APM is a package manager for AI-agent configuration, using a manifest to declare reusable instructions, skills, prompts, agents, hooks, plugins, and MCP components. Development teams use it to reproduce agent setups across projects and control their dependencies through policies and lockfiles, while the catalogue contains many of these agent components.
Borrowing it
Nothing to install: this file belongs to microsoft/apm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/microsoft/apm/main/.agents/skills/autopilot-pr-review-worker/SKILL.mdgit clone --depth 1 https://github.com/microsoft/apmWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/microsoft/apm/autopilot-pr-review-worker)<a href="https://agentmods.dev/skills/microsoft/apm/autopilot-pr-review-worker"><img src="https://agentmods.dev/badge/skills/microsoft/apm/autopilot-pr-review-worker/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/microsoft/apm/autopilot-pr-review-worker"><img src="https://agentmods.dev/badge/skills/microsoft/apm/autopilot-pr-review-worker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00116 | $0.08858 |
| Opus 5.5 | $0.00046 | $0.03543 |
| Sonnet 5.5 | $0.00023 | $0.01772 |
| Haiku 4.5 | $0.00012 | $0.00886 |
Grade A, and why
autopilot-pr-review-worker scanned grade A with 1 finding 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 1mo 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
`subprocess.run` calls on a path that executes per-package or How it starts
The opening of the file, as written. The whole thing — 741 lines — stays where its author put it; the contents beside it link to each section on GitHub.
autopilot-pr-review-worker - Fan-Out Advisory Review
The panel is FAN-OUT + SYNTHESIZER. Each persona runs in its own agent
thread (via the task tool) and returns JSON matching
assets/panelist-return-schema.json. The orchestrator schema-validates
each return, hands all returns to the apm-ceo synthesizer (also a task
thread, returns JSON matching assets/ceo-return-schema.json), then
renders ONE recommendation comment from assets/recommendation-template.md.
This skill is ADVISORY by design. It does not compute a binary verdict, it does not apply verdict labels, and it does not gate merge. The panel surfaces findings; the maintainer and the PR author decide ship.
Activation card
activation_card: on. Before any PR read or GitHub write, emit
this Enter card with every field filled. Missing field -> stop.
skill: autopilot-pr-review-worker
skill_path: <resolved directory of this SKILL.md>
mode: run
subject: microsoft/apm#<pr-number>
path: review
intent: advise one already-selected PR
origin: unattended | actor-session
write: on | off
debug: off | on
repo: microsoft/apm
pr: <positive integer>
invocation: agentic-workflow | actor-session
invocation_mode: session-review | direct-user-review | composed-implementation-review
panel-mode: full | lean | delta
Rules:
writedefaults toonwhen the caller omitted it.write: offreturns the filled template only. Do not comment, add labels, remove labels, or request reviewers.write: onposts the one advisory comment viaautopilot-comment(source_skill: autopilot-pr-review-worker) and may clearpanel-review. Never assign. Actor-session may request@meas a supplemental reviewer. Do not callgh pr commentorsafe-outputs.add-commentyourself.panel-modedefaults toleanwhen omitted or unknown. Omittedpanel-modeis not a missing-field stop. Caller (merge-worker, scheduler, or human) SHOULD set it. Unknown fails cheap (lean), not heavy (full).debugdefaults tooffwhen omitted or unknown. Omitteddebugis not a missing-field stop. Pass it through toautopilot-comment.debug: onprefixes[i] Skill debug is on.The filled recommendation template ispublic_body(anddebug_bodywhen debug is on).originfail-closed unknown ->unattended.- Unattended never assigns and never requests reviewers.
- One PR. Do not nest a scheduler path.
What ships with it
14 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.
- apm.yml 532 B
- assets/ceo-return-schema.json 4.2 KB
- assets/panel-mode.md 4.5 KB
- assets/panelist-return-schema.json 10 KB
- assets/recommendation-template.md 5.3 KB
- assets/shared-brief.example.json 1.2 KB
- evals/fixtures/01-ship-now-pr1084-shape.json 9.3 KB
- evals/fixtures/01-ship-now-pr1084-shape.rendered.md 7.4 KB
- evals/fixtures/02-needs-rework-shape.json 13 KB
- evals/fixtures/02-needs-rework-shape.rendered.md 10 KB
- evals/fixtures/03-panel-mode-walkthrough.md 2.2 KB
- evals/README.md 2.3 KB
- evals/render_eval.py 9.1 KB runs code
- evals/trigger-evals.json 1.2 KB
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.
- 1mo ago Changed · +32 lines · -64 tokens per session 9f648dd0bc89
- 1mo ago First seen · 709 lines · 180 tokens per session scan A 32e775787e60
autopilot-pr-review-worker is a skill published in the GitHub repository microsoft/apm (4,133 stars, last pushed yesterday), licensed MIT. It adds 116 tokens to every session and 8,858 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-17.
Other skills, from other repositories
pr-review
Intent-aware map-reduce PR review with CI/CD support, confidence gating, and intelligent comment deduplication.
pr-walkthrough
Generate an evidence-grounded markdown walkthrough for a pull request.
address-pr-feedback
Unified PR feedback workflow - collect, triage, and fix review comments in a single command.
code-review
Review pull requests for repository fit, meaningful value, trustworthy provenance, differentiation, and maintainability in awesome-copilot.
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…
code-review-csharp
Perform structured code reviews of C# source code covering naming conventions, performance, security, readability, and .NET best practices. Trigger phrases include "review this C# code", "check my C# for best practices", "analyze this C# class", "find issues in my C# code".