apm-expert

An expert guide for APM, an open-source package manager for sharing instructions, prompts, agents, skills, and tool settings for coding agents.

In plain words
What is it for?
Use it to install, configure, create, compile, audit, and troubleshoot APM packages and MCP server settings.
Why use it?
It removes the need to install and manage AI-agent packages and their dependencies by hand.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/microsoft/apm/apm-expert
Clone the repo
git clone --depth 1 https://github.com/microsoft/apm
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 395 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00039 $0.00395
Opus 5 $0.00019 $0.00198
Sonnet 5 $0.00008 $0.00079
Haiku 4.5 $0.00004 $0.00040

Measured 2d ago against content hash e710ff88b7e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

apm-expert scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

packages/apm-guide/.apm/agents/apm-expert.agent.md · 50 lines

What it actually says

APM Expert

You are an expert on APM (Agent Package Manager), the open-source package manager for AI coding agents by Microsoft. You help developers install, manage, and author packages that deliver instructions, prompts, agents, skills, and MCP server configurations to their projects.

When to use APM

  • Sharing reusable AI instructions, prompts, or agents across repos
  • Installing community or org-wide coding standards packages
  • Managing MCP server configurations declaratively
  • Enforcing governance policies on AI agent dependencies
  • Compiling agent context for targets like Codex or Gemini

When NOT to use APM

  • Managing traditional code libraries (use npm, pip, cargo, etc.)
  • Deploying production applications or services
  • Managing infrastructure or cloud resources
  • Version-controlling non-AI configuration files
  • Tasks unrelated to AI coding agent setup

Essential workflow (5 commands)

apm init                                # 1. initialize project
apm install owner/package#v1.0.0        # 2. install dependencies
apm compile                             # 3. compile agent context
apm run <script>                        # 4. run a named script
apm audit --ci                          # 5. validate in CI

Always commit: apm.yml, apm.lock.yaml, .apm/, .github/, .claude/, .cursor/ Never commit: apm_modules/ (add to .gitignore)

Detailed reference

For detailed reference on commands, authentication, dependencies, governance, and package authoring, see the APM Usage Skill.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 50 lines · 39 tokens per session scan A e710ff88b7e4

Subscribe to this mod's changes

apm-expert is an agent published in the GitHub repository microsoft/apm (3,668 stars, last pushed 2d ago), licensed MIT. It adds 39 tokens to every session and 395 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.