Agent Package Manager
APM (Agent Package Manager) is an open-source dependency manager from Microsoft that brings package-manager conventions to AI agent configuration. Developers declare agent dependencies once in an `apm.yml` manifest, covering instructions, skills, prompts, hooks, plugins, and MCP servers, and a single `apm install` command reproduces the full setup across Claude Code, GitHub Copilot, Cursor, Codex, Gemini, and Windsurf. The tool resolves transitive dependencies the way npm or pip does, pins resolved sources and content hashes in an `apm.lock.yaml` lockfile, and scans installs for hidden Unicode that can manipulate LLM behavior. A notable feature is `apm compile -t copilot`, which writes `.github/copilot-instructions.md` automatically with no additional configuration. Enterprise teams can enforce source allowlists and primitive restrictions through an `apm-policy.yml` file with tighten-only inheritance from enterprise down to repository level. The project targets developers and security teams who need reproducible, auditable agent context across multi-agent, multi-tool projects.
- ✓Open-source license (MIT)
- ✓Actively maintained (<30d)
- ✓Healthy fork ratio
- ✓Topics declared
- ✓Trusted owner (microsoft)
- ✓Documented (README)
git clone https://github.com/microsoft/apm && cp apm/*.md ~/.claude/agents/23 items in this repository
Use this skill to verify CLAIM-LEVEL grounding of a documentation page (or set of pages) against the source code. Activate when you have specific pages to check for factual accuracy -- not when sweeping a whole corpus (use docs-corpus-audit for that) and not when triaging a PR diff (use docs-sync for that). Trigger nouns: "is this doc accurate", "verify the page against the code", "fact-check this section", "any claims that drifted from source", "fact-checking", "grounding audit", "drift hunt", "claim verification". Returns per-claim verdicts (GROUNDED | PARTIAL | CONTRADICTED | UNSUPPORTED) with file:line evidence citations. Catches paragraph-level inaccuracies that page-level audit averages over -- e.g. a paragraph with 5 claims where 4 are grounded and 1 is fabricated. Does NOT modify files (returns advisory only); does NOT re-architect the docs; does NOT triage PRs.
Subagents overview
What people ask about apm
What is microsoft/apm?
+
microsoft/apm is subagents for the Claude AI ecosystem. Agent Package Manager It has 2.9k GitHub stars and was last updated today.
How do I install apm?
+
You can install apm by cloning the repository (https://github.com/microsoft/apm) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is microsoft/apm safe to use?
+
Our security agent has analyzed microsoft/apm and assigned a Trust Score of 100/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains microsoft/apm?
+
microsoft/apm is maintained by microsoft. The last recorded GitHub activity is from today, with 81 open issues.
Are there alternatives to apm?
+
Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.
Deploy apm to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/microsoft-apm)<a href="https://claudewave.com/repo/microsoft-apm"><img src="https://claudewave.com/api/badge/microsoft-apm" alt="Featured on ClaudeWave: microsoft/apm" width="320" height="64" /></a>More Subagents
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The agent that grows with you
Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Production-ready platform for agentic workflow development.
The agent engineering platform.
🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.