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.
MrPunyapalllms.txtMrPunyapal/laravel-attributes-list/docs/llms.txt
request contains unknown fields - https://mrpunyapal.github.io/laravel-attributes-list/attributes/testing/Seeder: Run a specific seeder class during tests - https://mrpunyapal.github.io/laravel-attributes-list/attributes/testing/Seed: Run the database seeder during tests - https://mrpunyapal.github.io/laravel-attributes-list/attributes/testing/SetUp: Mark a trait method
AaryanvermaReads credentialsllms.txtAaryanverma/graybox/llms.txt
file discovery. - [Packaging](https://github.com/Aaryanverma/graybox/blob/main/pyproject.toml): console entry point, Python requirement, and optional `test`/`azure` dependencies. - [Runtime dependencies](https://github.com/Aaryanverma/graybox/blob/main/requirements.txt): dependencies including LiteLLM, PyYAML, requests, tenacity, python-dotenv, readchar
vstorm-collms.txtvstorm-co/agenticos/llms.txt
what it cost and who approved it — written even when the run failed. This test is written to be applied to other products in the category, and to this
oliver-zehentleitnerDeletes or force-pushesllms.txtoliver-zehentleitner/keep-the-why/llms.txt
what changed; Keep the Why preserves why it changed. Complements README, AGENTS.md, docs, CONTRIBUTING.md, tests, Keep a Changelog rather than replacing any of them — see "Where this fits
Zhiyuan-ZengReads credentialsllms.txtZhiyuan-Zeng/RLVE/tinker-cookbook/llms-full.txt
nextra/components' import { CookbookLink } from '../components/CookbookLink' # Evaluations Our training scripts will print out training and test loss. Two common workflows for evaluations are to do inline evals during training
joshuaswarrenReads credentialsllms.txtjoshuaswarren/openclaw-engram/llms.txt
SECURITY.md Vulnerability reporting and disclosure. AGENTS.md / CLAUDE.md Agent operating rules and privacy policy. BUILD / TEST / DEVELOP Install: pnpm install Build: pnpm run build Test: pnpm test Typecheck: pnpm run check
SyntheticAutonomicMindllms.txtSyntheticAutonomicMind/CLIO/llms.txt
Debug mode ``` ## Key Files for AI Agents - `AGENTS.md` - Technical reference (architecture, code style, testing) - `.clio/instructions.md` - Project methodology (The Unbroken Method) - `docs/ARCHITECTURE.md` - System design overview - `docs/DEVELOPER_GUIDE.md` - Contribution guidelines ## Architecture ``` User Input
FLOX-Foundationllms.txtFLOX-Foundation/flox/docs/llms-full.txt
# lrvx — full documentation bundle lrvx is a C++23 high-performance trading framework with
KbWenllms.txtKbWen/agentic-os/llms.txt
Copilot, Google Antigravity, and any Markdown-reading LLM agent — a repeatable plan → build → review → test → ship workflow with quality gates: a credential scan and a validator that fails when
congminh1254llms.txtcongminh1254/shopee-sdk/llms.txt
Node Version**: >= 20.0.0 **Main Entry**: `src/sdk.ts` → `lib/sdk.js` (compiled) **Dependencies**: Minimal (only `node-fetch`) **Test Coverage**: 95%+, 1160 comprehensive tests ## 🏗️ Project Structure ``` shopee-sdk/ ├── src/ # Source code (TypeScript) │ ├── sdk.ts # Main
jenticllms.txtjentic/jentic-one/llms.txt
raw.githubusercontent.com/jentic/jentic-one/refs/heads/main/CONTRIBUTING.md): development workflow, commit conventions and the checks a change has to pass. - [Testing](https://raw.githubusercontent.com/jentic/jentic-one/refs/heads/main/docs/development/testing.md): the Python test tiers and the generated-artifact drift checks. - [Issues
dyllms.txtdy/jz/llms.txt
Compile the numeric JavaScript you already test to lean GC-free WASM — same source, no rewrite, type annotations, or runtime. JZ compiles JavaScript into native-grade WASM. The same source
matank001Pipes a download into a shellllms.txtmatank001/clodfarm/site/llms.txt
session and merges their branches. - An optional check (e.g. the project's tests) runs before work lands; a failing check sends the agent back to fix it. - A budget governor
dylanroscoverllms.txtdylanroscover/Embody/web/llms-full.txt
type directly in Claude Code to trigger common workflows. ### `/run-tests` Runs the Embody test suite via MCP and reports results. ``` /run-tests # Run all 122 test suites /run-tests test_path_utils
denolandllms.txtdenoland/docs/static/llms.txt
runtime built on V8 and Rust, > distributed as a single binary. TypeScript, formatting, linting, testing, and > a standard library work with zero configuration. Programs are sandboxed by > default; capabilities (network
garagonllms.txtgaragon/nanostack/llms.txt
reference each other through structured artifacts in `.nanostack/`. ## Verified adapters These hosts have a tested adapter in `adapters/` with documented capability evidence. The `adapters/ .json` files are the single source
socai-iollms.txtsocai-io/jev-social/site/llms.txt
compatibility will only be claimed after its public request and response contract can be tested end to end. The provider is only the decision layer. Jev Social rebuilds the allowed
guardanallms.txtguardana/guardana/site/llms.txt
rules - [writing-rules.md](https://raw.githubusercontent.com/guardana/guardana/refs/heads/main/docs/writing-rules.md): create YAML or Python rules - [usage-rule-test.md](https://raw.githubusercontent.com/guardana/guardana/refs/heads/main/docs/usage-rule-test.md): test positive, negative, and inconclusive fixtures - [extending.md](https://raw.githubusercontent.com/guardana/guardana/refs/heads/main/docs/extending.md): provide rules, evaluators, targets, or taxonomies
tradecatlabsllms.txttradecatlabs/fatecat/llms.txt
produce structured results; FateCat normalizes inputs, capability contracts, evidence fields, Markdown reports, delivery interfaces, tests, and release gates. AI or Agent consumers should interpret the returned structure instead of recalculating
nikolai-vysotskyiReads credentialsllms.txtnikolai-vysotskyi/trace-mcp/docs/llms-full.txt
what depends on this file or symbol. Each dependent symbol includes `hasTestReach` (whether any test that covers the file also references that specific symbol) | Always | | `get_task_context` | **Graph-aware
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.
