How real projects summarise themselves for language models.
Kosmorayllms.txtKosmoray/dayan-agent-skills/llms.txt
risky request into a falsifiable problem hypothesis and minimal task contract. - Dayan Adversarial Reviewer: reviews a bounded engineering change through failure-mode, maintainability, and trust-boundary lenses, then returns evidence
liafeillms.txtliafei/kodawari/llms.txt
markdown file > describing a feature; it plans, writes the code, runs your tests, has a second > AI model review the result, fixes what review flags, and stops at a ship/no-ship
lpalboullms.txtlpalbou/AIRelays/llms-full.txt
both providers, plus credits, spend control, and any named extra quotas (for example code review) the plan reports. Which windows appear is plan-dependent upstream policy; only reported windows
mayowa-kalejaiyellms.txtmayowa-kalejaiye/Failures/website/llms.txt
deterministic check works. - [Tools Reference](https://failures.pxxl.click/docs/tools.html): All 13 MCP tools — review_code, review_plan, check_invariant, check_idempotency, check_retry_safety, check_transaction_safety, generate_failure_cases, generate
mkalkerellms.txtmkalkere/agent-coordinator/llms.txt
File-based message channels ``` ## Use Cases - Running multiple Claude Code agents on the same monorepo - Coordinating developer + reviewer agent pairs for autonomous PR workflows - Managing AI agent teams across different
papperrollinggeryllms.txtpapperrollinggery/delegate-to-deepseek-harness/llms.txt
installed version is in VERSION. - Primary use cases: copywriting, research synthesis, video-preproduction text, coding, review, and independent opinions inside larger projects. - Parallel behavior: delegate returns after prompt acceptance
parousia8888llms.txtparousia8888/web-app-security-skill/llms.txt
program: scope gate, frontend exposure, API security, LLM security and federated identity, server-side code audit, database isolation, supply chain, blue-team detection, reporting and retest. - Settles the crawl boundary
rhein1llms.txtrhein1/fable5-codex/llms.txt
Codex Fable-5 is an OpenAI Codex plugin for evidence-first audits, deep code review, fact checks, codebase understanding, design options, and repo-wide sweeps. Latest public tagged release: `v0.4.0-alpha.2
shadoprizmllms.txtshadoprizm/videolens/site/llms.txt
Managed modes. - MCP server: exposes VideoLens as tools for AI agents such as Claude Code and Cursor. ## Report styles - Detailed Report: comprehensive explanation of the video's main ideas, examples
skew-labsllms.txtskew-labs/skewarchive/docs/llms.txt
public overview, execution lanes, repo layout, status. - `docs/README.md` — public docs index for humans and reviewers. - `docs/ARCHITECTURE.md` — system design and trust boundaries. - `docs/risk-model.md` — formulas, state machines, invariants. - `docs/COMPARISON.md` — structural comparison
snapsynapsellms.txtsnapsynapse/graceful-boundaries/llms-full.txt
# Graceful Boundaries (full) > A specification for how services communicate their operational limits to humans
Super-Lilillms.txtSuper-Lili/Super-Lilis-Daily-Adventure/docs/llms.txt
directors) and builds one browser-native tool for it, every day. Weekly > self-evolution reviews the week's work and updates its own engineering > rules. All harness engineering, quality gates
The-825llms.txtThe-825/breadcrumbs/llms.txt
that fire on a condition instead of waiting to be remembered. Pattern only, no code ships. - [docs/governing-agents-that-act.md](docs/governing-agents-that-act.md): read this if your agent takes actions and someone will eventually audit
theyoungastronautsllms.txttheyoungastronauts/polaris/llms.txt
before code.** Brainstorm → plan → execute. A bad plan compounds into bad code. - **Small phases.** Each phase should be reviewable in one sitting (1–3 hours of execution). - **Verify separately.** Fresh
tydandoullms.txttydandou/tracebook/site/llms.txt
evidence triage for human review, not an automatic truth verdict. ## Install Codex: codex plugin marketplace add tydandou/tracebook --ref v4.0.12 codex plugin add tracebook@tracebook Claude Code: claude plugin marketplace
vnykmshrllms.txtvnykmshr/playbook/llms.txt
security](https://github.com/vnykmshr/playbook/blob/main/commands/reviews/pb-security.md): security checklist with quick, standard, and deep tiers - [pb-review-code](https://github.com/vnykmshr/playbook/blob/main/commands/reviews/pb-review-code.md): code review with LLM-output trust boundaries - [pb-review-tests](https://github.com
Adonis0123llms.txtAdonis0123/adonis-skills/llms.txt
adonis-skills > Agent-agnostic skills for coding agents (review loops, workflow gates, MCP setup, Git delivery, local environment audits). Each skill is `skills/ /SKILL.md`. Install with `npx skills add adonis0123/adonis-skills
aidesignblueprintllms.txtaidesignblueprint/integrations/shared/llms.txt
Code, the Claude desktop app, Cowork, Gemini CLI, Codex and GitHub Copilot CLI (skills, role agents, remote MCP) - [Security & Application](https://aidesignblueprint.com/en/security-application): the enterprise security and application-review surface
AI-Scarlettllms.txtAI-Scarlett/DSH-Store/marketplace/llms.txt
requested detail. Unverified fields remain explicitly unknown. - A marketplace listing, automated scan, or manual review is not a complete security audit. ## Main sections - Installation command and sequence: https://dsh.store/#top
AlexShchukallms.txtAlexShchuka/neuro-matrix/llms.txt
/AlexShchuka/neuro-matrix/blob/main/agents/developer.md): code mutator — the only agent that writes code, runs builds/tests, and pushes. - [agents/analyzer.md](https://github.com/AlexShchuka/neuro-matrix/blob/main/agents/analyzer.md): system investigator — RCA, design, review, dead-end diagnostics. - [agents/critic.md](https://github.com/AlexShchuka/neuro-matrix/blob/main/agents/critic.md): anti
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.
