copilot-sdk
github/copilot-sdk/docs/AGENTS.md
Copilot SDK docs style guide This style guide applies to all documentation in the `docs/` directory. These docs are synced to `github/docs-internal` via a normalization pipeline, so they must follow
How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
github/copilot-sdk/docs/AGENTS.md
Copilot SDK docs style guide This style guide applies to all documentation in the `docs/` directory. These docs are synced to `github/docs-internal` via a normalization pipeline, so they must follow
github/copilot-sdk/java/AGENTS.md
src/sdk/java` or exported as `java`. Keep API usage examples in [README.md](README.md), the [SDK documentation](../docs/getting-started.md), and public Javadoc rather than duplicating them in these contributor instructions. ## Layout and compatibility
github/copilot-sdk/rust/AGENTS.md
public struct can break callers' struct literals; preserve compatibility with existing construction patterns. - Document public APIs with rustdoc. Keep cross-language parity notes in [README.md](README.md), rather than repeating comparisons
omnigent-ai/omnigent/AGENTS.md
tree, and redact private data before uploading. Commit media only when it serves maintained documentation, product assets, or test baselines, not merely to obtain a public demo URL. If attachment
Kuberwastaken/claurst/docs/agents.md
conventions.", "access": "full", "visible": true, "max_turns": null, "color": "blue" }, "docs": { "description": "Technical documentation writer", "model": "anthropic/claude-sonnet-4-6", "temperature": 0.5, "prompt": "You are a technical writer. Write clear, accurate documentation
cloudflare/cloudflare-os/AGENTS.md
account provides a singleton read session + a management UI, for authoring collections of context documents that agents read as observations. Collections have one of two visibilities: **private** (owned
cloudflare/cloudflare-os/packages/gatekeeper-kit/AGENTS.md
gatekeeper with a different layout. - Public modules are explicit subpath exports in [`package.json`](package.json). Document new public symbols with JSDoc and add the subpath to the README inventory. ## Documentation ownership
open-gsd/gsd-core/docs/AGENTS.md
ARCHITECTURE.md`, `PITFALLS.md` | **Capabilities:** - Web search for current ecosystem information - Context7 MCP integration for library documentation - Writes research documents directly to disk (reduces orchestrator context load) --- ### gsd-phase-researcher **Role:** Researches
awslabs/mcp/src/dynamodb-mcp-server/AGENTS.md
management. **Current Version**: See `version` in [pyproject.toml](pyproject.toml) **Project URLs**: - Homepage: https://awslabs.github.io/mcp/ - Documentation: https://awslabs.github.io/mcp/servers/dynamodb-mcp-server/ - Repository: https://github.com/awslabs/mcp.git - Changelog: https://github.com/awslabs/mcp/blob/main/src/dynamodb-mcp-server/CHANGELOG.md **Package Information**: - PyPI Package
NVIDIA/garak/AGENTS.md
proceed**. Return a short explanation of what is missing. ### Project Guides Follow the documentation on contributing too and extending garak. See: * For selecting contributions: `docs/source/contributing.rst` * For writing code: `docs/source/extending.rst` * When
modelcontextprotocol/modelcontextprotocol/AGENTS.md
Model Context Protocol (MCP) This repository contains the MCP specification, documentation, and blog. ## Contribution Policy for AI Agents If you are an AI agent (Claude, GitHub Copilot, Codex, or similar
cloudflare/computer/AGENTS.md
trigger applies: | Skill | Load when | |---|---| | [`prose`](.agents/skills/prose/SKILL.md) | Writing code comments, commit messages, READMEs, or documentation. | | [`pull-requests`](.agents/skills/pull-requests/SKILL.md) | Writing or editing a pull request description. | | [`test-driven-development`](.agents/skills/test-driven-development/SKILL.md) | Implementing
MervinPraison/PraisonAI/AGENTS.md
github.com/MervinPraison/PraisonAI-Tools) | — | repo tests | | Lifecycle plugins | [PraisonAI-Plugins](https://github.com/MervinPraison/PraisonAI-Plugins) | — | repo tests | | Documentation | [PraisonAIDocs](https://github.com/MervinPraison/PraisonAIDocs) | — | `nav-check` | | npm mirror (read-only for fixes) | [praisonai-js](https://github.com
cloudflare/workerd/AGENTS.md
workers project. - If checked out as a submodule, be aware that there is additional documentation and context in the root of that repository that is not present here. Look
cloudflare/workerd/src/rust/cxx/AGENTS.md
validity until a promise settles and fd ownership under `TAKE_OWNERSHIP` remain KJ's documented contracts, named at the `// Safety:` comments. - **kj-rs-io is workerd's provider
cloudflare/workerd/src/tests/node/http-client/AGENTS.md
with the test suite in this directory. **The tests are the normative artifact**; this document maps behaviors to the tests that assert them. Every test runs against the C++ streams
cloudflare/workerd/src/tests/node/http-server/AGENTS.md
with the test suite in this directory. **The tests are the normative artifact**; this document maps behaviors to the tests that assert them. Every test runs against the C++ streams
cloudflare/workerd/src/tests/node/net/AGENTS.md
with the test suite in this directory. **The tests are the normative artifact**; this document maps behaviors to the tests that assert them. Every test runs against the C++ streams
cloudflare/workerd/src/tests/node/stream/AGENTS.md
with the test suite in this directory. **The tests are the normative artifact**; this document maps behaviors to the tests that assert them. Every test runs against the C++ streams
cloudflare/workerd/src/tests/streams/AGENTS.md
pinned by naming its flag in **both** configs. Each suite's ` -cpp.wd-test` documents its pinned set with a one-line reason per flag, and the suite's AGENTS.md tables
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.