How real projects summarise themselves for language models.
NSPG13llms.txtNSPG13/agent-bounties/site/llms.txt
agent_bounties_get_creator_review` and `agent_bounties_stage_creator_verdict` on the participant page. Preparation never signs or pays. Funding-ready coding handoffs pass `benchmark` and `evidence_schema` together
ssdeanxllms.txtssdeanx/secure-rag-multi-agent/llms.txt
markdownlint.json](.markdownlint.json): Markdown linting configuration - [.vscode/settings.json](.vscode/settings.json): VS Code workspace settings - [.vscode/tasks.json](.vscode/tasks.json): VS Code task configurations ## Agents - [src/mastra/agents/](src/mastra/agents/): Directory containing all specialized AI agents - [src/mastra/agents/identity.agent.ts](src/mastra/agents/identity.agent.ts): JWT validation
xi-karillms.txtxi-kari/crossframe-skill/llms.txt
article protocol](skills/crossframe-critical/protocols/critical-article-protocol.md): dossier to critique matrix to article plan to long-form essay. - [Review skill](skills/crossframe-review/SKILL.md): audit CrossFrame outputs for reasoning fidelity, evidence boundaries, citations, and repair steps. - [Dialogue
zxpmailllms.txtzxpmail/ReqForge/llms.txt
builder, change-manager, design-brief-builder, design-maker, dev-planner, dev-builder, bug-fixer, code-review, release-builder, domain-mapper, request-dispatcher, feedback-writer, evolution-engine, skill-builder, reqforge-greenkeeper
alexfrmnllms.txtalexfrmn/murmur/site/llms-full.txt
problem it solves AI agents are usually isolated. A coding assistant cannot ask another agent for context or a review, so a person ends up as the relay, copying messages
cameronryellms.txtcameronrye/activitypub-mcp/public/llms-full.txt
bash # Lint code npm run lint # Fix linting issues npm run lint:fix # Format code npm run format # Check formatting npm run format:check # Validate Biome configuration npm run validate
cis2042llms.txtcis2042/product-design-harness/llms-full.txt
Loop. Last reviewed: 2026-07-11 Canonical website: https://cis2042.github.io/product-design-harness/ Source repository: https://github.com/cis2042/product-design-harness ## Core Facts - UX3 is a product decision harness, not a coding harness
cis2042llms.txtcis2042/product-design-harness/llms.txt
docs/CONTRACTS.md - docs/COUNCIL.md - docs/LIVE-CODING.md Golden review examples (all validate against the canonical review contract): - examples/quick-gate-review.json - examples/standard-gate-review.json - examples/ux3-council-review.json Live coding golden chain: - examples/live-coding-product-brief.json - examples/live-coding-review.json - examples/live-coding-context-pack.json Verify locally (CI runs the full suite
Hedgy-Labsllms.txtHedgy-Labs/setoku/site/llms.txt
shape of the API. ## Install Setoku - [Setoku quickstart](https://setoku.com/#quickstart): add the Claude Code plugin (`/plugin marketplace add Hedgy-Labs/setoku`), then run `/setoku:onboard` from your project directory
heymillms.txtheymi/aldus-palace/llms-full.txt
must audit AI-written data | Every action the system takes for you is recorded, reviewable and revocable; names and amounts are stripped before anything reaches a model; deleting really deletes
junjsleellms.txtjunjslee/episteme/llms.txt
encoding operator preferences. Adapters mount the same kernel files into specific runtimes (Claude Code, Hermes, future). ## Primary identity (load first) - [THE_WAY_TO_THINK](./docs/THE_WAY_TO_THINK.md): what episteme
mimnetsllms.txtmimnets/OpenHRApp/public/llms-full.txt
your recent notifications. Each notification shows: - **Type icon** — Color-coded by category (Leave, Attendance, Announcement, Review, System) - **Title** — A brief description of the event - **Message** — Details about what happened - **Timestamp
MustaphaStephllms.txtMustaphaSteph/agent-bus/llms.txt
final_answer: string | null manager_reviewed: boolean file_scope: string[] edit_scope: string[] read_scope: string[] pending_assignee: string | null stale?: boolean } ``` ## Error codes | Code | Meaning | Common cause | |---|---|---| | `INVALID_INPUT
ReallyArtificialllms.txtReallyArtificial/mcp-jest/llms-full.txt
expect": "content[0].text === '8'" } }, "resources": { "config.json": { "expect": "exists" }, "docs/*": { "expect": "count >= 1" } }, "prompts": { "review-code": { "args": { "code": "function test() {}" }, "expect": "messages.length > 0" } }, "timeout": 30000 } } ``` ### HTTP Transport Config ```json { "server
agentic-hilllms.txtagentic-hil/agentic-hil/llms.txt
Agentic HIL > Agentic HIL is a hardware-in-the-loop MCP server for AI coding agents. It lets an agent develop firmware on the real board: bounded tools to flash
ashlraillms.txtashlrai/phantom-secrets/docs/llms-full.txt
phantom init` then `phantom exec -- claude` — code safely 2. **Delegate the bounded setup**: Add the MCP server, ask Claude to propose protection, then review mutations and complete secret entry
ashlraillms.txtashlrai/phantom-secrets/docs/llms.txt
release attestations passed in https://github.com/ashlrai/phantom-secrets/actions/runs/33952398697. The separately managed Homebrew formula publishes reviewed `v0.7.8`. macOS: ``` brew tap ashlrai/phantom brew trust --formula ashlrai/phantom/phantom brew install ashlrai/phantom/phantom ``` For the current macOS
bntvllntllms.txtbntvllnt/agent-skills/llms-full.txt
testing, agent self-improvement, anti-regression (#7) - feat(workflow): add production-grade auto-selecting code review (#6) - feat(tmux): add complete tmux management skill (#5) ## [1.8.0] - 2026-03-21 - feat
bntvllntllms.txtbntvllnt/agent-skills/llms.txt
development — plan, ship, fix, review, done - [tmux](tmux/SKILL.md): Terminal multiplexer — sessions, windows, panes, layouts, scripting ## Optional - [Security Policy](SECURITY.md): Vulnerability reporting and disclosure policy - [Code of Conduct](CODE_OF_CONDUCT.md): Community guidelines
erishforGllms.txterishforG/git-parsec/docs/llms-full.txt
License: MIT Author: erishforG --- ## Why it exists When multiple developers — or multiple AI coding agents running in parallel — work on the same repo: - `git add` / `commit` operations collide on `.git/index.lock
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.
