How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
rohitg00AGENTS.mdrohitg00/ai-engineering-from-scratch/AGENTS.md
remains English-only and is intentionally outside the machine-translation pipeline as well. ### code/ - Runs end-to-end and exits 0 on the canonical command for the language. - Self-terminating
aaif-gooseAGENTS.mdaaif-goose/goose/AGENTS.md
changes to agent-loop behavior must be implemented and tested in both paths. When reviewing code, check whether a change to either path also applies to the other and flag
JetBrainsAGENTS.mdJetBrains/kotlin/compiler/AGENTS.md
Representation) Located in `compiler/ir/`. Backend IR is used by all targets for: - Lowering (transforming code to target-friendly form) - Optimization - Serialization to klibs Backend implementations: - `compiler/ir/backend.jvm/` - JVM backend - `compiler/ir/backend.js/` - JavaScript
AstralAGENTS.mdastral-sh/ruff/AGENTS.md
request already addresses the issue, do not submit a competing one without maintainer agreement. ## Code Review Rules For security reviews of Ruff and ty runtime changes, use the [threat models
ayghriAGENTS.mdayghri/i-have-adhd/AGENTS.md
Authorship, labels, safety, review, and PR requirements. | ## Runtime entry points When debugging or changing one integration, begin with its entry point: | Runtime | Read first | | --- | --- | | Claude Code | `.claude-plugin/plugin.json`, `hooks/hooks.json
QuantumNousAGENTS.mdQuantumNous/new-api/AGENTS.md
tool — not a grep, a partial skim, memory, or a summary — before planning, coding, or reviewing, and then follow every rule in it. A task touches billing when it meets
sickn33AGENTS.mdsickn33/agentic-awesome-skills/AGENTS.md
Before PRs, run `npm run validate && npm run test && npm run security:docs`. ## Coding Style & Naming Conventions Use Markdown for skills and docs, JavaScript/Node for most tooling, and Python
danny-avilaAGENTS.mddanny-avila/LibreChat/AGENTS.md
Keep only what the change carries, and describe the code as it stands rather than narrating earlier commits or review rounds. Naming the merged pull request that caused
SentryAGENTS.mdgetsentry/sentry/AGENTS.md
user requests like PR review, branch audit, and Warden follow-up. - If a downstream review harness controls the final response shape, do not hardcode a competing output format
K-Dense-AIAGENTS.mdK-Dense-AI/scientific-agent-skills/AGENTS.md
scripts/`, or `assets/` only when they earn their place. 4. Run the commands and code you document. Scope claims to the release you actually tested ("targets stable GeoPandas
VercelAGENTS.mdvercel-labs/agent-browser/AGENTS.md
cli/src/color.rs`. This module respects the `NO_COLOR` environment variable. Never use hardcoded ANSI color codes. - CLI flags must always use kebab-case (e.g., `--auto-connect`, `--allow-file-access`). Never
alibabaAGENTS.mdalibaba/open-code-review/AGENTS.md
Agent Guidelines for open-code-review This file provides instructions for AI coding assistants working on this project. ## Development Assistance Below are rules that a contributor must follow during development
herdrdevAGENTS.mdherdrdev/herdr/AGENTS.md
already split into state, actions, and input. Keep it that way. - **Platform code is isolated.** OS-specific behavior lives in the matching `src/platform/ .rs` file, with only shared traits, types
ToolJetAGENTS.mdToolJet/ToolJet/AGENTS.md
changes. Keep evidence links current, preserve explicit inference labels, and review map changes with the same owners as the code. Stale context is worse than no context
HKUDSAGENTS.mdHKUDS/DeepTutor/AGENTS.md
reporting | | `visualize` | analyzing → generating → reviewing (SVG / Chart.js / Mermaid / HTML; or routes to Manim sub-stages via `render_type`) | | `math_animator` | concept_analysis → concept_design → code_generation → code_retry → summary → render
tinyhumansaiAGENTS.mdtinyhumansai/openhuman/AGENTS.md
implementation home for behavior that belongs to a vendored project. Before changing code, identify the owning repository below. Implement a module/library capability, bug fix, or contract change in that submodule
wshobsonAGENTS.mdwshobson/agents/docs/agents.md
completeness, consistency, and correctness | ### Quality Assurance & Security #### Code Quality & Review | Agent | Model | Description | | ------------------------------------------------------------------------------------------------ | ----- | --------------------------------------------------------------- | | [code-reviewer](../plugins/comprehensive-review/agents/code-reviewer.md) | opus | Code review with security focus and production reliability | | [security-auditor](../plugins/comprehensive-review/agents/security-auditor.md) | opus | Vulnerability
PostHogAGENTS.mdPostHog/posthog/AGENTS.md
monitor it, or resolve its blockers. Agents may inspect status, fix code and CI, request a stamphog review when a required approval is missing (MCP first, label fallback, see `/merging-prs
GitHubAGENTS.mdgithub/awesome-copilot/AGENTS.md
your contribution works with GitHub Copilot - [ ] Checked that file names follow the naming convention ### Code Review Checklist For instruction files (\*.instructions.md): - [ ] Has markdown front matter - [ ] Has non-empty `description` field
GitHubAGENTS.mdgithub/awesome-copilot/skills/setup-my-iq/assets/templates/AGENTS.md
voice, formatting rules | `communicationStyle` | | Working preferences, hard rules | `preferencesAndConstraints` | | "Tell me about myself" / broad review | All six | Cross-cutting questions (e.g., "what do I do for team X?") may require
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.
