How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
gtappsAGENTS.mdgtapps/skills/skills/review-to-pr/references/agents.md
Codex, Grok CLI and Copilot CLI workflow for review-to-pr. Verifies finished work, commits it locally, has a separate reviewer CLI review it read-only, applies the confirmed findings through review-findings, re-verifies, and opens or updates the PR.
gtappsAGENTS.mdgtapps/skills/skills/task-report/references/agents.md
Publish a completed task's debrief as a Codex.ai Artifact — outcome verdict, decisions made, verification evidence, review-priority file map, mechanically-rendered diffs, and copy-as-prompt follow-ups. Trigger on /task-report or when the user asks to summarize what you did, show what changed in this task/session, make a report/debrief/recap/handoff of the work, or review completed work — even phrased casually ("show me what you changed", "wrap this up as a report"). Do NOT use for a quick factual question about one file or change (answer in prose), for reviewing code for bugs (that's code review), or for plans awaiting approval (that's plan-to-artifact).
dcsgAGENTS.mddcsg/keel/website/agents.md
18 domain agents that review plans, audit code, and implement features. How they work with rule packs, how routing works, how to customize.
launchapp-devAGENTS.mdlaunchapp-dev/animus-cli/.agents/skills/rust-skills/AGENTS.md
Comprehensive Rust coding guidelines with 179 rules across 14 categories. Use when writing, reviewing, or refactoring Rust code. Covers ownership, error handling, async patterns, API design, memory optimization, performance, testing, and common anti-patterns. Invoke with /rust-skills.
chasebuildAGENTS.mdchasebuild/fuelcheck-cli/.agents/skills/rust-skills/AGENTS.md
Comprehensive Rust coding guidelines with 179 rules across 14 categories. Use when writing, reviewing, or refactoring Rust code. Covers ownership, error handling, async patterns, API design, memory optimization, performance, testing, and common anti-patterns. Invoke with /rust-skills.
xiaolaiAGENTS.mdxiaolai/cc-suite/AGENTS.md
Project instructions for cc-suite — the Claude Code plugin that bridges Claude Code, Codex CLI, and Antigravity CLI (agy) with single-source AGENTS.md, shared skills, mirrored hooks, and bidirectional MCP delegation; adds Claude→Grok delegation, bounded Qwen review, and opt-in MCP bridging to more coding agents.
obraAGENTS.mdobra/superpowers/AGENTS.md
theoretical fixes Every PR must solve a real problem that someone actually experienced. "My review agent flagged this" or "this could theoretically cause issues" is not a problem statement
NousResearchAGENTS.mdNousResearch/hermes-agent/agent/AGENTS.md
name == ...` chain); `tools/todo_tool.py` is the pattern. ## Message-flow invariants (every change is reviewed against these) - **Prompt caching must not break.** Never alter past context, change toolsets, reload memories, or rebuild
NousResearchAGENTS.mdNousResearch/hermes-agent/AGENTS.md
unfixed code, build the fix, iterate until the lane is green, then open the PR — the live receipt on the exact head is the Windows proof reviewers ask for. Extend
NousResearchAGENTS.mdNousResearch/hermes-agent/cron/AGENTS.md
pool is keyed by home (`cron.max_parallel_jobs` is per profile); and the stale-code yield gate asks `scheduler_ownership.owns_cron_tick_for(home)` / `live_gateway_ticking(home)` instead
affaan-mAGENTS.mdaffaan-m/ECC/AGENTS.md
design and scalability | Architectural decisions | | tdd-guide | Test-driven development | New features, bug fixes | | code-reviewer | Code quality and maintainability | After writing/modifying code | | security-reviewer | Vulnerability detection | Before commits, sensitive
affaan-mAGENTS.mdaffaan-m/ECC/.codex/AGENTS.md
metadata Available skills: - tdd-workflow — Test-driven development with 80%+ coverage - security-review — Comprehensive security checklist - coding-standards — Universal coding standards - frontend-patterns — React/Next.js patterns - frontend-slides — Viewport-safe HTML
DeepSeekAGENTS.mddeepseek-ai/deepseek-harness/AGENTS.md
transaction, or lifecycle boundary. Do not narrate control flow or tests, preserve review history, or restate code. Keep behavior, failure, timing, ownership, and safe-use facts; link the rationale
DeepSeekAGENTS.mddeepseek-ai/deepseek-harness/docs/AGENTS.md
timing, ownership, modality, exceptions, consequences, and non-obvious orientation; delete narration, test walkthroughs, review analysis, and code restatement. Keep the local contract and link its rationale. Use [dsh-prose-standard
DeepSeekAGENTS.mddeepseek-ai/deepseek-harness/native/system/AGENTS.md
packages have one independent version and release workflow. ## Runtime rules - Landlock's argv, exit codes, diagnostics, and fail-closed confinement are defined in [docs/cli-contract.md](docs/cli-contract.md). Do not change them when
DeepSeekAGENTS.mddeepseek-ai/deepseek-harness/packages/client/AGENTS.md
current design; these are the rules you must not violate when writing or reviewing client code: 1. **Two declaration forms**: use `ctx.slots.register({ name, children?, store?, inject? }, Component)` for a parent
n8n-ioAGENTS.mdn8n-io/n8n/AGENTS.md
system` skill in reviews ### Verify changes - Run focused tests from the owning package: `pnpm test `. - Run that package's `pnpm lint` and `pnpm typecheck` before committing code. Build first when
MicrosoftAGENTS.mdmicrosoft/vscode/extensions/copilot/assets/prompts/skills/agent-customization/references/agents.md
Supported Events `SessionStart`, `UserPromptSubmit`, `PreToolUse`, `PostToolUse`, `PreCompact`, `SubagentStart`, `SubagentStop`, `Stop` ### Example ```yaml --- description: "Secure code reviewer that blocks dangerous commands" tools: [read, search, execute] hooks: PreToolUse: - type: command command: "./scripts/block-dangerous-cmds.sh
MicrosoftAGENTS.mdmicrosoft/vscode/extensions/copilot/src/extension/chatSessions/copilotcli/AGENTS.md
Copilot CLI agent: * File Operations * Shell Operations * Search Operations * Agent & Task Operations * User Interaction * Code Review & Git * Data, Memory & MCP * Security ### `common/copilotCLIPrompt.ts` Parses raw user prompts and extracts structured chat
MicrosoftAGENTS.mdmicrosoft/vscode/src/vs/platform/agentHost/node/copilot/prompts/AGENTS.md
other prompt or filesystem inputs to this setting without an explicit security review. Code-managed prompt experiments should still use a contributor (Lever 2) gated
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.
