marimo
marimo-team/marimo/AGENTS.md
users Being an open source library, the public API, abstractions, documentation, and the code itself are the product and deserve careful consideration. When working in this repository, you should consider
How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
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.
marimo-team/marimo/AGENTS.md
users Being an open source library, the public API, abstractions, documentation, and the code itself are the product and deserve careful consideration. When working in this repository, you should consider
oxc-project/oxc/AGENTS.md
quality or unreviewed AI content will be closed immediately All AI-generated code must be thoroughly reviewed, tested, and understood by the contributor before submission. Code should meet
comet-ml/opik/AGENTS.md
ignore this directory and use `.agents/` as the canonical source. - `.github/copilot-instructions.md` is GitHub Copilot code review guidance only. ## Security & Configuration Tips - Keep secrets and API keys out of source control
Steady6 mentions in 2 weeks
No other project uses it yet
pubkey/rxdb/AGENTS.md
messages in production builds. Use the error codes from `src/rx-error.ts` and add new error codes if needed like `PL1`, `PL2`. Example: `throw newRxError('PL1', { plugin });` ## Documentation Style - SHOULD use clear
dotnet/maui/AGENTS.md
work, including .NET 12 fixes | `main` | | .NET 11 servicing fixes | Literal `net11`, for review | | Older servicing, release integration, infrastructure, or documentation | The branch designated for that work; do not guess
czlonkowski/n8n-mcp/AGENTS.md
every code change and `npm run build` after MCP server changes. - After rebuilding server code, ask the user to reload the MCP server before testing the changed MCP behavior. - Name
Steady9 mentions in 2 weeks
No other project uses it yet
steipete/CodexBar/AGENTS.md
cold-build comparison, or maintainer-requested cleanup. - Run focused tests during development; the final code needs focused tests plus `make check`, with the full suite from
Steady2 mentions in 2 weeks
No other project uses it yet
openobserve/openobserve/AGENTS.md
enable repo-wide); hold the code you add to this order even though nothing enforces it yet. ## Comments STRICT, and enforced in review — a comment that breaks these is deleted
2025Emma/vibe-coding-cn/AGENTS.md
提示词转换:进入 `libs/external/prompts-library/` 后执行 `python main.py` 按交互提示进行转换,运行前请确认虚拟环境、依赖与输出目录,并在完成后检查生成 Markdown 是否符合 lint 规则。 ## Coding Style & Naming Conventions - 文字层:文档、注释、日志使用中文;代码符号(函数 / 变量 / 模块)统一英文且语义直白,避免晦涩缩写。 - 缩进与排版:全仓保持空格缩进
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
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
Steady2 mentions in 2 weeks
No other project uses it yet
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
Steady2 mentions in 2 weeks
No other project uses it yet
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
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
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
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
Steady3 mentions in 2 weeks
No other project uses it yet
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
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
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
mediar-ai/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
1 project uses a version of this
An open format for instructions to coding agents, read by Codex, Cursor and others. Think of it as a README written for agents.
At the repository root, with more specific files in subdirectories. Agents read the one closest to the file they're editing.
Setup and test commands, code style, and the rules a new contributor would need to know.
Claude Code reads CLAUDE.md. A one-line CLAUDE.md that points at AGENTS.md covers both.