How real projects summarise themselves for language models.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
mattrobinsonsrePipes a download into a shellllms.txtmattrobinsonsre/terrapod/llms.txt
first-class Terraform/OpenTofu provider, `terraform-provider-terrapod` (for managing Terrapod itself as code; see the `provider/` entry below and [docs/terraform-provider.md](docs/terraform-provider.md)). Deployed exclusively via a Helm chart on Kubernetes
SentryReads credentialsllms.txtgetsentry/dotagents/docs/public/llms.txt
getsentry/skills find-bugs # Add multiple skills at once npx @sentry/dotagents add getsentry/skills find-bugs code-review commit # Add all skills from a repo npx @sentry/dotagents add getsentry/skills
vinkius-labsReads credentialsllms.txtvinkius-labs/mcp-fusion/docs/llms.txt
# MCP Fusion > fusion is the TypeScript framework for production MCP servers. MVA architecture, structured
FlorianBruniauxllms.txtFlorianBruniaux/claude-cowork-guide/llms.txt
dashboards (beta) and animations (Motion, beta, Team and Enterprise) from any conversation - Execute task code in an isolated environment ## Boundaries to Keep in Mind - Folder access, the built-in browser
FlorianBruniauxllms.txtFlorianBruniaux/claude-cowork-guide/machine-readable/llms.txt
dashboards (beta) and animations (Motion, beta, Team and Enterprise) from any conversation - Execute task code in an isolated environment ## Boundaries to Keep in Mind - Folder access, the built-in browser
KyaniteLabsllms.txtKyaniteLabs/kinocut/docs/llms-full.txt
Creation: Hyperframes and local Revideo have separate runtime requirements. Custom executable scenes are trusted code. CPU/GPU availability alone does not prove encoder usability, decoded fidelity, portability or a fixed speedup
KyaniteLabsllms.txtKyaniteLabs/kinocut/llms.txt
github.com/KyaniteLabs/kinocut/blob/master/docs/VIDEO_RECEIPT.md - Rescue: https://github.com/KyaniteLabs/kinocut/blob/master/docs/RESCUE.md - 360 assembly: https://github.com/KyaniteLabs/kinocut/blob/master/docs/360_ASSEMBLY.md - AI-video review (dev tip): https://github.com/KyaniteLabs/kinocut/blob/master/docs/AI_VIDEO_REVIEW_AND_SALVAGE.md - FAQ: https://github.com/KyaniteLabs/kinocut/blob/master/docs/faq.md - Agent skill: https://github.com/KyaniteLabs/kinocut/blob/master/skills/kinocut/SKILL.md - Changelog
oliver-zehentleitnerDeletes or force-pushesllms.txtoliver-zehentleitner/keep-the-why/llms.txt
framework already governs how the work gets done (brainstorming, planning, systematic debugging, TDD, code review), that workflow runs first; Keep the Why doesn't compete for that role, and preserves
joshuaswarrenReads credentialsllms.txtjoshuaswarren/remnic/llms.txt
deepSleep off by default. - Coding graph: code-symbol knowledge graph for coding agents. Verify any default in packages/remnic-core/src/config.ts or the openclaw.plugin.json configSchema before relying on it. ACCESS LAYER HTTP
KbWenllms.txtKbWen/agentic-os/llms.txt
agents. It gives agents — Claude Code, OpenAI Codex, Cursor, GitHub Copilot, Google Antigravity, and any Markdown-reading LLM agent — a repeatable plan → build → review → test → ship workflow with quality gates
jenticllms.txtjentic/jentic-one/llms.txt
only the operations it has been approved for, and asking for more is a reviewable request rather than a silent widening. - Leave a trail. Every brokered call is recorded
roy-tongllms.txtroy-tong/AgentMeasure/llms.txt
Free local checks for Codex / Claude Code logs and reproducible agent metering verification. Human-delivered diagnostics: $10 Healthcheck and $20 Metering QA. Last reviewed: 2026-10-15. ## Start here - [Website
Fangx-AIllms.txtFangx-AI/geo-doctor/llms.txt
licensed code; it does not promise rankings. GEO 医生是一个开源的中英双语 GEO（生成式引擎优化）技能：装进 Claude Code、Codex、WorkBuddy 等 AI 助手后，说"帮我做 GEO"，它按"问诊 → 体检 → 事实卡 → 问题集 → 采样 → 诊断
mihneaptullms.txtmihneaptu/opencode-fusion/site/llms.txt
them. Skills are discovered on demand; installing one needs no restart. 5. Cross-vendor review is emergent: pick main and sidekick from different model families. 6. Only the permission layer
congminh1254llms.txtcongminh1254/shopee-sdk/llms.txt
ESLint npm run format # Prettier ``` ### Code Quality Tools - **ESLint**: TypeScript-aware linting (`.eslintrc.json`) - **Prettier**: Code formatting (`.prettierrc`) - **Husky**: Git hooks for pre-commit checks - **Commitlint**: Conventional commit messages - **Jest**: Testing
dylanroscoverllms.txtdylanroscover/Embody/web/llms-full.txt
bloom on the final output. ``` You're not getting a screenshot or a code snippet to paste. You're getting the **actual network**, in front of you, ready to play
garagonllms.txtgaragon/nanostack/llms.txt
work. Not a saved phase; the artifact appears on review. - /review: Two-pass code review (structural + adversarial). Detects scope drift against the plan and conflict-precedence against prior /security. - /security
nikolai-vysotskyiReads credentialsllms.txtnikolai-vysotskyi/trace-mcp/docs/llms-full.txt
requires external binaries and complex backend choices. [trace-mcp vs CodeGraphContext](/vs/codegraphcontext.html) | | **Review graph** | [code-review-graph](https://github.com/code-review-graph/code-review-graph) | Tracks incremental changes with empty-result uncertainty explanations. | Specialised
nikolai-vysotskyillms.txtnikolai-vysotskyi/trace-mcp/docs/llms.txt
calls return vs making structural questions about code cheap to ask. - [trace-mcp vs code-review-graph](https://trace-mcp.com/vs/code-review-graph.html): Head-to-head against the incremental SQLite graph peer — blast
AGIHuntPipes a download into a shellllms.txtAGIHunt/blurt/site/llms.txt
into items: issues with repro steps and the code most likely involved, ideas, notes and to-dos, each with a frame. Review with the keyboard (A keeps, X discards
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.
