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-triage-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-triage-worker)<a href="https://agentmods.dev/skills/microsoft/apm/autopilot-pr-triage-worker"><img src="https://agentmods.dev/badge/skills/microsoft/apm/autopilot-pr-triage-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-triage-worker"><img src="https://agentmods.dev/badge/skills/microsoft/apm/autopilot-pr-triage-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 | $0.00078 | $0.01600 |
| Opus 5.5 | $0.00031 | $0.00640 |
| Sonnet 5.5 | $0.00016 | $0.00320 |
| Haiku 4.5 | $0.00008 | $0.00160 |
Grade A, and why
autopilot-pr-triage-worker 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
autopilot-pr-triage-worker
Advisory classification of ONE already-selected PR. Do not review
the diff as autopilot-pr-review-worker does. Do not drive merge.
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-triage-worker
skill_path: <resolved directory of this SKILL.md>
mode: run
subject: microsoft/apm#<pr-number>
path: triage
intent: advise one already-selected PR
origin: unattended | actor-session
write: on | off
json: off | on
debug: off | on
repo: microsoft/apm
pr: <positive integer>
invocation: agentic-workflow | actor-session
Rules:
writedefaults toonwhen the caller omitted it.write: offreturns the filled template only. Do not comment, add labels, or remove labels.write: onposts one GitHub comment viaautopilot-commentand processing / classification labels. Never assign. Never request reviewers. Do not callgh pr commentyourself. Do not writestatus/accepted,status/needs-design, orstatus/needs-triage. Writestatus/deferredonly when this PR is not labelledstatus/acceptedand has no same-repo linked issue labelledstatus/accepted.jsondefaults tooffwhen omitted or unknown. Omittedjsonis not a missing-field stop.json: off-> no machine JSON receipt.json: on-> fill JSON only as an internal payload (session file or parent Exit). Never post it on GitHub.debugdefaults tooffwhen omitted or unknown. Omitteddebugis not a missing-field stop.debug: off-> passpublic_bodyas the Suggested PR comment (unwrap the markdown fence) toautopilot-comment. Do not pass recommendation, linked issue, classification, or next action headings aspublic_body.debug: on-> passdebug_bodyas the filled template without a JSON fence.autopilot-commentprefixes[i] Skill debug is on.- Load
autopilot-commentbefore any GitHub comment write.source_skill: autopilot-pr-triage-worker. Missing card -> stop. originfail-closed unknown ->unattended.- One PR. Do not nest a scheduler path.
What ships with it
2 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.
- 1mo ago Changed · +24 lines 33e5daa2f1f0
- 1mo ago First seen · 139 lines · 78 tokens per session scan A 588482dfa134
autopilot-pr-triage-worker is a skill published in the GitHub repository microsoft/apm (4,133 stars, last pushed yesterday), licensed MIT. It adds 78 tokens to every session and 1,600 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-17.
Other skills, from other repositories
git-branch-cleanup
Analyzes and safely cleans up local Git branches. Categorizes branches by merge status, staleness, and remote tracking. Provides interactive selection with safety guards. Use when the user wants to clean up branches, delete old branches, organize Git branches, or asks about which branches can be safely deleted.
pr-stack
Plan and execute splitting a large PR or branch into a reviewable stacked PR sequence.
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.
publish-artifact
Publish an rp1 artifact (investigation report, design doc, audit) from .rp1/work/ as an idempotent PR or issue comment instead of committing it to the repo; re-runs update the same comment in place.