AGENTS.md examples from real projects

sandboxie-plusAGENTS.md

Sandboxie

sandboxie-plus/Sandboxie/AGENTS.md

email or GitHub advisory reporting, and do not submit unverified AI-generated security reports. ## Code review - Review the entire diff, not just the first files/issues found. - Flag every occurrence

No other project uses it yet

agent0aiAGENTS.md

agent-zero / prompts

agent0ai/agent-zero/prompts/AGENTS.md

prompt templates. - Keep placeholder names, include aliases, and template assumptions synchronized with prompt-loading code and extensions. - `agent.system.main.communication.native.md` owns native function-call formatting; profiles may override it alongside the legacy

agent0aiAGENTS.md

agent-zero / a0-create-plugin

agent0ai/agent-zero/skills/a0-create-plugin/AGENTS.md

local/community choice; ask once when it is unknown before creating a new plugin. - Keep review and contribution discoverable through this entrypoint; do not recreate separate router/debug/review/contribution skills. - Keep plugin manifest

No other project uses it yet

elizaOSAGENTS.md

eliza

elizaOS/eliza/AGENTS.md

useful effect, unnecessary tests, defensive code, validation, or truncation. Preserve required safety boundaries. - Validate real behavior end to end and attach results for the reviewed commit. Use existing tests. Avoid

No other project uses it yet

Hugging FaceAGENTS.md

trl

huggingface/trl/.ai/AGENTS.md

must also add a corresponding subsection to `paper_index.md`. When reviewing such PRs, ensure that `paper_index.md` was updated. ### Code duplication and consistency Trainers in this repository are **self-contained by design

ccusageAGENTS.md

ccusage

ccusage/ccusage/AGENTS.md

size` - release profile, dependency features, native packaging size, executable bloat. - `reduce-similarities` - duplicate Rust code detection with `similarity-rs`. - `ast-grep` - structural searches in Rust or TypeScript. - `nushell` - `.nu` scripts

VercelAGENTS.md

agent-desktop

vercel-labs/agent-desktop/AGENTS.md

domains, binary folders, OS allow-list) change only in review. The CI `cargo tree` isolation steps remain the transitive check. ## Coding standards - **400 lines at most per hand-written

wasp-langAGENTS.md

wasp

wasp-lang/wasp/AGENTS.md

involving design decisions) requires a Wasp maintainer's agreement on the approach _before_ the code is written, in a [GitHub issue](https://github.com/wasp-lang/wasp/issues) or in the [`#wasp-dev` channel

gastownhallAGENTS.md

gastown

gastownhall/gastown/AGENTS.md

Stage code changes bd sync # Commit beads changes git commit -m "..." # Commit code bd sync # Commit any new beads changes git push # Push to remote ``` ### Key Concepts - **Priority**: P0=critical

etherAGENTS.md

etherpad

ether/etherpad/AGENTS.MD

Coding Style - **Indentation:** 2 spaces for all files (JS/TS/CSS/HTML). No tabs. - **TypeScript:** All new code should be TypeScript. Strict mode is enabled. - **Comments:** Provide clear comments for complex logic only

xerj-orgPipes a download into a shellAGENTS.md

xerj

xerj-org/xerj/AGENTS.md

pages). **What this project is NOT:** an Elasticsearch clone or fork. It shares no code and no architecture with Elasticsearch or Lucene. It *also* speaks the ES 8.x wire

No other project uses it yet

plotlyAGENTS.md

plotly.js

plotly/plotly.js/AGENTS.md

open a PR for an issue labeled with `plotly-internal`. 2. A human reviews the code before it reaches a pull request. If you cannot see the rendered plot

No other project uses it yet

NVIDIAAGENTS.md

Megatron-LM

NVIDIA/Megatron-LM/AGENTS.md

apply it to `megatron/training` or other training-loop code unless the PR explicitly opts into that migration. - In reviews, flag new direct `parallel_state.get_*_group()` usage in `megatron/core` unless

emcie-coAGENTS.md

parlant

emcie-co/parlant/AGENTS.md

again until you get it. 4. Implement the tests first. Ask for confirmation and code review. 5. Once tests are approved, once again suggest your implementation plan for making them

lidge-junPipes a download into a shellAGENTS.md

opencodex

lidge-jun/opencodex/AGENTS.md

This file summarizes; it never overrides it. ## Review guidelines These rules apply to all code reviews on this repository, including automated reviewers (Codex, CodeRabbit). - **Language:** always review in English, regardless

lidge-junAGENTS.md

opencodex

lidge-jun/opencodex/.github/AGENTS.md

boundary Every workflow, ownership, branch-enforcement, release, or repository-automation change requires explicit security review under `MAINTAINERS.md`. ## Workflow rules - Grant the minimum required `permissions`. - Pin third-party actions to immutable

No other project uses it yet

lidge-junAGENTS.md

opencodex / gui

lidge-jun/opencodex/gui/AGENTS.md

cache `c`/`w`) - URLs / localhost endpoints, adapter ids (`oauth`, `passthrough`, npm channels) - Keep **code comments** (including shell `# …` comments in samples). Never strip them to “satisfy” i18n. - Run `bun run lint

lidge-junAGENTS.md

opencodex / src

lidge-jun/opencodex/src/AGENTS.md

APIs. Introduce a Node-only runtime dependency only when the task explicitly requires compatibility code and the owning module already has that role. - Preserve existing public exports and configuration compatibility

No other project uses it yet

lidge-junAGENTS.md

opencodex / structure

lidge-jun/opencodex/structure/AGENTS.md

that followed it. Reasoning written as ordinary prose is not detectable and stays a review judgement. The check is a literal match, which is why this line describes the marker

No other project uses it yet

laramiesAGENTS.md

theHarvester

laramies/theHarvester/AGENTS.md

payloads out of commits, fixtures, diagnostic logs, and development or review artifacts. ## Read for the task - For setup, coding conventions, contribution workflow, or release preparation, use the relevant section