AGENTS.md examples from real projects

web-infra-devAGENTS.md

midscene

web-infra-dev/midscene/AGENTS.md

commit or updating a PR, run `pnpm run lint` from the repository root. - For code changes, run the smallest relevant Nx target for each touched project instead of defaulting

CarGuoAGENTS.md

gsy_github_app_flutter

CarGuo/gsy_github_app_flutter/AGENTS.md

token 从设备上被清空，reviewer 侧无法直接复核，属于 **author 责任事故**。此后但凡装机脚本 / 命令里出现 `flutter install`， reviewer 一律直接打回。 - ❌ **在文档 / commit message / code comment 里编造 VM Service / mcp_dart 时序细节**（2026-09-03 拍板）：不许写"evaluate

crowdsecurityAGENTS.md

crowdsec

crowdsecurity/crowdsec/AGENTS.md

comment should rarely be longer than the code it describes. A 20-line comment over a 5-line function is noise. **Review replies** — answer the question that was asked

No other project uses it yet

akitaonrailsAGENTS.md

ai-memory

akitaonrails/ai-memory/AGENTS.md

invisible to every other agent and fragments continuity, so capture them here instead. A reviewed decision record kept in the repository (an ADR directory, a Keep the Why `context/` tree

ChocobozzzAGENTS.md

PeerTube

Chocobozzz/PeerTube/AGENTS.md

bash npm run start # server + client npm run start:server # server only (--no-client) ``` ## Code Style & Conventions ### Formatting (enforced by Oxlint) | Rule | Value | |---------------------|---------------------------------------| | Semicolons | **never** (`@stylistic/semi`) | | Max line length

jupyterlabAGENTS.md

jupyterlab

jupyterlab/jupyterlab/AGENTS.md

template comment asks for. Do not describe the diff change by change: the reviewer reads the code - Steps to reproduce a bug belong in the issue. Give them

apacheAGENTS.md

pulsar

apache/pulsar/AGENTS.md

proposals. | | [`CODING.md`](CODING.md) | Coding conventions: style, async/`CompletableFuture`, concurrency, logging ([slog](https://github.com/merlimat/slog)), dependencies, backward compatibility, testing, and the review checklist. | | [`SECURITY.md`](SECURITY.md) | Reporting a vulnerability, disclosure hygiene

NanmiCoderAGENTS.md

cc-haha

NanmiCoder/cc-haha/AGENTS.md

need to run every lane separately first. Reuse passing results for unchanged code; rerun or broaden checks when subsequent edits, failures, or unresolved risks warrant it. - Required PR checks must

experientiallabsAGENTS.md

experiential

experientiallabs/experiential/AGENTS.md

ingestion never imports runtime or simulation code; source selection is composed by the consuming command. - Python applications use `exp.compose_router` to complete review, plan-bound simulation, judgment, fitting, held

apifyAGENTS.md

apify-mcp-server

apify/apify-mcp-server/AGENTS.md

handle similar cases. Ask: "Am I adding code, or fixing the code that's already there?" - **Self-review your diff.** Before declaring done, review: Is this the minimal

No other project uses it yet

lynx-familyAGENTS.md

lynx / core

lynx-family/lynx/core/AGENTS.md

from this file. ## Common Review Questions - Is this change modifying a shared contract, or should it stay inside one implementation subtree? - Does the touched code own the behavior

No other project uses it yet

caproverAGENTS.md

caprover

caprover/caprover/AGENTS.md

failure paths. Avoid unrelated refactors or style-only changes. ## Review checklist 1. Identify the simplest implementation consistent with nearby code **before** accepting the PR's chosen architecture. Compare the submitted

prowler-cloudAGENTS.md

prowler

prowler-cloud/prowler/AGENTS.md

Publishing artifacts to Prowler Registry | `prowler-registry-artifact` | | Refactoring code | `tdd` | | Regenerate AGENTS.md Auto-invoke tables (sync.sh) | `skill-sync` | | Review PR requirements: template, title conventions, changelog gate | `prowler-pr` | | Review

No other project uses it yet

prowler-cloudAGENTS.md

prowler / api

prowler-cloud/prowler/api/AGENTS.md

django-drf` | | Implementing feature | `tdd` | | Modifying API responses | `jsonapi` | | Modifying component | `tdd` | | Refactoring code | `tdd` | | Review changelog format and conventions | `prowler-changelog` | | Reviewing JSON:API compliance | `jsonapi` | | Running makemigrations

No other project uses it yet

prowler-cloudAGENTS.md

prowler

prowler-cloud/prowler/docs/AGENTS.md

domestic law or regulation, add the nationality and the original name. **Example:** Code for the Cybersecurity Law published in the Spanish Official State Bulletin (BOE, Boletín Oficial del Estado). Most

No other project uses it yet

prowler-cloudAGENTS.md

prowler / prowler

prowler-cloud/prowler/prowler/AGENTS.md

packages | `prowler-registry-artifact` | | Publishing artifacts to Prowler Registry | `prowler-registry-artifact` | | Refactoring code | `tdd` | | Review changelog format and conventions | `prowler-changelog` | | Reviewing compliance framework PRs | `prowler-compliance-review` | | Syncing

No other project uses it yet

MicrosoftAGENTS.md

playwright-python

microsoft/playwright-python/AGENTS.md

code that we port. `.upstream/` is a full clone of it (gitignored). Read upstream code there. Do not edit, commit or switch branches in it. ```sh python scripts/upstream.py checkout # clone

No other project uses it yet

MicrosoftAGENTS.md

playwright-python / tests

microsoft/playwright-python/tests/AGENTS.md

playwright-roll` skill. The port is line by line, with **zero deviations**. A reviewer reads the `.spec.ts` file and the two `.py` files side by side. Each upstream statement maps

No other project uses it yet

sympyAGENTS.md

sympy

sympy/sympy/AGENTS.md

generated. Disclosure is not required for minor assistive tasks such as spell-checking or code review in primarily human-authored work — but if in doubt, disclose. As noted

NVIDIAAGENTS.md

TensorRT-LLM

NVIDIA/TensorRT-LLM/AGENTS.md

Protected APIs exist** — changes to LLM API signatures will fail `tests/unittest/api_stability` tests. Get code owner review. - **Integration tests need GPUs + models** — always set `LLM_MODELS_ROOT` and ensure GPU access