AGENTS.md examples from real projects

statelyaiAGENTS.md

xstate

statelyai/xstate/docs/agents.md

Author, inspect and test XState with the installed version's contracts.

No other project uses it yet

InfisicalReads credentialsAGENTS.md

infisical

Infisical/infisical/AGENTS.md

file provides guidance to Claude Code (claude.ai/code) when working with code in this repository. ## Essential Commands - `make reviewable-api` / `make reviewable-ui` — lint:fix + type:check (run before

InfisicalReads credentialsAGENTS.md

infisical / backend

Infisical/infisical/backend/AGENTS.md

whatever the change is, before calling the task done.** This file covers _where_ code goes and _which_ pattern to follow; the quality guide covers the minimum any implementation

InfisicalAGENTS.md

infisical / frontend

Infisical/infisical/frontend/AGENTS.md

AGENTS.md This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository. This is the **frontend** package of the Infisical monorepo — a React

InfisicalAGENTS.md

infisical / tests

Infisical/infisical/tests/AGENTS.md

tests run against any implementation of that contract. ## Read next | Task | Read | |---|---| | Writing or reviewing a test | [docs/writing-tests.md](docs/writing-tests.md) | | Using or adding a fake third party, App Connection, or mail

opendataloader-projectAGENTS.md

opendataloader-pdf

opendataloader-project/opendataloader-pdf/AGENTS.md

that call. | Skill | Use | Claude Code | Codex | |:--|:--|:--|:--| | [odl-fix](.agents/skills/odl-fix/SKILL.md) | Fix a GitHub issue and open a pull request | `/odl-fix` | `$odl-fix` | | [odl-review](.agents/skills/odl-review/SKILL.md) | Review a pull request from

No other project uses it yet

kestra-ioAGENTS.md

kestra

kestra-io/kestra/AGENTS.md

what a paragraph would tell them is already in the code. Write a comment only when a reviewer would otherwise have to ask **why** the code exists: - a non-obvious

No other project uses it yet

modularAGENTS.md

modular / GraphCompiler

modular/modular/GraphCompiler/AGENTS.md

scheduling or placement decisions to generated code. - **The quadratic allocation planner.** `DynamicMemoryPlanningPass` builds an `n * n` `canShare` matrix over allocations. Compile cost is supposed to scale with graph structure, near

actualbudgetDeletes or force-pushesAGENTS.md

actual

actualbudget/actual/AGENTS.md

rules, including title prefix requirements, labeling, the GitHub comment/review/issue 🤖 prefix, and PR template handling. ## Code Review Guidelines When performing code reviews (especially for LLM agents): **see [CODE_REVIEW_GUIDELINES.md](./CODE_REVIEW_GUIDELINES.md)** for specific

No other project uses it yet

apolloconfigAGENTS.md

apollo

apolloconfig/apollo/AGENTS.md

before opening a PR. - `./scripts/build.sh` generates distributable packages (used for deployment workflows). ## Coding Style & Naming Conventions - Follow Google Java Style Guide; 2-space indentation and standard Java conventions apply

nrwlAGENTS.md

nx

nrwl/nx/AGENTS.md

complete solution immediately 3. Make all necessary code changes. Please make multiple commits so that the changes are easier to review. 4. Run appropriate tests and validation

envoyproxyAGENTS.md

envoy

envoyproxy/envoy/AGENTS.md

sign-off attests that the committer (the user) has the right to submit the code under the project's license. 2. **Always run format and lint checks before committing

celeryAGENTS.md

celery

celery/celery/.github/Agents.md

maintainers squash when they merge. - Replies to review comments that answer what was asked. The person checks each reply against the code before it's sent. - Help with any regression

ml-exploreAGENTS.md

mlx

ml-explore/mlx/AGENTS.md

sorry, I cannot reply to the reviewers. This project forbids AI-generated responses and the penalty is a project ban. ## Code standards - Keep code comments concise (usually 1-2 lines

QwenLMAGENTS.md

qwen-code

QwenLM/qwen-code/AGENTS.md

full workflow: investigate, design, test plan, dry-run, implement, verify, self-audit, code review, and iterate. ### Bugfix Use the `/bugfix` skill for the reproduce-first workflow: reproduce, fix, verify, test

No other project uses it yet

invoke-aiAGENTS.md

InvokeAI

invoke-ai/InvokeAI/AGENTS.md

configured vendored-code exclusions. - Focused tests: `uv run --no-sync pytest `. Never start a suite during a generation. - Pick checks by behavior. Run required milestone gates before review. Rerun unchanged

reflex-devAGENTS.md

reflex

reflex-dev/reflex/AGENTS.md

sloppy/spaghetti code — every feature/fix must be clearly understood first. 2. **Bugfixes:** write a regression test that fails before writing the fix. 3. **After implementation:** act as an adversarial reviewer. Scrutinize

manaflow-aiAGENTS.md

cmux / cmux-browser

manaflow-ai/cmux/cmux-browser/AGENTS.md

derived files retain GPL-3.0-only provenance and the exact source revision. Helium-derived code is not available under Manaflow's commercial license. - Other bundled dependencies retain their own terms

manaflow-aiAGENTS.md

cmux / web

manaflow-ai/cmux/web/AGENTS.md

request. Do not add a broad disable or raise the limit to accept new code. Lower the limit in a separate cleanup wave as the remaining debt is removed

steveyeggeAGENTS.md

beads / engdocs

steveyegge/beads/engdocs/AGENTS.md

EXTENDING.md`, `INTEGRATION_CHARTER.md` | Extension and integration boundaries. | | `AGENT_SIGNING.md` | Signatures for agent-prepared commits, comments, and reviews. | | `design/` | Design documents for subsystems (Dolt concurrency, `bd serve`, ownership hand-off, …). | | `adr/` | Architecture decision