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.
dr34mhacksllms.txtdr34mhacks/XSSNow/llms.txt
Search Optimization > XSSNow is a free, open-source XSS payload database and security research platform for ethical penetration testing and bug bounty hunting. ## About XSSNow provides 1000+ curated Cross-Site
KimYx0207llms.txtKimYx0207/Meta_Kim/llms.txt
changes. Upgrade to `npm run meta:verify:all` for install, runtime, hook, dependency, package, security, or release-grade changes. ## Public Claims Boundary Safe claims: - Meta_Kim has default formal projections
OdyseeTeamReads credentialsllms.txtOdyseeTeam/odysee-frontend/llms.txt
# Odysee Platform Technical Reference (`llms.txt`) This file is a contributor-focused, source-verified technical
wazuhllms.txtwazuh/wazuh-documentation/source/llms.txt
work together. - **[Use cases](https://documentation.wazuh.com/current/getting-started/use-cases/index.md)** Examples of how Wazuh addresses common security challenges, grouped into endpoint security, threat intelligence, security operations, and cloud security. Covers configuration assessment, file
jfarcandllms.txtjfarcand/mirroir-mcp/llms.txt
runner/docs/mirroir-dotfile.md) - [SAMPLE.md format](runner/docs/sample-md-format.md) - [Drift and accept](runner/docs/drift-and-accept.md) - [Playwright setup](runner/docs/playwright-setup.md) - [CI integration](runner/docs/ci-integration.md) ## Security & Permissions **Fail-closed by default.** Without configuration, only read-only tools are exposed. Mutating tools
loulanyuellms.txtloulanyue/awesome-claude-notes/llms.txt
target Provenance and support: - Upstream source: https://github.com/affaan-m/ECC - Distribution repository: https://github.com/loulanyue/awesome-claude-notes - Security reports: use the repository Security tab, not a public Issue
aws-samplesPipes a download into a shellllms.txtaws-samples/sample-well-architected-skills-and-steering/llms.txt
agents Well-Architected aware. When loaded, you should apply the six pillars (Operational Excellence, Security, Reliability, Performance Efficiency, Cost Optimization, Sustainability) to architecture discussions, code reviews, and design decisions. ## Installation
billy-enrizkyReads credentialsllms.txtbilly-enrizky/openbrowser-ai/stress-tests/llms-full.txt
openbrowser import BrowserProfile profile = BrowserProfile( headless=True, viewport_width=1280, viewport_height=720, disable_security=False, extra_chromium_args=["--disable-gpu"], record_video_dir="./recordings", proxy={ "server": "http://proxy.example.com:8080", "username
tawrootPipes a download into a shellllms.txttawroot/antigravity-cleaner/website/llms.txt
РФ)](https://tawroot.github.io/antigravity-cleaner/blog-google-antigravity-russia-403.html) - [Full Troubleshooting & Diagnostic Matrix](https://tawroot.github.io/antigravity-cleaner/troubleshooting.html) - [Frequently Asked Questions & Security FAQ](https://tawroot.github.io/antigravity-cleaner/faq.html) - **License**: Apache-2.0 (100% auditable, offline, zero-telemetry) - **Supported Platforms**: Linux
mattrobinsonsrePipes a download into a shellllms.txtmattrobinsonsre/terrapod/llms.txt
summary line) and naming every gate that can block (mandatory policy sets, enforced security scans, post-plan run tasks) and how each ruled — passes included, in the order
nirholasReads credentialsllms.txtnirholas/three.ws/llms-full.txt
# three.ws > Open-source platform for 3D AI agents. Turn text or a photo into
nirholasPipes a download into a shellllms.txtnirholas/three.ws/public/llms-full.txt
embed try to boot, and name the exact line to change: a Content-Security-Policy that dropped the runtime, a container with no height, a private agent id, WebGL turned
QVerisAIPipes a download into a shellllms.txtQVerisAI/QVerisAI/agent/llms-full.txt
search engines (Google, Tavily) - **Safety:** "Call" is safer than "execute" for LLM perception — avoids security trigger concerns with remote execution - **Semantic precision:** These three verbs map precisely to agent workflow
UKGovernmentBEISllms.txtUKGovernmentBEIS/control-arena/docs/llms.txt
Control experiments built on top of Inspect AI, created by the UK AI Security Institute. It provides evaluation settings, control protocols, monitors, and analysis tools for designing and testing safety
deinfreullms.txtdeinfreu/hytale-server-container/docs/llms.txt
ARM64 architectures, runs as a non-root user by default for security, and includes the `hytale-downloader` CLI tool for managing server binaries and performing in-game updates without rebuilding
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
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
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
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.
