How real projects summarise themselves for language models.
hiroyuki-miyauchillms.txthiroyuki-miyauchi/axiarch/llms.txt
behavior in AI-assisted software development. It defines minimum quality standards across engineering, product, security, operations, and business work through a multi-layer constitutional architecture, making consistent output quality easier
illodevllms.txtillodev/workfile/site/llms-full.txt
workfile.illodev.com/docs/http-api.md) — HTTP API - [/docs/ui.md](https://workfile.illodev.com/docs/ui.md) — The interface - [/docs/security.md](https://workfile.illodev.com/docs/security.md) — Security model - [/docs/spec.md](https://workfile.illodev.com/docs/spec.md) — Spec — Repository Workfile - MCP Registry: `io.github.illodev/workfile` · npm: `@illodev/workfile` · source
illodevllms.txtillodev/workfile/site/llms.txt
served by the same node:http server that answers the API. It ships precompiled:… - [Security model](https://workfile.illodev.com/docs/security.md): Workfile is a local tool. Its threat model is small
info-dev-13llms.txtinfo-dev-13/alphainfo-claude-skill/llms.txt
auto-infer domain - [tasks/probes.md](tasks/probes.md) — 21 recipes + 8 domain probe libraries (finance, biomedical, mlops, security, industrial, climate, energy_grid, logistics) - [reference/api_guide.md](reference/api_guide.md) — full API specification - [reference/interpretation.md](reference/interpretation.md) — how to translate
joncoronelllms.txtjoncoronel/skillbundle/public/llms.txt
skill}`. Each skill page carries the rendered SKILL.md, install count and rank, install history, security audit verdicts, a copyable install command, and a full change history with diffs between
knowledgetrailsaillms.txtknowledgetrailsai/OASIS/llms.txt
measurement framework, adoption roadmap, tailoring, use cases and appendices. ## Architecture, Engineering, Security, Monitoring - [Reference Architecture](https://raw.githubusercontent.com/knowledgetrailsai/OASIS/main/Architecture/oasis-reference-architecture.md): the nine architecture perspectives and where each companion repository implements a specific
Mesutcydevllms.txtMesutcydev/vamp-suite/docs/llms.txt
hosted relay is required. ## Documentation - Install: https://thevamp.app/sync/#download - iOS sideloading: https://github.com/Mesutcydev/vamp-suite/blob/main/docs/IOS_SIDELOAD.md - Security: https://github.com/Mesutcydev/vamp-suite/blob/main/SECURITY.md
Mesutcydevllms.txtMesutcydev/vamp-suite/llms.txt
/Mesutcydev/vamp-suite Assistant source: https://github.com/Mesutcydev/vamp-assistant Install: https://github.com/Mesutcydev/vamp-suite/blob/main/docs/INSTALL.md Sideload: https://github.com/Mesutcydev/vamp-suite/blob/main/docs/IOS_SIDELOAD.md Security: https://github.com/Mesutcydev/vamp-suite/blob/main/SECURITY.md
munhqllms.txtmunhq/codeindex/llms.txt
tree`, `get_hot_files`, `status`, `read_file`, `index_workspace`. - `analyze` (kind) — 22 analyses: security, dead_code, cycles, architecture, unwrap_audit, clones, duplication, health and others. Production-cost analyses: spawn_scan
OpenAdaptAIllms.txtOpenAdaptAI/openadapt-agent/llms.txt
documents - [README](https://github.com/OpenAdaptAI/openadapt-agent/blob/main/README.md): install, quickstart, honest limits. - [docs/DESIGN.md](https://github.com/OpenAdaptAI/openadapt-agent/blob/main/docs/DESIGN.md): architecture, security model, what v2 deliberately does not do. - [docs/DISTRIBUTION.md](https://github.com/OpenAdaptAI/openadapt-agent/blob/main/docs/DISTRIBUTION.md): registry artifacts, the public
open-payroll-datallms.txtopen-payroll-data/philippines-payroll-data/llms.txt
Asian countries — **Philippines, Singapore, Malaysia, Thailand, Indonesia, Vietnam** — covering income tax & employer withholding, social-security / provident-fund contributions, statutory benefits & leave, and minimum wage. The Philippines also has a linked
peopleforresterllms.txtpeopleforrester/claude-dotfiles/llms.txt
patterns - documentation/ — ADR generation, changelog automation - git/ — Commit crafting, PR descriptions - quality/ — Code review, security scanning - optimization/ — Learning, context management, verification - patterns/ — Language-specific patterns (TypeScript, Python, Go, Rust) - frameworks
sailorpepellms.txtsailorpepe/undesirables-mcp-server/llms.txt
FFmpeg Video Production 6. Zero-Token-Drag Web Scraping (DuckDuckGo) 7. Physical SAST Code Security Auditing 8. Seatbelt-Sandbox Shell/Python Execution 9. Financial Analytics Oracle (conformal risk forecast + Safe-Hold
sandraschillms.txtsandraschi/arxiv-mcp/llms.txt
releases). - Fleet: `glama.json`, `manifest.json` (MCPB); `justfile` recipes. - `src/arxiv_mcp/data/fleet_default.json` (Apps hub); `mcp-central-docs/projects/arxiv-mcp/README.md`. ## Security - All external text (titles, abstracts, full text, blog content, DOI metadata) wrapped with adversarial safety
shenlian19831109llms.txtshenlian19831109/progmune-runtime/web/llms.txt
auxiliary checker). - [vs Semgrep](https://progmune.top/compare/semgrep.html) / [vs CodeQL](https://progmune.top/compare/codeql.html) / [vs CodeBuddy Security](https://progmune.top/compare/codebuddy-security.html): honest complementary comparisons — Progmune is NOT a replacement for any of them
shimo4228llms.txtshimo4228/claude-harness/llms.txt
that don't resolve on disk); deterministic, delegates quality / risk / validation to skill-stocktake / security-scan / skill-comply - [skill-creator](skills/skill-creator/SKILL.md): write or rewrite a skill / agent definition — intent packet
shimo4228llms.txtshimo4228/search-first/llms-full.txt
front-end check (before code is written) while verification skills (test coverage, security review, code review) are the back-end checks (after code exists). The skill is also a kind
sweenzorllms.txtsweenzor/roam-docs/public/llms.txt
Tokens](https://roamdocs.fyi/help/create-api-tokens.md): (how to create Roam API tokens for a graph) - [Security](https://roamdocs.fyi/help/security.md): Security Policy - [Right Sidebar](https://roamdocs.fyi/help/right-sidebar.md): Roam Team Videos:: - [Roam Depot
tristanmanchesterllms.txttristanmanchester/agent-skills/agent-use/llms.txt
references/app-ui-and-workspace-readiness.md): UI/action parity and shared workspaces. - [Files/mobile/long-running work](references/files-mobile-and-long-running-work.md): Checkpoints, offline constraints, task status. - [Security and recovery](references/security-recovery.md): Permissions, dry-run, approval, rollback, idempotency. - [Evaluation](references/evaluation.md): Task-level evals
urmzdllms.txturmzd/agentspec/llms.txt
discovered ## Optional - [CHANGELOG](https://github.com/urmzd/agentspec/blob/main/CHANGELOG.md): Release history - [LICENSE](https://github.com/urmzd/agentspec/blob/main/LICENSE): Apache-2.0 - [SECURITY](https://github.com/urmzd/agentspec/blob/main/SECURITY.md): Vulnerability reporting
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.
