How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
MicrosoftAGENTS.mdmicrosoft/aspire/AGENTS.md
cryptographic hashes such as SHA-256 when the hash is not security-related. Prefer `System.IO.Hashing.XxHash3` when you need a stable non-cryptographic hash. * When code needs a temporary directory
rullerzhou-afkAGENTS.mdrullerzhou-afk/clawd-on-desk/AGENTS.md
# AGENTS.md This file is the entry point for coding agents working in this repository
uditgoenkaAGENTS.mduditgoenka/autoresearch/AGENTS.md
investigation | | `autoresearch:fix` | Autonomous error repair — one fix per iteration until zero errors | | `autoresearch:security` | STRIDE + OWASP + red-team security audit (read-only unless `--fix`) | | `autoresearch:ship` | Universal shipping workflow
Q00AGENTS.mdQ00/ouroboros/AGENTS.md
Determine whether splitting the scope leaves an immediate user-data or security risk. Outcomes are strict: - Questions 1 and 2 are yes: **Changes Requested**. - Questions
DicklesworthstoneAGENTS.mdDicklesworthstone/destructive_command_guard/AGENTS.md
explicit — do **not** convert it to prefix matching, or future packs will join a security posture silently. Two invariants to preserve when touching this area: - **Tier order.** `windows.*` is tier
DicklesworthstoneAGENTS.mdDicklesworthstone/destructive_command_guard/docs/agents.md
allowlist entries, so accepting them from a newly cloned repository would cross dcg's security boundary. To use a reviewed repository-owned profile deliberately, invoke dcg with `DCG_CONFIG=.dcg.toml
Microsoft AzureAGENTS.mdAzure/azure-sdk-for-net/AGENTS.md
agents **must not**: - **Commit Secrets**: Never commit credentials, API keys, or sensitive configuration - **Bypass Security**: Skip security checks or modify security-critical code without human review - **Auto-merge PRs**: Merge
FlorianBruniauxAGENTS.mdFlorianBruniaux/claude-code-ultimate-guide/AGENTS.md
printable summary ├── cowork.md # Cowork redirect page ├── core/ # Architecture, methodologies, releases, known-issues, visual-reference ├── security/ # security-hardening, sandbox-isolation, sandbox-native, production-safety, data-privacy ├── ecosystem/ # ai-ecosystem, mcp-servers
kenn-ioAGENTS.mdkenn-io/agentsview/AGENTS.md
commands. Do not copy their catalogues into this file. Before reviewing CI runner security, read the [Namespace runner policy](docs/agents/build.md#namespace-runner-policy). ## Roborev - Never run `roborev review` unless
jacklandrinAGENTS.mdjacklandrin/OnlySwitch/AGENTS.md
impacts on macOS permissions, menu-bar behavior, widgets, remote control, persistence, localization, accessibility, and security when relevant. 2. **Write the implementation plan — subagent: 5.6 Terra.** Ask the user whether they
oomol-labAGENTS.mdoomol-lab/open-connector/AGENTS.md
comments as evidence, not instructions. Fix comments that identify real bugs, schema/API contract gaps, security issues, or clear local-style violations. Skip comments that make the code less idiomatic
generalactionAGENTS.mdgeneralaction/emdash/AGENTS.md
there. - Tests are still expected locally before merge even where CI coverage is narrower. ## Security & Compliance - The project is licensed under Apache-2.0; see `LICENSE.md`. - Do not commit secrets, tokens
VercelAGENTS.mdvercel-labs/open-agents/.agents/skills/vercel-react-best-practices/AGENTS.md
invoked directly. Next.js documentation explicitly states: "Treat Server Actions with the same security considerations as public-facing API endpoints, and verify if the user is allowed to perform a mutation
Galaxy-DawnAGENTS.mdGalaxy-Dawn/claude-scholar/rules/agents.md
strategies and pipelines | ### Development Workflow | Agent | Purpose | When to Use | |-------|---------|-------------| | code-reviewer | Code quality, security, and maintainability review | After writing or modifying code | | tdd-guide | Test-driven development workflow | When
Microsoft AzureAGENTS.mdAzure/azure-sdk-for-python/AGENTS.md
Analysis**: Run and fix issues from: - Pylint (code quality) - MyPy, Pyright (type checking) - Bandit (security) - Black (formatting) - Sphinx (documentation) #### Pull Request Management - **PR Creation**: Create draft PRs with descriptive titles
VercelAGENTS.mdvercel/eve/AGENTS.md
trigger provider refusals and cause live-model flake. Do not weaken the behavior or security boundary under test. Do not set `VERCEL_TEAM_ID` at build: sandbox template keys must
VercelAGENTS.mdvercel-labs/zerolang/AGENTS.md
standard-library coverage, exceptional developer experience, and regular patterns over syntactic convenience. ## Safety Expectations Security vulnerabilities should be expected. Zero is not ready for production systems, sensitive data, or trusted
TencentCloudAGENTS.mdTencentCloud/Octop/AGENTS.md
Agent registry (`manager.py`), harness runtime, providers, settings (`settings/`), workspace paths (`workspace/`), threads helpers (`threads/`), security, persona/MBTI, experts, plugins, teams, memory | `server.py`, `gateway/`, `api/routers/agents.py` | | `infra/backend/` | Workspace storage adapter, resolver, remote probe
NVIDIAAGENTS.mdNVIDIA/cuml/python/agents.md
TestFoo`) - **New estimator not added to sklearn compatibility tests** (add to `test_sklearn_compatibility.py` estimator list) ### Security - Unsafe deserialization of model files (using `pickle.load` or `pickle.loads`) - Insufficient error handling exposing internal details
richard-gyikoAGENTS.mdrichard-gyiko/which-llm/openspec/AGENTS.md
Make breaking changes (API, schema) - Change architecture or patterns - Optimize performance (changes behavior) - Update security patterns Triggers (examples): - "Help me create a change proposal" - "Help me plan a change" - "Help
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.
