How real projects summarise themselves for language models.
JAYcodrllms.txtJAYcodr/claude-code-ultimate-guide-zh/llms-full.txt
lets developers interact with Claude directly from the terminal to write, edit, debug, and review code. Unlike IDE plugins, it has full filesystem access, can run shell commands, and works
JAYcodrllms.txtJAYcodr/claude-code-ultimate-guide-zh/llms.txt
cc.bruniaux.com ### For Templates - 186 Production Templates: https://github.com/FlorianBruniaux/claude-code-ultimate-guide/tree/main/examples - Agents: backend-architect, security-guardian, code-reviewer, debugger, devops-sre, adr-writer - Commands: /pr, /commit, /release-notes, /diagnose, /generate-tests, /optimize, /git-worktree - Hooks
jrullanllms.txtjrullan/ducklab/llms.txt
Ducklab > Multi-LLM development harness: brief → requirements → spec → plan → build → > review → release, with real verification gates. Local-first (llama.cpp, > vLLM, any OpenAI-compatible or Anthropic endpoint), self-hosted, no > telemetry
Karthick-Ramachandranllms.txtKarthick-Ramachandran/persist-os/llms.txt
doctor`. No network calls, no telemetry, no AI API calls, no code generation. Persist OS writes structured, reviewable memory (product intent, architecture decisions, module ownership, testing and security expectations
m3dcodiellms.txtm3dcodie/prompt-contract/llms.txt
through structured "Contracts" and "Cognitive Archetypes." This project provides a professional alternative to "Vibe Coding" by treating LLM interactions as governed system architecture. It includes foundational theory, structured contract layers
mcpwarellms.txtmcpware/IntentProbe/llms-full.txt
sentence summary IntentProbe is a local scanner for MCP servers, AI agent tools, Claude Code skills, packages, and runtime tool events. It runs a tool description or prompt through
mcpwarellms.txtmcpware/IntentProbe/llms.txt
batch`, `runtime`. GitHub Action: `mcpware/IntentProbe@main`. Runtime hook for Claude Code PreToolUse. - Research preview, a local registration-time review signal, NOT a hard security boundary. ## Install ``` pip install intentprobe intentprobe
melbinjpllms.txtmelbinjp/jules-prompts/llms.txt
channel gets the next route, never a verdict on the idea. - [Security Review of Agent-Written Code](https://jules-prompts.wecanuseai.com/.well-known/agent-skills/security-review-agent-code/SKILL.md): To review a change an agent wrote for the security
mikusnuzllms.txtmikusnuz/agent-link-mcp/llms.txt
returned together. Accepts array of agent specs with individual model/thinking/context settings. Great for parallel code reviews, getting multiple opinions, or distributing subtasks. ### reply Continue a conversation with a spawned agent
occasiolabsllms.txtoccasiolabs/occasio/web/llms.txt
contacted and with what payloads. - Compliance evidence: signed, verifiable record of AI-assisted code changes. - Incident review: replay any past session from the local ledger. ## Links - Website: https://useoccasio.com
phonowellllms.txtphonowell/invoke-opencode-acp/llms.txt
protocol to save tokens. Primary use cases (EN): - Multi-file refactors and batch operations - Code reviews or long-running tasks via subagent Keywords (EN): claude-code, opencode, acp-protocol, json
saifeldeen911llms.txtsaifeldeen911/actionfence/llms-full.txt
invocation spend cap in major currency units. - `currency` (string, optional): ISO 4217 currency code. - `requires_human_approval` | `boolean` | `false` | When true, pauses evaluation only if `onApprovalRequired` is configured; otherwise
saifeldeen911llms.txtsaifeldeen911/actionfence/llms.txt
review schema drift without rewriting the policy: `npx actionfence pin-schemas guard-policy.json "node server.js" --diff`. This read-only mode prints field-level changes and returns exit code `2` when drift
snapsynapsellms.txtsnapsynapse/turnfile/docs/llms.txt
authors a contract's evals does not implement it; the counterpart implements; the author reviews. - Model-agnostic: one unmodified protocol has run across Claude Opus 4.6, Fable 5, Opus
thevibeworksllms.txtthevibeworks/cctrace/llms.txt
oriented) - [SECURITY](https://raw.githubusercontent.com/thevibeworks/cctrace/main/SECURITY.md): redaction guarantees, reporting - [Agent skill](https://raw.githubusercontent.com/thevibeworks/cctrace/main/skills/cctrace/SKILL.md): how coding agents drive cctrace (commands, UI routes, jsonl anatomy) ## Notes - The trace .jsonl is machine-readable
txn2llms.txttxn2/mcp-data-platform/docs/llms-full.txt
# mcp-data-platform > MCP server for AI-assisted data exploration. DataHub semantic layer with
amazopicllms.txtamazopic/claude-code-statusline/docs/llms-full.txt
# Claude Code Status Line — full project context for AI This file is intended to
derob98llms.txtderob98/ailmanac/static/llms.txt
Third-Party Code](https://derob98.github.io/ailmanac/docs/security/reviewing-third-party-code): Plugins, skills and MCP servers can ship executable code — review before you trust. - [Responsible Use, Ethics & Verification](https://derob98.github.io/ailmanac/docs/security/responsible-use): The autonomy ladder
iampantherrllms.txtiampantherr/SecureContext/llms.txt
signal "I'm done, please review" - Orchestrator has no visibility into agent state without polling files - Agents re-read each other's code from disk — inefficient and error-prone **With
jackg825llms.txtjackg825/claude-code-agents/llms.txt
development. ## Agent Definitions - [Strategic Planner](./personas/strategic-planner.md): Requirements and design - [Task Executor](./personas/task-executor.md): Precise implementation - [Code Reviewer](./personas/code-reviewer.md): Quality assurance - [Steering Architect](./personas/steering-architect.md): Project analysis - [Debugger](./personas/debugger.md): Error resolution - [Data Scientist
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.
