One search for your own team's files and the public ecosystem. See how real projects write their agent instructions, and bring the good ideas home.
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.
MicrosoftAGENTS.mdmicrosoft/vscode-docs/docs/agents/concepts/agents.md
An agent is an AI system that uses a language model and tools to complete a goal on your behalf. A language model generates responses based on the information in…
MicrosoftCopilot instructionsmicrosoft/vscode-docs/.github/copilot-instructions.md
Follow the documentation writing guidelines when reviewing or writing documentation.
No other project uses it yet
MicrosoftSkillmicrosoft/vscode-docs/.github/skills/blog-writer/SKILL.md
Plan, write, and review VS Code blog posts. ALWAYS use this skill when the user asks to "write a blog post", "draft a blog", "add a blog post for", "review this blog post", or provides a feature/issue/PR to announce on the VS Code blog. For new posts, it proposes an outline and asks clarifying questions first, and does not edit any files until you approve the plan.
MicrosoftSkillmicrosoft/vscode-docs/.github/skills/content-redirect/SKILL.md
Create and manage redirects in VS Code documentation when pages are moved, renamed, or deleted. Use when moving docs pages, renaming files, restructuring content, or when the user asks about redirects.
MicrosoftSkillmicrosoft/vscode-docs/.github/skills/daily-docs-audit/SKILL.md
Audit recently merged microsoft/vscode pull requests for documentation impact, stage deduplicated issue proposals, and create confirmed issues in microsoft/vscode-docs. ALWAYS use this skill when asked to run or configure a daily docs audit, identify documentation work from merged VS Code PRs, review pending docs issue proposals, or create docs issues for product updates.
MicrosoftSkillmicrosoft/vscode-docs/.github/skills/docs-product-alignment/SKILL.md
Audit and update docs/copilot/ documentation to accurately reflect current VS Code AI capabilities. Use when: competitive analysis reveals gaps, product launches new features, docs use outdated framing, or keyword coverage needs strengthening for discoverability by users and AI agents. Produces a gap analysis plus targeted edits across affected files.
MicrosoftSkillmicrosoft/vscode-docs/.github/skills/doc-writer/SKILL.md
Plan and write VS Code documentation for a new or updated feature. ALWAYS use this skill when the user asks to "document", "add docs for", "write docs for", or "update the docs for" a feature, or provides a GitHub issue/PR link to document — even if the change seems small. Proposes a documentation plan and asks clarifying questions first — it does not edit any files until you approve the plan.
MicrosoftSkillmicrosoft/vscode-docs/.github/skills/frontmatter-description/SKILL.md
Check and optimize MetaDescription frontmatter fields in VS Code documentation. Use when auditing, adding, or improving page descriptions for SEO and discoverability. Apply this when making content changes to markdown articles.
MicrosoftSkillmicrosoft/vscode-docs/.github/skills/generate-release-notes/SKILL.md
generate-release-notes
MicrosoftSkillmicrosoft/vscode-docs/.github/skills/pr-review/SKILL.md
Verify the technical accuracy of a vscode-docs pull request against the VS Code source code in microsoft/vscode. Use when reviewing a docs PR for factual correctness: setting names, command IDs, default values, API shapes, keybindings, versioned availability, and described behavior.
MicrosoftSkillmicrosoft/vscode-docs/.github/skills/release-note-writer/SKILL.md
Guidelines for writing and reviewing Insiders and Stable release notes for Visual Studio Code. This also includes instructions for updating release notes for recovery releases.
MicrosoftSkillmicrosoft/vscode-docs/.github/skills/review-article/SKILL.md
Review a docs article
MicrosoftSkillmicrosoft/vscode-docs/.github/skills/review-blog/SKILL.md
You are a technical writer reviewing a VS Code blog post for clarity, conciseness, and adherence to the writing style guidelines.
MicrosoftSkillmicrosoft/vscode-docs/.github/skills/write-my-release-notes/SKILL.md
Generate VS Code release notes for the features you worked on in a milestone. ALWAYS use this skill when the user asks to "write release notes for my features", "document my milestone features", or "generate release notes from my issues". It gathers the milestone features you own from GitHub, analyzes each feature and its related issues, and writes user-focused feature sections into the milestone release notes file.
MicrosoftAGENTS.mdmicrosoft/agent-governance-toolkit/agent-governance-claude-code/AGENTS.md
The agent-governance-claude-code/ directory contains the first-party Claude Code plugin package for Agent Governance Toolkit. It wires AGT policy evaluation into Claude-native hooks, markdown commands, and a bundled MCP server.
MicrosoftAGENTS.mdmicrosoft/agent-governance-toolkit/agent-governance-dotnet/AGENTS.md
agent-governance-dotnet/ contains the .NET SDK for Agent Governance Toolkit: policy enforcement, execution rings, trust, SRE controls, MCP security, lifecycle management, and auditability for .NET applications.
MicrosoftAGENTS.mdmicrosoft/agent-governance-toolkit/agent-governance-opencode/AGENTS.md
Scope: this folder publishes @microsoft/agent-governance-opencode, the AGT governance plugin for OpenCode. OpenCode loads plugins in-process as async JS/TS functions. The plugin entry point is src/index.mjs, which: - caches a single loadPolicy() state per OpenCode process - maps AGT decisions (allow / review / deny) onto OpenCode's contract: - deny → throw new Error(...) from the hook - review → annotate output.args.__agt_review_reason - allow → return undefined - exposes agt_policy_status and agt_policy_check_text as both in-process custom tools and stdio MCP server…
MicrosoftAGENTS.mdmicrosoft/agent-governance-toolkit/agent-governance-python/agent-mesh/AGENTS.md
AgentMesh is a trust-first communication layer for AI agents — providing cryptographic identity, multi-dimensional trust scoring, scope chains, and governance enforcement for multi-agent systems. Architecture: 4-layer trust stack - All data models use Pydantic BaseModel - Identity: AgentIdentity with .sign(data: bytes) -> str (base64 Ed25519 signatures) - Trust scores: 5 dimensions — competence, integrity, availability, predictability, transparency - DID format: did:mesh:{hex} — see the proof-of-possession note under Boundaries: registry/app.py derives DIDs from the public key, while AgentDID.generate mints a random…
MicrosoftAGENTS.mdmicrosoft/agent-governance-toolkit/agent-governance-python/agent-mesh/sdks/AGENTS.md
This directory contains cross-language AgentMesh SDKs: These SDKs should stay conceptually aligned with the trust, identity, governance, and MCP security surfaces provided elsewhere in the repo. This directory reflects the repo layout at this point in time. Some language implementations may eventually move into standalone top-level directories such as agent-governance-golang/, agent-governance-rust/, or agent-governance-python/. If that happens, treat the standalone top-level directory as the primary home for new work. This directory should then be treated as legacy/shared-layout guidance for the code…
MicrosoftAGENTS.mdmicrosoft/agent-governance-toolkit/agent-governance-python/agent-os/AGENTS.md
Agent-OS is a governance-first kernel for AI agents — a Python framework providing policy enforcement, semantic intent classification, identity management, and execution control for autonomous AI agents. Architecture: 4-layer modular kernel Framework adapters route intervention points through HostSession and receive PolicyEvaluation. Raise the canonical PolicyViolationError.from_evaluation_result(result) for denied or escalated results. Hosts should surface str(error) and use error.evaluation_result.reason_code for structured handling. Use conventional commits: feat:, fix:, docs:, test:, refactor:, chore:
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
