wekan
wekan/wekan/AGENTS.md
section links a commit that release does not contain. The contributor's half is review. Nobody but the maintainer commits to `main` in wekan/wekan, so a change from anyone else
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.
wekan/wekan/AGENTS.md
section links a commit that release does not contain. The contributor's half is review. Nobody but the maintainer commits to `main` in wekan/wekan, so a change from anyone else
pydantic/pydantic-ai/AGENTS.md
slow and CI covers them at the right time. # Coding Guidelines When generating or reviewing code anywhere in this repo, always read [agent_docs/index.md](agent_docs/index.md) and follow/enforce those guidelines
pydantic/pydantic-ai/docs/AGENTS.md
fence, such as `{test="skip" lint="skip"}`, rather than adding tooling suppressions to pedagogical code. Examples that are linted are also type-checked with pyright; opt one out with `typecheck
pydantic/pydantic-ai/pydantic_ai_slim/pydantic_ai/durable_exec/AGENTS.md
implementation rename unless the migration of in-flight executions is intentional and reviewed. Resolve base and per-tool configuration with `OperationConfigRole` and `DurableOperationId`. Handle known ID variants and retain
pydantic/pydantic-ai/src/pydantic_ai_harness/AGENTS.md
collection of pre-made capabilities for Pydantic AI. - **AICA**: AI Code Assistant -- the automated agent that implements issues, reviews plans, and handles PR feedback ## AICA preflight Before implementing or reviewing
nats-io/nats-server/AGENTS.md
interested in talking to agents when reviewing issues or PRs. Advise your human not to meat-proxy when contributing to NATS. When writing code: * Fixes must have accompanying unit tests
Steady3 mentions in 2 weeks
No other project uses it yet
monkeytypegame/monkeytype/AGENTS.md
type-check` instead of `tsc`. Coding standards (styling, icons, refs, modals) for writing and reviewing code: `CODING_STANDARDS.md`. Before any browser testing, read `docs/AGENT_BROWSER.md` (dev server, `window.__mt` debug handle, gotchas). Roadmap
gravitational/teleport/AGENTS.md
AGENTS.md ## Review Guidelines - Focus only on critical security, reliability, performance, and scalability issues. - Ignore style, performance micro-optimizations, and readability nits unless they are tied to a significant failure ### What
gravitational/teleport/docs/AGENTS.md
written in MDX. These guidelines apply to changes under `docs/`; for code changes, see the repo-root `AGENTS.md`. ## Review guidelines - Focus on accuracy, structure, and conventions. Flag issues
peass-ng/PEASS-ng/AGENTS.md
merge approved changes back into it. Target release branches only when required. Respect reviews, checks, and branch protection. - **Create only needed branches.** Check `git status` and worktrees first
Steady9 mentions in 2 weeks
No other project uses it yet
dotnet/roslyn/AGENTS.md
EditorFeatures,VisualStudio,LanguageServer}` - [`Razor.instructions.md`](.github/instructions/Razor.instructions.md) — `src/Razor` - **Task-specific skills:** [`.github/skills/`](.github/skills/) (auto-discovered; e.g. `code-review`, `ci-analysis`, `update-agent-docs`). ## Orientation protocol 1. Read [`.github/copilot-instructions.md`](.github/copilot-instructions.md). 2. Read [`.github/memory/INDEX.md
JetBrains/intellij-community/AGENTS.md
order. - User-visible strings belong in `*.properties` for localization. ## Language - Read [Code Style](./.agents/skills/code-style/SKILL.md) before writing or reviewing Kotlin or Java. - Read [Rust Code Style](./.agents/skills/rust-code-style/SKILL.md) before writing or reviewing
google/filament/AGENTS.md
Synchronization guidelines for Java/JNI (Android) and JavaScript/TypeScript (Web/WASM) when public C++ APIs change. ### 6. Code Review & Invariant Auditing * [skills/code_review/SKILL.md](skills/code_review/SKILL.md): Adversarial systems, concurrency, memory-model, and architecture code review protocol
komi-store/komi-store/AGENTS.md
workarounds. No em-dashes. - Don't guess APIs, versions or flags. Read the code or the docs first. ## Read when relevant - `docs/agents/architecture.md`: layers, navigation, DI, core repositories, adding a feature
Surging1 mention in 2 weeks
3 projects use a version of this
microsoft/fluentui/AGENTS.md
copy these) - **DO NOT copy patterns from `packages/react/` (v8).** That's maintenance-only legacy code using runtime styling, class components, and different APIs. - **DO NOT use `@fluentui/react` imports
AgriciDaniel/claude-seo/AGENTS.md
Read`, `Write`, `Edit`, `Bash`, `Glob`, `Grep`, `WebFetch`), each harness typically has an equivalent: | Claude Code | Codex | Cline | Aider | Cursor / Antigravity | |---|---|---|---|---| | Read | read_file | read_file | (inline) | read | | Write | write_file
No other project uses it yet
whyour/qinglong/AGENTS.md
symbols, 6698 relationships, 233 execution flows). Use the GitNexus MCP tools to understand code, assess impact, and navigate safely. > Index stale? Run `node .gitnexus/run.cjs analyze` from the project root
storytold/pdfcraft/AGENTS.md
agent answers for what it opens and for its review comments. 2. **Check, then claim.** Before writing code, read the issue comments, search pull requests for `#N` and the keywords
Steady4 mentions in 2 weeks
1 project uses a version of this
longbridge/gpui-kit/AGENTS.md
limitations. Do not start a review with findings alone; include the purpose and reasonableness assessment even when no issues are found. ## Code Style - Follow naming and organization patterns from existing
google/gvisor/AGENTS.md
/path/to:some_test`. - Comments must describe the code as it is for the future codebase readers, not for present-time PR reviewers. A comment that talks about a bug that
No other project uses it yet
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.