How real projects summarise themselves for language models.
verivus-ossllms.txtverivus-oss/llm-cli-gateway/site/llms.txt
configured API providers through one local control plane. It is best for cross-model code review, durable long-running jobs, provider-native session continuity, approval gating, and remote HTTP
wonsukchoillms.txtwonsukchoi/domain-experts/docs/llms.txt
space, evaluating a wall or floor assembly's STC/IIC rating against a code or… - [Adhesive Bonding Machine Operator](https://domainexperts.dev/roles/adhesive-bonding-machine-operator/): distinguishing an open-time violation from a pot-life
Alessandro-Pangllms.txtAlessandro-Pang/harnessmith/llms.txt
user's request. Accepted values are `codex`, `cursor`, `claude`, `claude-code`, `opencode`, `kimi`, `kimi-code`, `deepseek`, `dsh`, `deepseek-harness`, `pi`, `pi-agent`, and `all`. Never infer `all` from an ambiguous
ASGComputellms.txtASGCompute/asgcard-public/llms-full.txt
approval_required` + `approvalUrl` 2. Owner opens the approval page at stripe.asgcard.dev/approve 3. Owner reviews and approves → Stripe Elements form with real-time pricing 4. Owner pays via Stripe → card/Apple
jimy-rllms.txtjimy-r/agent-workspace-architecture/docs/llms.txt
building agent workspaces: the roles, routines, hooks, memory, and task coordination that turn a coding agent into a system you can hand work to. One person's working setup, published
jvoganllms.txtjvogan/symphony-linear-starter/llms.txt
self-improving runbook loop. ## Key concepts - **Orchestrator**: Your Codex or Claude Code agent. Plans issues, dispatches workers, reviews output, promotes learnings. - **Symphony**: OpenAI's open-source runtime for dispatching isolated
remembra-aillms.txtremembra-ai/remembra/landing/llms.txt
session hooks are verified. So are Gemini CLI's, Qwen Code's and Kimi Code's: each was run against the real tool. Codex runs a hook only after
tamdogoodllms.txttamdogood/parler-protocol/llms.txt
Engineering guidelines](/docs/engineering-guidelines.md): the contract every change follows (hard gates, invariants, definition of done). - [Code review guidelines](/docs/code-review-guidelines.md): how every change is reviewed (verified findings, severity ladder). - [CI/CD](/docs/ci-cd.md): pipeline
allemaarllms.txtallemaar/open-skills/llms.txt
before any work begins. — triggers: /plan-create, make a plan, plan this out, design before coding - plan-deep-dive [protocol.yon] — Phase-by-phase deep inspection of any multi-phase plan — stop
mick-gskllms.txtmick-gsk/drift/llms.txt
changed files - Git change detection failure This gives AI coding agents an immediate go/no-go signal after each edit — no manual review needed. ## Use Cases - Detect pattern fragmentation: same concern implemented
odythllms.txtodyth/red-queen/docs/llms.txt
workers through a configurable SDLC pipeline: spec writing, > automated plan review, human spec review, coding, code review, testing, > and human review. Phases, skills, and gates are declared in > `redqueen.yaml`. Open
odythllms.txtodyth/red-queen/llms.txt
Code or Codex workers (selectable per phase) through a > configurable SDLC pipeline (spec → plan review → code → review → test → > human review) with human-in-the-loop gates; issues linked as blockers
peacprotocolllms.txtpeacprotocol/peac/llms.txt
cross-runtime systems. > Portable signed records anyone can verify offline. > Current release: v0.16.4 > Last reviewed: 2026-06-24 ## What is PEAC PEAC Protocol provides cryptographically signed, offline-verifiable interaction records
ariaxhanllms.txtariaxhan/kernel-claude/llms.txt
function budgets, regression diffs, and a project-owned verify gate. - `/kernel:review` · `$kernel:review`: code review with a deterministic scanner lane and a refutation pass; APPROVE, REQUEST CHANGES, or COMMENT
Brandcode-Studiollms.txtBrandcode-Studio/brandsystem-mcp/llms.txt
Figma files, or heads and wants them machine-readable - User wants Claude Design, Claude Code, Cursor, or Windsurf to ground on their brand via a direct local MCP connection
hongnoulllms.txthongnoul/gwae/llms.txt
Homebrew: `brew install hongnoul/tap/gwae`. gwae exists for people who run several coding agents (Claude Code, Jcode, Codex CLI, OpenCode, Gemini CLI, Aider) in parallel on a Mac. tmux and Zellij
jedijashwallms.txtjedijashwa/pullmark/site/llms.txt
rendered diffs with word-level highlights. It is built for > reading and reviewing the Markdown that coding agents and teams produce: > plans, specs, design docs, ADRs, runbooks. Key facts: macOS
oyi77llms.txtoyi77/1ai-skills/llms.txt
response, zero trust, cloud security, API security, OT/ICS security - **Development** (90 skills) — TDD, debugging, code review, PRD, spec-driven development, context engineering, browser testing, Git workflows - **Content** (62 skills) — Video
alexpilottollms.txtalexpilotto/uxon-ai/llms.txt
poll generation jobs. - Import coded page bundles from Claude Code, Codex, Cursor, or v0. - Publish, duplicate, and review landing pages through API commands. - Launch A/B/n experiments across UXON pages, external
antoinedcllms.txtantoinedc/MantaUI/website/llms.txt
mobile](https://mantaui.com/claude-code-mobile): a native iPhone app, full transcript, approvals, dictation. - [Claude Code remote](https://mantaui.com/claude-code-remote): running the agent on a VPS or home server. - [Open source
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.
