How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
triggerdotdevAGENTS.mdtriggerdotdev/trigger.dev/AGENTS.md
facing, add a `.server-changes/` file instead. See `.server-changes/README.md` for format and documentation. **Write the description for users, not maintainers.** Both changesets and `.server-changes/` notes ship verbatim
Hugging FaceAGENTS.mdhuggingface/transformers.js/.ai/AGENTS.md
install pnpm --filter @huggingface/transformers test pnpm --filter @huggingface/transformers typegen pnpm --filter @huggingface/transformers docs-generate ``` ## Documentation generation Run the full documentation generator after any JSDoc, docs snippet, task metadata, or generated
citrolabsAGENTS.mdcitrolabs/ego-lite/AGENTS.md
lite app bundles its own `ego-browser` binary that embeds this runtime; `skills/ego-browser/SKILL.md` documents that binary's usage (`ego-browser nodejs <<'EOF' ... EOF`). The repo CLI built here takes
CloudflareAGENTS.mdcloudflare/cloudflared/AGENTS.md
consistency**: Use structured logging throughout 6. **Testing coverage**: Aim for comprehensive test coverage 7. **Documentation**: Comment exported functions and types Remember: This is a mission-critical networking tool used
HashiCorpAGENTS.mdhashicorp/packer/AGENTS.md
lint` for PR-relevant lint validation, or the reason they were skipped is documented. - `make generate` was run when config structs or components changed, and the regenerated files are committed
chenhg5AGENTS.mdchenhg5/cc-connect/AGENTS.md
sync.Mutex` or `atomic` types - Use `context.Context` for cancellation propagation - Channels should have clear ownership; document who closes them - Prefer `sync.Once` for one-time teardown (`pendingPermission.resolve()`) ### 7. i18n All user-facing
eigent-aiAGENTS.mdeigent-ai/eigent/AGENTS.md
before creating a new component. 3. Use the semantic tokens and supported component axes documented in the guideline. 4. Treat `src/style/tokens`, `src/style/generated`, and shared UI primitives as the executable source
ElasticAGENTS.mdelastic/logstash/AGENTS.md
type, :default => value` — defined in `logstash-core/lib/logstash/config/mixin.rb`. The framework handles validation, coercion, and documentation generation from these declarations. - **Set output concurrency at the class level** with `concurrency :shared
NanmiCoderAGENTS.mdNanmiCoder/cc-haha/AGENTS.md
changing, read the nested `AGENTS.md` in that directory and any applicable ancestors. Load other documentation when the task needs it. ## Start Here - Run `git status --short` before editing and preserve
NanmiCoderAGENTS.mdNanmiCoder/cc-haha/docs/AGENTS.md
Documentation Instructions These rules apply to `docs/` changes in addition to the root instructions. ## Who the docs are for Two audiences, nothing else. If a page serves neither, it does
NanmiCoderAGENTS.mdNanmiCoder/cc-haha/.github/AGENTS.md
branch protections to make another change pass. Maintainer override labels require an explicit, documented decision. - Repository settings, rulesets, secrets, and required-check changes require explicit user authorization; editing workflow files
NanmiCoderAGENTS.mdNanmiCoder/cc-haha/site/AGENTS.md
React Site Instructions These rules apply to the public landing page and documentation experience under `site/`. ## Contracts that must not break - Keep the site independently installable with
NVIDIAAGENTS.mdNVIDIA/TensorRT-LLM/AGENTS.md
runtime;info:serve"`); see [Module-Level Logging](docs/source/developer-guide/overview.md#module-level-logging) for details. ## Key Documentation | Topic | Path | |-------|------| | Coding guidelines | `CODING_GUIDELINES.md` | | Architecture overview | `docs/source/developer-guide/overview.md` | | PyTorch backend | `docs/source/torch/arch_overview.md` | | Adding a new model
NVIDIAAGENTS.mdNVIDIA/TensorRT-LLM/cpp/tensorrt_llm/batch_manager/kv_cache_manager_v2/AGENTS.md
make changes here depend on the Python KVCacheManagerV2 implementation or its migration documents; those files are temporary and will be removed after the migration. The current C++ headers and tests
palmier-ioAGENTS.mdpalmier-io/palmier-pro/AGENTS.md
async work. - Treat Objective-C and third-party callback isolation as untrusted unless documented. Hop explicitly to the correct actor and use `@Sendable` where a callback crosses isolation. - Avoid `nonisolated
NevaMind-AIAGENTS.mdNevaMind-AI/memU/AGENTS.md
Vector ranking: `tests/test_vector.py` - Embedding providers/gateway: `tests/test_embedding.py` - CLI surface: `tests/test_cli.py` - Host adapter inject seam: `tests/test_host_instruction.py` ## Documentation Rules - Update `README.md` or `npm/README.md` when user-visible behavior changes. - Add or update ADRs under
MicrosoftAGENTS.mdmicrosoft/agent-framework/dotnet/AGENTS.md
necessary public APIs. - **Strong Typing**: Use strong typing to ensure that code is self-documenting and to catch errors at compile time. ## Sample Structure Samples (in `./samples/` folder) should follow
MicrosoftAGENTS.mdmicrosoft/agent-framework/dotnet/samples/AGENTS.md
Samples Structure & Design Choices — .NET > This file documents the structure and conventions of the .NET samples so that > agents (AI or human) can maintain them without rediscovering decisions. ## Directory layout
MicrosoftAGENTS.mdmicrosoft/agent-framework/python/AGENTS.md
AGENTS.md Instructions for AI coding agents working in the Python codebase. **Key Documentation:** - [DEV_SETUP.md](DEV_SETUP.md) - Development environment setup and available poe tasks - [CODING_STANDARD.md](CODING_STANDARD.md) - Coding standards, docstring format, and performance
MicrosoftAGENTS.mdmicrosoft/agent-framework/python/packages/ag-ui/AGENTS.md
Multimodal user inputs support both legacy (`text`, `binary`) and draft-style (`image`, `audio`, `video`, `document`) shapes. - Interrupted runs complete with `RUN_FINISHED.outcome.type == "interrupt"` and canonical `outcome.interrupts`; do not document
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.
