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 agents/microsoft/apm/apm-expertgit 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 | $0.00039 | $0.00395 |
| Opus 5 | $0.00019 | $0.00198 |
| Sonnet 5 | $0.00008 | $0.00079 |
| Haiku 4.5 | $0.00004 | $0.00040 |
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.
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.
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 · 50 lines · 39 tokens per session scan A e710ff88b7e4
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.
Other agents, from other repositories
prompt-pipeline-runner
Executes the six-stage prompt-writer pipeline and produces two mandatory output artifacts (ready-to-run prompt, confidence report).
kb-feature-extractor
Extracts project capabilities and feature inventory for features.md from pre-filtered anchor-class files.
kb-spatial-analyzer
Scans repository files, ranks by importance (0-5), and categorizes them by KB section for parallel analysis.
project-documenter
Generates a digestible 3-tier/9-section birds-eye-view document from KB + codebase, with per-claim provenance in hidden HTML comments.
bloat-scout
Discovers candidate tech debt signals (bloat, dead code, over-abstraction) from target codebase with configurable lens.
kb-concept-extractor
Extracts domain concepts and terminology for conceptmap.md from pre-filtered files.