How real projects summarise themselves for language models.
heymegabytellms.txtheymegabyte/claude-skills/llms.txt
durable stance + stack defaults/constants - **Doctrinal rules** — 160 always-/pack-loaded rules in `rules/` (autonomy · verification · security · feature-flags · payments · …); routed via the Router's “Doctrinal principles” + pack lists - [Changelog](CHANGELOG.md) — package
ShieldNet-360llms.txtShieldNet-360/secure-vibe/docs/llms-full.txt
SecureVibe — full documentation Prevention-first security for AI-written code. This file concatenates the core docs for LLM ingestion. Source: https://shieldnet-360.github.io/secure-vibe/ ================================================================ # SOURCE: docs/index.md ================================================================ # SecureVibe Prevention-first security
ShieldNet-360llms.txtShieldNet-360/secure-vibe/docs/llms.txt
SecureVibe > Prevention-first security for AI-written code. Signed security skills shape what AI coding assistants (Claude Code, Cursor, Copilot, Codex, Windsurf, Cline, Antigravity, Devin) write at generation time; deterministic
AnayDhawanllms.txtAnayDhawan/openvidstudio/llms.txt
github.com/AnayDhawan/openvidstudio/blob/main/CODE_OF_CONDUCT.md) - Good first issues: Check the issues tab for the current list. ## Security - [Security policy](https://github.com/AnayDhawan/openvidstudio/blob/main/SECURITY.md): report vulnerabilities privately to dhawansanay@gmail.com, not as a public issue. ## Optional
cz1993llms.txtcz1993/vibe-coding-repository-standard/llms.txt
Codex-first in the current reference implementation. It does not guarantee production readiness, security, compatibility across all agents, or search visibility. ## Start here - README: README.md - White paper: WHITEPAPER.md - Getting started
anthony-chaudharyllms.txtanthony-chaudhary/dos-kernel/llms-full.txt
# DOS — the Dispatch Operating System (dos-kernel) — llms-full.txt > The one-fetch expansion of llms.txt
anthony-chaudharyllms.txtanthony-chaudhary/dos-kernel/llms.txt
through (.dos/), verdicts out (git + verdict.json) — and why that makes every host adapter thin - [Security](https://raw.githubusercontent.com/anthony-chaudhary/dos-kernel/master/SECURITY.md): the threat model and the supply-chain notes (including the `dos` name
doanbactamllms.txtdoanbactam/agent-skills-directory/public/llms.txt
Android, and cross-platform mobile development - **Automation & Agents** — CI/CD, workflows, and automation tools - **Security** — Authentication, encryption, and security tools - **Dev Tools** — Git, CLI, editors, and developer utilities - **Business & Productivity** — Workflow
getcargohqllms.txtgetcargohq/cargo-skills/llms.txt
hits come pre-annotated: findEmail (0.5) returns a status field, full MX diagnostics (provider, security gateway, records), and bonus company firmographics in the same payload. - [linkedin](https://github.com/getcargohq/cargo-skills/blob/main/cargo-gtm/provider-playbooks/linkedin.md): LinkedIn
jigarbhoye04llms.txtjigarbhoye04/MatlabMCP/llms-full.txt
Tool integration for executing commands and scripts * Local server connections for enhanced privacy and security > ⓘ Note: The Claude.ai web application does not currently support MCP. MCP features are only
me-publicllms.txtme-public/nemus/docs/llms-full.txt
Contributing Contributions are welcome! Please read [CONTRIBUTING.md](CONTRIBUTING.md) and our [Code of Conduct](CODE_OF_CONDUCT.md). Security issues: see [SECURITY.md](SECURITY.md). ## License [MIT](LICENSE) © Nemus contributors
me-publicllms.txtme-public/nemus/docs/llms.txt
/me-public/nemus/blob/main/CONTRIBUTING.md): dev setup, tests, and the PR workflow. - [Code of Conduct](https://github.com/me-public/nemus/blob/main/CODE_OF_CONDUCT.md) - [Security policy](https://github.com/me-public/nemus/blob/main/SECURITY.md): supported versions and how to report a vulnerability. ## Optional - [npm package
sandraschillms.txtsandraschi/advanced-memory-mcp/llms.txt
USAGE.md`, `FLEET.md`). - **Benny Protocol**: The "Benny Anchor" (German Shepherd) serves as the emotional and security grounding adjudicator for the Advanced Data Network. - **Pristine Root Architecture**: Repository root is optimized
sunnyday-technologiesllms.txtsunnyday-technologies/CADCLAW/docs/llms.txt
endpoint and does not control a native CAD application. It is also not a security sandbox: path-taking tools can read declared STEP, spec, rules, BOM, and metadata inputs
arikusillms.txtarikusi/deepseek-mcp-server/llms-full.txt
Core Reasoning - debug_with_reasoning(code, error?, language?) - code_review_deep(code, language?, focus: security|performance|quality|all) - research_synthesis(topic, context?, depth: brief|moderate|comprehensive) - strategic_planning(goal, context
CLOUDWERX-DEVllms.txtCLOUDWERX-DEV/gpt-image-1-mcp/.docs/llms-full.txt
when assigned to Agents | | [VS Code GitHub Copilot][VS Code] | ❌ | ❌ | ✅ | ❌ | ✅ | Supports dynamic tool/roots discovery, secure secret configuration, and explicit tool prompting | | [Windsurf Editor][Windsurf] | ❌ | ❌ | ✅ | ❌ | ❌ | Supports tools with AI Flow
dshakesllms.txtdshakes/distil/docs/llms.txt
cold-point` opts out. ## Key sources README (canonical overview, install, head-to-head table, security): https://github.com/dshakes/distil/blob/main/README.md CHANGELOG (per-version feature list): https://github.com/dshakes/distil/blob/main/CHANGELOG.md Changelog (the same CHANGELOG.md
heuremallms.txtheurema/signum/llms.txt
scenarios validate hidden acceptance criteria. Up to 3 independent AI reviews (Claude semantic, Codex security, Gemini performance). Synthesizer combines all signals into a consensus decision. PACK: Bundles contract, diff, baseline
heznpcllms.txtheznpc/AirMCP/llms.txt
www.npmjs.com/package/airmcp) - [Full Tool Reference](https://github.com/heznpc/AirMCP/blob/main/llms-full.txt) - [Contributing Guide](https://github.com/heznpc/AirMCP/blob/main/CONTRIBUTING.md) - [Security Policy](https://github.com/heznpc/AirMCP/blob/main/SECURITY.md) ## Start Here A reader that meets the module catalogue first concludes
Microsoftllms.txtmicrosoft/azure-sql-database-container/docs/llms.txt
TRUNCATE TABLE is refused while the index exists (Msg 42232), and a security policy and a vector index cannot share a table in either order
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.
