AGENTS.md examples from real projects

NVIDIAAGENTS.md

NemoClaw / langchain-deepagents-code

NVIDIA/NemoClaw/agents/langchain-deepagents-code/AGENTS.md

Deep Agents Code Integration Use the shared dependency-upgrade workflow for version changes. This guide describes the maintained component boundaries, not a release checklist. ## Build and runtime ownership `requirements.in

NVIDIAAGENTS.md

NemoClaw

NVIDIA/NemoClaw/AGENTS.md

rerun affected checks without asking at each step. Continue into PR publication and review follow-up when requested. A first patch or lifecycle handoff is not completion. Keep local verification

NVIDIAAGENTS.md

NemoClaw

NVIDIA/NemoClaw/docs/AGENTS.md

review documentation. This file owns agent-specific documentation routing and workflow. - Write clear, accurate, task-oriented documentation for developers who run NemoClaw with OpenClaw, Hermes, LangChain Deep Agents Code

No other project uses it yet

NVIDIAAGENTS.md

NemoClaw / tools

NVIDIA/NemoClaw/.dsh/tools/AGENTS.md

they matter. - Prefer a direct, focused tool over overlapping projections or orchestration layers. Ordinary code review, representative harness exercises, and repository hooks are the validation boundary. Do not add repository

No other project uses it yet

NVIDIAAGENTS.md

NemoClaw / messaging

NVIDIA/NemoClaw/src/lib/messaging/AGENTS.md

messaging egress opt-in unless accepted product policy states otherwise. Load `nemoclaw-maintainer-security-code-review` when the change affects credentials, public ingress, sender authorization, network policy, or another trust

No other project uses it yet

mochajsAGENTS.md

mocha

mochajs/mocha/AGENTS.md

node runtime behavior, include smoke + targeted node suite. ### CJS to ESM migration conventions (runtime code) - Scope: prioritize runtime modules under `lib/`; do not include test fixtures unless explicitly requested

vectordotdevAGENTS.md

vector

vectordotdev/vector/AGENTS.md

avoid "Co-Authored-By: Claude" attribution) - **Pull requests:** Do NOT add "Generated with Claude Code" or similar footers — keep PR descriptions focused on the technical changes ### Preserve Open Pull Request

foremAGENTS.md

forem

forem/forem/AGENTS.md

repetitive events. ## Testing Standards - **Regression Tests are Mandatory**: specific regression tests to verify your code works are required for almost all PRs. - **Follow Test Patterns**: Use `create(:factory)` syntax (FactoryBot

No other project uses it yet

PrimeIntellect-aiAGENTS.md

prime-agent

PrimeIntellect-ai/prime-agent/AGENTS.md

commit scripts or tools that no workflow, Makefile target, or other code runs (one-off review, parity, or reproduction scripts). Put their results in the PR body

No other project uses it yet

jhipsterAGENTS.md

generator-jhipster

jhipster/generator-jhipster/AGENTS.md

composition; blueprinted sub-generators are discovered and composed in `beforeQueue`. - `lib/` holds shared, **exported** code: `lib/jdl` (Chevrotain-based JDL parser), `lib/testing` (test harness, also importable as `#testing`), `lib/utils`, `lib/eslint`, `lib/ci

screenpipeAGENTS.md

screenpipe

screenpipe/screenpipe/AGENTS.md

requires both markers. ## Testing Test your work at the narrowest boundary that proves it — review is the bottleneck. For ordinary desktop React/layout changes, use the browser-mock loop documented

MicrosoftAGENTS.md

onnxruntime

microsoft/onnxruntime/AGENTS.md

github/skills/). Load each skill whose description matches the requested task, subsystem, or behavior. For code reviews, follow the `/code-review` skill in addition to relevant domain skills and matching path-scoped

HomebrewDeletes or force-pushesAGENTS.md

homebrew-cask

Homebrew/homebrew-cask/AGENTS.md

Agent Instructions for homebrew-cask This document helps coding agents produce high-quality PRs for Homebrew Cask contributions. ## Before Any PR 1. **Check for existing PRs** for the same cask

dyad-shAGENTS.md

dyad

dyad-sh/dyad/AGENTS.md

will run against stale code and results will be misleading. Only changes to test code itself (e.g. files in `e2e-tests/`) do not require a rebuild. See [rules/e2e-testing.md](rules/e2e-testing.md

No other project uses it yet

handsontableReads credentialsAGENTS.md

handsontable

handsontable/handsontable/AGENTS.md

evals/README.md` | | Step-by-step task workflows | `.claude/skills/` (e.g., `handsontable-dev`, `handsontable-plugin-dev`, `handsontable-code-review`, `pr-creation`) | `.ai/` reference locations: | `.ai/` location | Scope | |---|---| | `.ai/` (root) | Monorepo — stack, structure, build

handsontableAGENTS.md

handsontable / visual-tests

handsontable/handsontable/visual-tests/AGENTS.md

creating-visual-test-examples` skills, the PR template, the `pr-creation` and `handsontable-code-review` skills, `.ai/LOCAL-ENFORCEMENT.md`) carries one sentence and a link here. `.github/scripts/__tests__/visual-decision-rule.test.mjs` pins the paragraph to this

QwikDevAGENTS.md

qwik

QwikDev/qwik/AGENTS.md

grown out of that shape, rewrite it into that order before review instead of stacking fix-up commits. ### Code Quality #### Sanity - Remember to keep your code DRY. - Do not leave

QwikDevAGENTS.md

qwik

QwikDev/qwik/.ruler/AGENTS.md

grown out of that shape, rewrite it into that order before review instead of stacking fix-up commits. ### Code Quality #### Sanity - Remember to keep your code DRY. - Do not leave

matomo-orgAGENTS.md

matomo

matomo-org/matomo/AGENTS.md

specific skills when those skills are available. It is intended for: - AI coding agents - Matomo core engineers - Reviewers looking for a shared baseline This is not a generic PHP guide

gitbutlerappAGENTS.md

gitbutler

gitbutlerapp/gitbutler/AGENTS.md

reviewable changes; avoid unrelated rewrites. - Use the simplest design that solves the actual problem; do not add speculative machinery, and remove machinery your change makes unnecessary. - Inspect nearby code before