How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
apacheAGENTS.mdapache/storm/AGENTS.md
Security See [Security Model](https://storm.apache.org/security-model.html) - the linked security model for the project's threat model, in-scope / out-of-scope declarations, and known non-findings before reporting issues
gephiAGENTS.mdgephi/gephi/AGENTS.md
skipping flags or checkstyle suppressions to get a build green — fix the underlying issue. ## Security - Never commit secrets, API keys, or tokens. - This is a public repository
apacheAGENTS.mdapache/zeppelin/AGENTS.md
Logging**: SLF4J + Log4j2 - **License**: Apache License 2.0 — all new files need the ASF header ## Security Security model: [SECURITY.md](./SECURITY.md), which links to the project's threat model at [THREAT_MODEL.md](./THREAT_MODEL.md
Forget-CAGENTS.mdForget-C/Jellyfish/AGENTS.md
site/content/blog`）格式与风格规范： - 必须采用稳定章节结构（按需裁剪，但顺序保持一致）： - `Highlights` - `Added` / `Changed` / `Fixed` - `Breaking Changes`（如有行为或契约变化必须填写） - `Deprecations`（如有弃用路径必须填写） - `Security` - `Known Issues` - `Migration Guide` - `Rollback Notes` - `Compatibility Matrix` - `Validation Commands` - `Upgrade Checklist` - `References` - `Notes
pikuAGENTS.mdpiku/piku/AGENTS.md
bottom: globals → utilities → deploy functions → spawn/stop → CLI commands - `sanitize_app_name()` is the security boundary for app names — respect it ### Key functions | Function | Purpose | |---|---| | `do_deploy(app, deltas, newrev)` | Main
open-telemetryAGENTS.mdopen-telemetry/opentelemetry-go/AGENTS.md
pull request, double-check whether the finding or proposed change could involve a security vulnerability. - Do not create public issues or public pull requests, including drafts, for known or suspected
MicrosoftAGENTS.mdmicrosoft/agent-governance-toolkit/agent-governance-claude-code/AGENTS.md
Keep deterministic enforcement in Claude command hooks. - Treat hook and MCP launch wiring as security-sensitive. - Keep docs honest about parity gaps and Claude-specific limitations. - Prefer updating the packaged
MicrosoftAGENTS.mdmicrosoft/agent-governance-toolkit/agent-governance-dotnet/AGENTS.md
Agent Governance Toolkit: policy enforcement, execution rings, trust, SRE controls, MCP security, lifecycle management, and auditability for .NET applications. ## Build and Test Commands ```bash dotnet build AgentGovernance.sln dotnet test AgentGovernance.sln
MicrosoftAGENTS.mdmicrosoft/agent-governance-toolkit/agent-governance-python/agent-mesh/sdks/AGENTS.md
These SDKs should stay conceptually aligned with the trust, identity, governance, and MCP security surfaces provided elsewhere in the repo. ## Transition Note This directory reflects the repo layout **at this
MicrosoftAGENTS.mdmicrosoft/agent-governance-toolkit/agent-governance-rust/AGENTS.md
Agent Governance Toolkit: policy enforcement, trust, audit, identity, lifecycle, execution rings, and MCP security surfaces for Rust applications. ## Build and Test Commands ```bash cargo build --release --workspace cargo test --release
MicrosoftAGENTS.mdmicrosoft/agent-governance-toolkit/AGENTS.md
useful to users. 4. Keep `.github/` changes separate from feature work; they require extra security review. 5. If both a legacy shared path and a standalone top-level path exist
MicrosoftAGENTS.mdmicrosoft/agent-governance-toolkit/docs/AGENTS.md
docs | | `docs/tutorials/` | Step-by-step guides | | `docs/integrations/` | External integration guides | | `docs/security/` | Threat model, OWASP, security guidance | | `mkdocs.yml` | Site navigation and build configuration | ## Documentation Conventions - Be precise and honest
MicrosoftAGENTS.mdmicrosoft/agent-governance-toolkit/.github/pipelines/AGENTS.md
Python, npm, NuGet, Rust, and Go artifacts. ## Critical Rules - Treat every pipeline edit as security-sensitive. - Keep secrets, client IDs, key vault names, and certificate identifiers in pipeline secrets
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.
