How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
MicrosoftAGENTS.mdmicrosoft/agent-governance-toolkit/docs/AGENTS.md
Documentation - Coding Agent Instructions ## Project Overview The `docs/` tree powers the published documentation site for Agent Governance Toolkit: reference material, tutorials, architecture docs, threat modeling, compliance content, package pages
MicrosoftAGENTS.mdmicrosoft/agent-governance-toolkit/examples/AGENTS.md
still match the file layout. - Keep example policies and sample outputs consistent with the documented scenario
MicrosoftAGENTS.mdmicrosoft/agent-governance-toolkit/examples/demos/AGENTS.md
credentials belong in environment variables or local secrets only, never in code or docs. - Document prerequisites, expected cost, and runtime side effects. - Prefer localhost-safe defaults and explicit
MicrosoftAGENTS.mdmicrosoft/agent-governance-toolkit/policy-engine/AGENTS.md
Never commit secrets, credentials, or raw sensitive payloads in logs or fixtures. ## Prose style Documentation prose must be dense and technical. Do not use em dashes. Do not use colons
ThinkInAIXYZAGENTS.mdThinkInAIXYZ/deepchat/AGENTS.md
tests before handoff. - Commit only the smallest durable tests for user-visible behavior, documented contracts, persistence or migration, lifecycle or concurrency, recovery, security boundaries, or proven regressions. Prefer
MicrosoftAGENTS.mdmicrosoft/aspire/AGENTS.md
shapes or why a glob was split or broadened in the PR or maintenance documentation. Apply that precision to expensive or class-sharded selector-gated work. For smaller unsharded jobs
uditgoenkaAGENTS.mduditgoenka/autoresearch/AGENTS.md
scenarios | | `autoresearch:predict` | Multi-persona swarm — 5 expert perspectives before acting | | `autoresearch:learn` | Autonomous documentation engine — scout, generate, validate, fix | | `autoresearch:reason` | Adversarial refinement — blind judge panel for subjective domains
SylinkoAGENTS.mdSylinko/Everywhere/AGENTS.md
Change Discipline - Inspect the current implementation and its call sites before changing it. Design documents may lag behind the code after later refactoring and are not automatically authoritative. - Preserve unrelated
ningzimuAGENTS.mdningzimu/codex-ppt-skill/AGENTS.md
Commit messages, PR titles, changelog entries, and release notes must be written in English. - Documentation changes must update all existing language versions in sync, including repository README files
ikaijuaAGENTS.mdikaijua/Awesome-AITools/AGENTS.md
additions/removals/renames. - `scripts/format_readmes.py` — Maintenance/normalization script. ## Architecture The repo is structured as two parallel, mirrored documents that must stay in sync: - `README.md` and `README-CN.md` share the same category structure, the same
jacob-bdAGENTS.mdjacob-bd/gemini-notebook-mcp-cli/AGENTS.md
errors - Free tier: ~50 queries/day - Wait until the next day or upgrade to Plus ## Documentation ### API Reference **For detailed API documentation** (RPC IDs, parameter structures, response formats), see: **[docs/API_REFERENCE.md](./docs/API_REFERENCE.md
MicrosoftAGENTS.mdmicrosoft/VFSForGit/AGENTS.md
friends) put build outputs **one level up** from the git working tree. The Readme documents the recommended clone-into-`src\` convention, which matches the layout that `gvfs clone` creates
UfoMiaoAGENTS.mdUfoMiao/zcf/AGENTS.md
directly. Tests mirror the runtime tree inside `tests/` (`unit/`, `integration/`, and helper fixtures), and documentation resides in `docs/` plus localized READMEs. ## Build, Test, and Development Commands - `pnpm install` — sync dependencies
huangruitengAGENTS.mdhuangruiteng/loopx/AGENTS.md
others --exclude-standard`. 2. Classify every changed path before staging: - core product code; - core documentation; - durable validation smoke; - local/private state; - low-value or obsolete artifact. 3. Scan candidate paths
Microsoft AzureAGENTS.mdAzure/azure-sdk-for-net/AGENTS.md
Azure SDK for .NET - AI Agent Guidelines This document provides guidelines for AI agents (e.g., GitHub Copilot, MCP-based assistants, LLM-based tools) working with the Azure
FlorianBruniauxAGENTS.mdFlorianBruniaux/claude-code-ultimate-guide/AGENTS.md
Claude Code Ultimate Guide - Project Context ## Purpose This repository is the **comprehensive documentation for Claude Code** (Anthropic's CLI tool). It teaches users how to use Claude Code effectively through
kenn-ioAGENTS.mdkenn-io/agentsview/AGENTS.md
hostnames, personal identities, infrastructure details, and absolute user paths out of code, tests, fixtures, documentation, commit messages, and pull request text. Run the private-data scrub before publishing. - Write changelog
jacklandrinAGENTS.mdjacklandrin/OnlySwitch/AGENTS.md
macOS app, widgets, remote app, Swift Package modules, tests, OpenClaw integration, and project documentation. ## Workflow For every task, follow these steps in order. Each phase is delegated to the named
antfuAGENTS.mdantfu/skills/AGENTS.md
Skills Generator Generate [Agent Skills](https://agentskills.io/home) from project documentation. PLEASE STRICTLY FOLLOW THE BEST PRACTICES FOR SKILL: https://platform.claude.com/docs/en/agents-and-tools/agent-skills/best-practices - Focus on agents capabilities and practical usage patterns
oomol-labAGENTS.mdoomol-lab/open-connector/AGENTS.md
upstream-compatible field has no local source yet, prefer omitting it or returning a documented empty value from the serializer rather than scattering optional fields in routes. ## Providers - Provider code
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.
