How real projects summarise themselves for language models.
MonadWorksllms.txtMonadWorks/agentify/llms.txt
specifications into agent interface formats with a single command. Currently generates MCP Servers with security scanning; additional formats are planned. ## Quick Start ```bash npx agentify-cli transform https://petstore.swagger.io/v2/swagger.json
NickCrewllms.txtNickCrew/Claude-Cortex/site/llms-full.txt
MCPs, commands | Asset | What it is | Lifecycle | |---|---|---| | **Agent** | A specialized subagent persona (code-reviewer, security-auditor, python-pro, etc.) | Activated explicitly; persists until deactivated | | **Skill** | A focused instruction module with
NickCrewllms.txtNickCrew/Claude-Cortex/site/llms.txt
human rather than looping infinitely. ## What ships | Asset | Purpose | |---|---| | `agents/` | Specialized subagents (review, security, architecture, language pros) | | `skills/` | Skill modules with progressive disclosure | | `rules/` | Behavioral guardrails and coding conventions | | `hooks
nirholasllms.txtnirholas/UCAI/llms.txt
detects proxy contracts and fetches implementation ABIs - Creates typed tool definitions for Claude Desktop ### Security Scanner AI-powered smart contract risk analysis: - 50+ security patterns detected - Risk score
nmamanollms.txtnmamano/isomux/site/llms.txt
hardware setups - [Access and invites](https://isomux.com/docs/access-and-invites): Browser authentication and access control - [Security audit](https://isomux.com/docs/security-audit): Security model and findings ## Hosted Isomux policies - [Terms of Service](https://isomux.com
qormllms.txtqorm/platform/llms.txt
verify | mcp | preview | package | docs | audit | updates | update | version` — full reference: [api/cli.md](api/cli.md). ## Trust & security - [Bundle signing](docs/security/bundle-signing.md) — ed25519 verify-the-bundle delivery. - [Permission model](docs/security/permission-model.md) · [Security model](docs/security/security-model.md) ## Commercial
ZeroPointRepollms.txtZeroPointRepo/awesome-grok-bot/llms.txt
source at its last pass, nothing stronger. - This is a curated list, not a security review. Anything installed here runs with the permissions of whoever installed it. ## How an agent
fluttersdkllms.txtfluttersdk/wind/llms.txt
focus:`, `disabled:`, `loading:`, `selected:`, custom states. - [Dynamic rendering](https://fluttersdk.com/wind/core-concepts/dynamic-rendering.md): `WDynamic` JSON schema + security model. - [Debugging](https://fluttersdk.com/wind/core-concepts/debugging.md): `WindLogger`, `Wind.installDebugResolver()`, `Wind.installPerfResolver()` + `WindPerfCounters` (opt-in hit/miss/bypass and build counters
littlebearappsllms.txtlittlebearapps/outlook-assistant/llms.txt
/littlebearapps/outlook-assistant/main/ROADMAP.md): Active milestones (v3.11.2 tool description audit, v3.8.x carry-over, v3.12.0+ new Graph APIs) - [SECURITY](https://raw.githubusercontent.com/littlebearapps/outlook-assistant/main/SECURITY.md): Security policy, token handling, and MCP safety controls
Nagarjuna2997llms.txtNagarjuna2997/ios-agent-skill/site/llms-full.txt
Xcode for simulator workBrowser conversation Supported remote connection or portable guidance Account policy and secure hostingConnection test Tool discovery Does not establish model task success --- # How can Claude Code hooks
Nagarjuna2997llms.txtNagarjuna2997/ios-agent-skill/site/llms.txt
nagarjuna2997.github.io/ios-agent-skill/series/5.4.html) - [Memory: retain cycles agents create in closures and Combine](https://nagarjuna2997.github.io/ios-agent-skill/series/5.5.html) - [Security review of an agent-built app: keychain, ATS,…](https://nagarjuna2997.github.io/ios-agent-skill/series/5.6.html) - [Static review
curie-engllms.txtcurie-eng/curie/llms.txt
stdio MCP server, a shape a hosted harness cannot do. ## Optional - [SECURITY.md](SECURITY.md): the security posture and reporting process. - [docs/behavior-packs.md](docs/behavior-packs.md): reusable behavior packs for bundles. - [docs/onboarding.md](docs/onboarding.md
netkrllms.txtnetkr/mini-hids/llms.txt
stores ban state in SQLite, and exposes an MCP tool server for agent-native security operations. Mini-HIDS is optimized for local or single-host deployments where simple detection, understandable
proomptengllms.txtproompteng/bilig/docs/llms.txt
discovery: https://proompteng.github.io/bilig/.well-known/agent-skills/index.json legacy skill discovery: https://proompteng.github.io/bilig/.well-known/skills/index.json license: mit language: typescript security policy: https://github.com/proompteng/bilig/blob/main/SECURITY.md support policy: https://github.com/proompteng/bilig/blob/main/SUPPORT.md openssf scorecard: https://scorecard.dev/viewer/?uri=github.com/proompteng/bilig ## package
web3dev1337llms.txtweb3dev1337/agent-workspace/site/llms.txt
GitHub Repository](https://github.com/web3dev1337/agent-workspace) - [README](https://github.com/web3dev1337/agent-workspace#readme) - [Latest Release](https://github.com/web3dev1337/agent-workspace/releases/latest) - [Security Policy](https://github.com/web3dev1337/agent-workspace/blob/main/SECURITY.md) - [Terms of Use](https://agent-workspace.ai/terms.html) - [Privacy Policy](https://agent-workspace.ai/privacy.html)
yerdaulet-damirllms.txtyerdaulet-damir/awesome-solo-ai/llms.txt
Claude Code skills 2026](https://github.com/yerdaulet-damir/awesome-solo-ai/blob/main/skills/trending-2026.md): newer community skills for browser control, reasoning, security, and research (chrome-cdp-skill, cc-thinking-skills, claude-code-owasp, context-engineering-kit, Bloom
Fanfullallms.txtFanfulla/Lupin/llms.txt
CHANGELOG](https://raw.githubusercontent.com/Fanfulla/Lupin/main/CHANGELOG.md): released versions, and the known limitations stated rather than omitted - [SECURITY](https://raw.githubusercontent.com/Fanfulla/Lupin/main/SECURITY.md): the properties worth breaking (credentials never reach the config, the logs
mishrasanjeevllms.txtmishrasanjeev/grantex/web/llms.txt
Agent-to-Agent Authorization](https://docs.grantex.dev/integrations/a2a): Grant-token propagation for A2A tasks. ## Core Security and Verification - [How to Secure AI Agents](https://grantex.dev/vs/securing-ai-agents): Least privilege, consent, identity, audit
pumblusllms.txtpumblus/okf-harness/llms-full.txt
workspace](examples/ai-research-workspace/README.md) gives a small lintable workspace. - [Contributing](CONTRIBUTING.md) explains project scope and verification. - [Security](SECURITY.md) explains local data boundaries and reporting. #### Development ```bash pnpm install pnpm docs:llms pnpm
pumblusllms.txtpumblus/okf-harness/llms.txt
sample wiki content. - [Contributing](https://raw.githubusercontent.com/pumblus/okf-harness/main/CONTRIBUTING.md): contribution boundaries, development setup, and verification commands. - [Security](https://raw.githubusercontent.com/pumblus/okf-harness/main/SECURITY.md): local data boundaries, out-of-scope surfaces, and reporting contact. ## Optional - [Chinese
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.
