guanyuan/blob/main/SKILL.md - Chinese README: https://github.com/maojiebc/majia-guanyuan/blob/main/README.md - English README: https://github.com/maojiebc/majia-guanyuan/blob/main/README.en.md - Security policy: https://github.com/maojiebc/majia-guanyuan/blob/main/SECURITY.md - Attribution: https://github.com/maojiebc/majia-guanyuan/blob/main/ATTRIBUTIONS.md ## Skill Contents - `SKILL.md`: routing layer and core
mateffyllms.txtmateffy/struktur/docs/llms-full.txt
# config import { TypeTable } from 'fumadocs-ui/components/type-table'; import { Callout } from 'fumadocs-ui/components/callout'; import
m-kisllms.txtm-kis/merlya/docs/llms.txt
OpenRouter, OpenAI, Anthropic, Ollama) - Host discovery from SSH config, known_hosts, /etc/hosts, Ansible inventory - Security scanning with severity scoring - REPL mode with autocompletion and @ mentions ## Installation ```bash pip install merlya
mohamed-ashraf-elsaedllms.txtmohamed-ashraf-elsaed/claude-agent-sdk-laravel/llms-full.txt
signature - ToolUseBlock — $id, $name, $input - ToolResultBlock — $toolUseId, $content, $isError ### AgentDefinition (Subagents) new AgentDefinition( description: 'Security reviewer', prompt: 'Find vulnerabilities', tools: ['Read', 'Grep'], model: 'sonnet' ) ### Hook Events (12 total) PreToolUse, PostToolUse
nirholasllms.txtnirholas/atomic/llms.txt
signing keys. ## Top-level files - [`README.md`](./README.md) — public-facing project README with quickstart and security notes. - [`SECURITY.md`](./SECURITY.md) — threat model, secret handling, vulnerability disclosure. - [`CONTRIBUTING.md`](./CONTRIBUTING.md) — code style, commit conventions
selftune-devllms.txtselftune-dev/selftune/llms.txt
implicit, contextual, and negative trigger types ## Optional - [PRD](https://github.com/selftune-dev/selftune/blob/HEAD/PRD.md): Product requirements document - [SECURITY](https://github.com/selftune-dev/selftune/blob/HEAD/SECURITY.md): Vulnerability reporting policy - [CODE_OF_CONDUCT](https://github.com/selftune-dev/selftune/blob/HEAD/CODE_OF_CONDUCT.md): Contributor Covenant v2.1
shalintripathillms.txtshalintripathi/saas-marketing-agents/llms.txt
authentication, sender reputation, list hygiene and suppression, engagement-signal integrity (Apple Mail Privacy Protection, security-scanner bot clicks), and the cold sending estate: secondary sending domains isolated from the brand
skein-jsllms.txtskein-js/skein-js/llms-full.txt
# skein-js — full documentation > The open-source alternative to LangGraph Platform for TypeScript: a
sno-aillms.txtsno-ai/sno-station/llms.txt
Memory Bench); no datasets, no raw runs - docs/ — images, evidence, translations, security page - tests/apps/ — public-contract tests only ## Contributing - CONTRIBUTING.md — DCO sign-off, one change per PR, which checks
Speraxllms.txtSperax/sperax-crypto-mcp/BNB-Chain-MCP/llms-full.txt
provides a standardized interface for blockchain operations, market data, security analysis, and DeFi interactions. ### Target Users - **AI Agents**: Claude, ChatGPT, and other LLM-powered assistants - **Developers**: Building blockchain-aware
Speraxllms.txtSperax/sperax-crypto-mcp/BNB-Chain-MCP/llms.txt
transfers | | **Swap/DEX** | 12 | Quotes, swaps, liquidity, arbitrage | | **Bridge** | 6 | Cross-chain transfers, status tracking | | **Security** | 20 | Honeypot detection, rug pull analysis, GoPlus | | **Staking** | 14 | Lido, LP farming, liquid staking | | **Lending
thevibeworksllms.txtthevibeworks/claude-reads-hn/llms.txt
Services | 49499867, 49504625, 49480091, 49478426, 49501611 - [2026-08-31 01:00](digests/2026/08/31-0100.org): Kernel.org, QubesOS security advisory | 49491791, 49496918, 49503601, 49497810, 49499095 - [2026-08-30 12:00](digests/2026/08/30-1200.org): California saves Linux
verivus-ossllms.txtverivus-oss/llm-cli-gateway/site/llms.txt
gateway > Secure local control plane for AI coding agents. Operate Claude Code, Codex CLI, Gemini/Antigravity, Grok Build, Mistral Vibe, Cognition Devin, Cursor Agent, and optional HTTP API providers from supported
wonsukchoillms.txtwonsukchoi/domain-experts/docs/llms.txt
lateral grain-bin wall pressure with Janssen's equation, sizing a waterway or… - [Application Security Engineer](https://domainexperts.dev/roles/application-security-engineer/): checking whether an endpoint verifies object-level authorization (not just authentication
Acacianllms.txtAcacian/aegis/docs/llms.txt
Canonical Identity - **Project name**: Agent-Aegis (also: Aegis, agent-aegis) - **What it is**: Runtime security + governance middleware for Python AI agents - **What it is not**: An LLM, an output validator
Alessandro-Pangllms.txtAlessandro-Pang/harnessmith/llms.txt
allowlists, and approval - Do not tell the user that installing the file enforces DSH security controls or verifies a real Session baseline; file presence is not Host Eval evidence
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.
