How real projects summarise themselves for language models.
Ayithamsetty-Vamsi-krishnallms.txtAyithamsetty-Vamsi-krishna/claude-skills/llms.txt
narrative tasks (zero code snippets). Saves plan. - **saas-dev-execute**: Fresh subagent per task + specialist skill + design file. Two-stage review. ## Frontend UI Skills - **saas-dev-ui-react**: Premium React
bonzannillms.txtbonzanni/ha-casa-app/docs/llms.txt
bound identity, per-executor policy maps and their fail-closed fallbacks, and the claude_code containment floor. - [architecture/http-surface.md](architecture/http-surface.md): The two HTTP servers, what each exposes, and how an inbound
chhudsonllms.txtchhudson/bmad-claude-skills/docs/llms.txt
master | 4-Implementation | "sprint planning", "create story", "retrospective" | | developer | 4-Implementation | "dev story", "implement", "code review" | | test-architect | 4-Implementation | "test framework", "test design", "coverage" | | ux-designer | Cross-Phase | "wireframe
FoxsterDevllms.txtFoxsterDev/xuunity-mcp/llms.txt
docs/index.html: homepage for GitHub Pages / discovery landing surface - docs/install.html: install overview for Cursor, Claude Code, Codex, Claude Desktop, Rider, and Windsurf - docs/comparison.html: search-friendly summary page for XUUnity
gabrielmustierellms.txtgabrielmustiere/forge/site/llms.txt
chiffrée, baseline et kill switch. - `/forge:tech-implem` — exécution mesurée après chaque étape. - `/forge:review` — code review du diff : sécu, qualité, conformité au plan, non-régression. - `/forge:commit` — message Conventional
getcargohqllms.txtgetcargohq/gtm-skills/llms.txt
login --email you@company.com # sends a code, then exits cargo-ai login --email you@company.com --code 123456 ``` A new account starts with **100 free credits and needs no card**: roughly
go165llms.txtgo165/agent-skill-groups/docs/llms.txt
Skills directory submissions. They are discoverability signals after review and crawl time, not instant ranking guarantees. Supported runtimes: - OpenAI Codex - Claude Code - OpenCode - Generic Agent Skills layouts Fastest verification: ```bash
go165llms.txtgo165/agent-skill-groups/llms.txt
Skills directory submissions. They are discoverability signals after review and crawl time, not instant ranking guarantees. Supported runtimes: - OpenAI Codex - Claude Code - OpenCode - Generic Agent Skills layouts Fastest verification: ```bash
hermes-labs-aillms.txthermes-labs-ai/agent-gorgon/llms.txt
only --scope coding-agent -- ` - Safe calibration against a running process: `agent-gorgon --scope starter --agent-pid 12345 --poll 0.5 --no-llm --audit-only` - Active controls after policy review: `agent-gorgon
hiroyuki-miyauchillms.txthiroyuki-miyauchi/axiarch/llms-full.txt
Latest Stable: 1.18.0 | License: Apache 2.0 > Installation examples target v1.18.0; existing adopters must review and apply an upgrade to receive its changes. > Repository: https://github.com/hiroyuki-miyauchi/axiarch Axiarch is an open
hiroyuki-miyauchillms.txthiroyuki-miyauchi/axiarch/llms.txt
task records through explicit readiness/completion phases. - **Native Task State Sync**: Codex uses `update_plan`; Claude Code uses `TaskCreate` / `TaskUpdate` / `TaskList` / `TaskGet`, with `TodoWrite` only as an older-runtime fallback. ## Quick Start
illodevllms.txtillodev/workfile/site/llms-full.txt
transition by any other actor fails with `CARD_CLAIM_OWNER_MISMATCH`. In Claude Code, the plugin's hook asks before an edit inside a scope another actor holds. ### `unverified_done
Kickgeistllms.txtKickgeist/agents/llms.txt
consent page. Works on Free (1 connector), Pro, Max, Team, and Enterprise. - [Claude Code (CLI)](https://code.claude.com/docs/en/mcp): Run `claude mcp add --transport http kickgeist https://mcp.kickgeist.com/mcp`, then `/mcp
maphousellms.txtmaphouse/deltachat-claude-code/llms.txt
Everything you get in a terminal — file editing, bash, git, multi-step tool chains, code review, subagents, CLAUDE.md context, and slash commands — works from your phone or any device
OpenAdaptAIllms.txtOpenAdaptAI/openadapt-agent/llms.txt
serve --bundles [--allow-run]`: serve a private compiled bundle. `openadapt-agent serve --authoring`: local Claude Code first-demo tools `observe`, `start_record`, `click`, and `halt` over stdio. `--authoring` does not enable
peopleforresterllms.txtpeopleforrester/claude-dotfiles/llms.txt
patterns, testing 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
PhilipADllms.txtPhilipAD/health-export-mcp/llms.txt
days, workout keys). - [AGENTS.md](AGENTS.md): per-agent copy-paste setup (Claude Desktop, Cursor, VS Code, opencode, OpenClaw, Hermes, webhook for ChatGPT/Gemini/Grok/n8n/Home Assistant). ## Tools (14) - get_mcp_status, list_metrics
shenlian19831109llms.txtshenlian19831109/progmune-runtime/web/llms.txt
Trust Score + Decision (APPROVED / NEEDS_REVIEW / BLOCKED) + evidence chain. Deterministic state-machine checking; the LLM never judges. Open source (MIT), fully local static analysis — code never leaves the machine; masked
shimo4228llms.txtshimo4228/claude-harness/llms-full.txt
Skills directory**: `skills/` — covers research-before-coding, knowledge extraction, skill auditing, AI-facing documentation, JSON-LD knowledge graph design, human-facing writing review, authorship strategy, and DOI release - **Agents directory
shimo4228llms.txtshimo4228/claude-harness/llms.txt
model second opinion from the OpenAI Codex CLI (a different model family), read-only — code review of the current diff folded into the review chain, plus a plan-stage premise
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.
