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.
npx agentmods add skills/microsoft/apm/apm-usagenpx skills add microsoft/apm --skill apm-usagegit clone --depth 1 https://github.com/microsoft/apmWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00049 | $0.00491 |
| Opus 5 | $0.00024 | $0.00246 |
| Sonnet 5 | $0.00010 | $0.00098 |
| Haiku 4.5 | $0.00005 | $0.00049 |
Grade A, and why
apm-usage 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.
What it actually says
APM Usage
APM (Agent Package Manager) is the open-source package manager for AI coding agents. It lets teams install, share, and govern reusable instructions, prompts, agents, skills, and MCP server configurations across projects.
When to activate
- User mentions
apmor "Agent Package Manager" - Questions about installing or managing AI-agent packages
- Setting up instructions, prompts, agents, skills, or chatmodes
- Configuring MCP servers through apm.yml
- Authentication for private repos (GitHub, ADO, GHES, Artifactory)
- Policy enforcement or
apm audit - Package authoring or publishing
- Compiling agent context (
apm compile) - Troubleshooting apm errors
Key rules
- Commit these files: apm.yml, apm.lock.yaml, .apm/, deployed harness directories including .grok/, and AGENTS.md
- Never commit: apm_modules/ (add to .gitignore)
- Team sync: after
git clone, runapm installto restore dependencies - Update deps:
apm install --updaterefreshes to latest refs - Pin versions: use tags (
#v1.0.0) in production, branches for development - ASCII only: all CLI output and source must stay within printable ASCII
Reference
For detailed guidance, see the following resources:
- Installation -- install and update APM
- Workflow -- core workflow, apm.yml format, what to commit
- Commands -- full CLI command reference
- Dependencies -- all dependency formats and version pinning
- Authentication -- token setup for private repos
- Governance -- policy engine and audit checks
- Package Authoring -- creating APM packages
- Troubleshooting -- common errors and fixes
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 48 lines · 49 tokens per session scan A a76e5e768e5d
apm-usage is a skill published in the GitHub repository microsoft/apm (3,687 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 491 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.
Other skills, from other repositories
create-skill-sample
This skill should be used when the user asks to "create a new skill sample", "add a skill", "scaffold a new skill", "contribute a skill", "create a GitHub Copilot skill", "build a custom skill", or needs to create a new GitHub Copilot custom skill sample with proper folder structure, SKILL.md, README, and sample.json…
create-system-prompt
This skill should be used when the user asks to "create an agent instruction", "add agent instructions", "scaffold an agent sample", "create a system prompt sample", "add a system prompt", "create a new agent", "build an agent", or needs to create a new agent instruction sample with proper folder structure, README…
copilot-studio-agent-documenter
Generate comprehensive documentation for Microsoft Copilot Studio agents from exported Dataverse solutions using the Power Platform CLI. Use when asked, to analyse the solution with the agents file and create documentation from the contents.
mcp-server-review
Review a Model Context Protocol (MCP) server implementation against the 2026-07-28 protocol revision, which removed the initialize handshake and Mcp-Session-Id and made the protocol stateless. Use when the user asks to review, audit, upgrade or migrate an MCP server, asks whether their MCP server is spec compliant…
skill-evaluator
Evaluates agent skills against Anthropic's best practices. Use when asked to review, evaluate, assess, or audit a skill for quality. Analyzes SKILL.md structure, naming conventions, description quality, content organization, and identifies anti-patterns. Produces actionable improvement recommendations.
prompt-pack
Generates a self-contained prompt pack from a spec. Embeds real code patterns from .vibeflow/ so any coding agent (Claude Code, Cursor, Copilot) follows the project's conventions without needing repo context. Use when handing off implementation to a separate session or agent.