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.
SentryReads credentialsllms.txtgetsentry/dotagents/docs/public/llms.txt
filename as the subagent name. ```md --- name: code-reviewer description: Review code for correctness, security, and missing tests. --- Review the current diff and return findings with file references. ``` | Field | Type
vinkius-labsReads credentialsllms.txtvinkius-labs/mcp-fusion/docs/llms.txt
# MCP Fusion > fusion is the TypeScript framework for production MCP servers. MVA architecture, structured
clearcotelabsllms.txtclearcotelabs/clearcote-browser/llms.txt
endpoint on :9222. Run it with `--shm-size=1g -p 127.0.0.1:9222:9222 --security-opt seccomp= `; see /docker/README.md. - MCP server: `clearcote-mcp` (PyPI / npm). Profile Manager desktop app 0.12.2 (Windows
Leading-AI-IOllms.txtLeading-AI-IO/palantir-ontology-strategy/llms.txt
that models the world as nouns (objects, properties, > links) and verbs (actions, functions, dynamic security), enabling AI to > act safely on real-world operations through a branch-and-review > governance
surendranbPipes a download into a shellllms.txtsurendranb/google-analytics-mcp/docs/llms-full.txt
told to trust. Project config only applies to trusted projects, which is a deliberate security boundary rather than a bug. ```toml [mcp_servers.google-analytics] command = "uvx" args = ["google-analytics-mcp"] [mcp_servers.google-analytics.env
vstorm-collms.txtvstorm-co/agenticos/llms.txt
obligations and how they are met, the findings still open, and the release checklist. - [Security](https://vstorm-co.github.io/agenticos/security/): the threat model, what data leaves the deployment, what is encrypted where
Scottcjnllms.txtScottcjn/beacon-skill/llms.txt
docs/SECURITY.md) — Nonce strategy, timestamp validation, replay protection - [CONTRIBUTING.md](CONTRIBUTING.md) — How to contribute - [SECURITY.md](SECURITY.md) — Security disclosure policy
oliver-zehentleitnerDeletes or force-pushesllms.txtoliver-zehentleitner/keep-the-why/llms.txt
skills.sh: https://skills.sh/oliver-zehentleitner/keep-the-why/keep-the-why — backs the `npx skills add` method above - SkillsLLM: verified, passed security scan — https://skillsllm.com/skill/keep-the-why ## Core Concept Four modes. Every entry is classified on two separate
AgusMayolllms.txtAgusMayol/optics/public/llms.txt
/resources/animations): Standards for implementing animations within the design system, including timing and easing functions. ### Security [Security](https://optics.agusmayol.com.ar/resources/security): Best practices for securing applications built with the design system. ## Configuration
joshuaswarrenReads credentialsllms.txtjoshuaswarren/openclaw-engram/llms.txt
Binary lifecycle: mirror/redirect/clean stages for binary files. - Namespaces: per-principal isolation with read/write ACLs. - Secure store: at-rest encryption (encrypt-on-write; unlock to read). - Wearables: Limitless / Bee / Omi transcript
jenticllms.txtjentic/jentic-one/llms.txt
from source — prerequisites, `make install`, `make dev` or `make start-local`, and common failures. ## Security - [Hardening guide](https://raw.githubusercontent.com/jentic/jentic-one/refs/heads/main/docs/security/README.md): the threat model and a tiered set of deployment postures
alexei-ledllms.txtalexei-led/k8s-mcp-server/llms.txt
Server > MCP server for Kubernetes CLI tools — kubectl, Helm, istioctl, and ArgoCD — with security policies and Unix pipe support. K8s MCP Server implements the Model Context Protocol (MCP) to bridge
denolandllms.txtdenoland/docs/static/llms.txt
Deno > Deno is a secure JavaScript/TypeScript runtime built on V8 and Rust, > distributed as a single binary. TypeScript, formatting, linting, testing, and > a standard library work with zero configuration. Programs
garagonllms.txtgaragon/nanostack/llms.txt
framework for AI coding agents. It ships the default sprint (think -> plan -> build -> review -> security -> qa -> ship -> compound) plus a framework for declaring your own custom workflow stacks. Each phase
runesleollms.txtrunesleo/polymarket-toolkit/llms.txt
toolbox: https://github.com/runesleo/polymarket-toolkit/blob/main/docs/toolbox.md - mcp_docs: https://github.com/runesleo/polymarket-toolkit/blob/main/docs/mcp.md - mcp_npm: https://www.npmjs.com/package/polymarket-toolkit-mcp - security: https://github.com/runesleo/polymarket-toolkit/blob/main/SECURITY.md - ai_info: https://raw.githubusercontent.com/runesleo/polymarket-toolkit/main/ai-info.json - llms: https://raw.githubusercontent.com/runesleo/polymarket-toolkit/main/llms.txt ## Citation Guidance - Describe
guardanallms.txtguardana/guardana/site/llms.txt
Guardana > Guardana is open-source AI security verification. Its rule engine scans model artifacts, probes live endpoints and MCP servers, and grades completed agent runs. Use it on a laptop
tsubotaxllms.txttsubotax/melta-ui/llms-full.txt
fill="none"` でテーマカラーを継承 - 対象: Analytics（bar-chart-2, trending-up/down, activity）、Time（clock）、Security（shield, key）、Infrastructure（cloud, database, server）、Files（folder）、Payment（credit-card）、Device（monitor）、International（globe
nikolai-vysotskyiReads credentialsllms.txtnikolai-vysotskyi/trace-mcp/docs/llms-full.txt
audit` | One-shot project health: dead exports, untested code, dependency hotspots, heritage metrics | ## Quality & security | Tool | What it does | |---|---| | `scan_security` | OWASP Top-10 vulnerability scan: SQL injection, XSS, command
truenasllms.txttruenas/documentation/static/llms.txt
Network Tutorials: https://truenas.com/docs/scale/25.04/scaletutorials/network/ - Network UI Reference: https://truenas.com/docs/scale/25.04/scaleuireference/network/ ### User Management and Security - Credentials Tutorials: https://truenas.com/docs/scale/25.04/scaletutorials/credentials/ - Credentials UI Reference: https://truenas.com/docs/scale/25.04/scaleuireference/credentials/ ### Applications and Virtualization - TrueNAS
Googlellms.txtgoogle/three-live/examples/llms-full.txt
# Three-Live & XR-Live Complete LLM Reference (`llms-full.txt`) > Auto-generated from `docs/` and `skills
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.
