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.
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-issue-autopilotnpx skills add microsoft/apm --skill apm-issue-autopilotgit 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/apm-issue-autopilot)<a href="https://agentmods.dev/skills/microsoft/apm/apm-issue-autopilot"><img src="https://agentmods.dev/badge/skills/microsoft/apm/apm-issue-autopilot.svg" alt="Measured on agentmods" 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 | $0.00238 | $0.05202 |
| Opus 5 | $0.00119 | $0.02601 |
| Sonnet 5 | $0.00048 | $0.01040 |
| Haiku 4.5 | $0.00024 | $0.00520 |
Grade A, and why
apm-issue-autopilot 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 5d 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 — 398 lines — stays where its author put it; the contents beside it link to each section on GitHub.
apm-issue-autopilot - intake-to-merge issue orchestrator
This SKILL.md is the natural-language module derived from a genesis design packet; refactors re-run the genesis skill from that packet.
This skill is an A11 RECONCILIATION LOOP, MANUALLY INVOKED, over a queue of issues each driven to a terminal state under non-determinism. It generalizes batch-bug-shepherd from bugs-only to ANY issue type, and promotes the full apm-triage-panel rubric to the central front gate. It does NOT re-implement triage, panel review, or the per-PR convergence loop -- it COMPOSES existing skills.
What it composes (do not re-implement)
- apm-triage-panel -- the triage rubric, run per issue in DIRECT (orchestrator-return) mode.
- shepherd-driver -- the per-PR drive- to-merge convergence loop and cross-PR mergeability gate (which in turn composes apm-review-panel).
- pr-description-skill -- authors
the anchored, mermaid-validated body of the ONE issue PR opened at
Phase 4 acceptance-close (see
assets/acceptance-observer.md). The PR body is never hand-rolled.
All three are same-repo LOCAL SIBLINGS. This skill DECLARES each
dependency here AND in apm.yml, and PROBES for each at its use-site
(Phase 1 triage, Phase 4 PR-open, Phase 5 shepherd) with a tool call --
never an assertion from recall (A9 SUPERVISED EXECUTION).
Hard boundaries
- MANUAL invocation only. No event triggers, no label triggers, no
gh-aw. Labels (
status/accepted,status/shepherding) are WRITTEN for bookkeeping but are NEVER the trigger. - Triage is paramount. The autopilot ESCALATES to the maintainer by default; auto-implementation is the narrow exception, reached only for a clear, bounded, high-confidence accept the maintainer approved.
- ONE consolidated triage review for the whole batch, not drop-by- drop. Exactly one human checkpoint (Phase 2).
- Never auto-merge. Mergeability is the terminal state; the human approves the protected merge.
- Escalation NEVER auto-closes or auto-declines an issue. It surfaces the issue to the maintainer running the session and leaves it for human action (inherits batch-bug-shepherd terminal-handling).
What ships with it
27 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.
- assets/acceptance-observer.md 3.7 KB
- assets/autopilot-triage-schema.json 2.5 KB
- assets/confidence-gate-rubric.md 4.0 KB
- assets/final-report-template.md 1.6 KB
- assets/ground-truth-table.md 3.8 KB
- assets/ideate-prompt.md 3.1 KB
- assets/implement-bug.md 933 B
- assets/implement-docs.md 1.1 KB
- assets/implement-feature.md 1.1 KB
- assets/implement-refactor.md 1.4 KB
- assets/model-routing.md 16 KB
- assets/plan-panel-prompt.md 5.6 KB
- assets/plan-schema.json 6.2 KB
- assets/solution-pipeline-prompt.md 8.1 KB
- assets/task-implement-prompt.md 3.4 KB
- assets/triage-digest-template.md 1.9 KB
- assets/triage-prompt.md 2.7 KB
- assets/wave-gate-rubric.md 7.7 KB
- evals/.gitignore 9 B
- evals/content/gate-escalate-doubtful.json 2.4 KB
- evals/content/gate-proceed-clean-accept.json 2.4 KB
- evals/content/mixed-types-one-review.json 2.7 KB
- evals/evals.json 1.4 KB
- evals/README.md 2.1 KB
- evals/real-task-refinement.md 1.3 KB
- evals/triggers.json 4.0 KB
- scripts/run_evals.py 11 KB runs code
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.
- 5d ago First seen · 398 lines · 238 tokens per session scan A 9872bd7ada99
apm-issue-autopilot is a skill published in the GitHub repository microsoft/apm (3,726 stars, last pushed today), licensed MIT. It adds 238 tokens to every session and 5,202 once invoked, about $0.0012 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
review
Review a proposed change before applying it.
commit-helper
Conventional commit helper — analyze changes, detect secrets, create well-formatted commit.
commit
Create a git commit with clear, conventional commit messages. You MUST read this when the user wants to commit staged changes, write a commit message, or finalize code changes with proper conventional commit format since it describes how to follow the user's specific requirements.
commit
Creates conventional git commits enriched with a Context section that logs AI-layer changes (.wisci/, CLAUDE.md, skills, rules), turning git history into queryable long-term memory. Use to commit changes, optionally pushing afterward.
commit
Stage, commit, and push code changes with branch safety and explicit staging. Use when ready to commit work. Invoked by saying "commit", "push", or "commit and push".
commit-all
Batch-commit all uncommitted changes grouped by relevance. Use when multiple accumulated changes need committing. Invoked by saying "commit all" or "commit everything".