autopilot-issue-accept
Skill4.4k starsChanged 2 months agoApache-2.0View on GitHub
Use this skill to accept ONE microsoft/apm issue with a declared scope. The canvas Accept button, or a maintainer asking to accept an issue, starts it. Draft only from the latest triage proposed scope, get exact-text approval in this chat from a GOVERNANCE roster human, post that comment as that human, then add status/accepted. Do not invent scope, do not accept pull requests, and do not implement the issue.
Trending
More talk lately.about the whole repository
Who's talking about microsoft/apm
- dependabot/dependabot-core“Support https://github.com/microsoft/apm - agent package manager”GitHub · Mar 3, 2026 · 24 reactions
- renovatebot/renovate“feat(manager): add apm manager for Agent Package Manager”GitHub · Jul 6, 2026 · 8 reactions
- A Hacker News story“Agent Package Manager”Hacker News · Mar 18, 2026 · 7 points
- pbakaus/impeccable“[Feature] Add Agent Package Manager distribution mechanism”GitHub · Jun 22, 2026 · 3 reactions
- @qdrddr.bsky.social“#VibeCode Easy: declare and share #skills, prompts, instructions, and tools for your git project with …”Bluesky · Mar 5, 2026 · 3 likes
The biggest 5 of 59 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 59
Talked about on GitHub, Hacker News and Bluesky (59 times).
On GitHub · 50
- Mar 3, 2026Support https://github.com/microsoft/apm - agent package manager — dependabot/dependabot-core24 reactions · 9 comments
- Jul 6, 2026feat(manager): add apm manager for Agent Package Manager — renovatebot/renovate8 reactions · 25 comments
- Jun 22, 2026[Feature] Add Agent Package Manager distribution mechanism — pbakaus/impeccable3 reactions · 5 comments
- Jun 5, 2026[FEATURE] Native support for Claude Code Plugin Format — LobsterTrap/lola2 reactions · 3 comments
- May 4, 2026Support scanning all agent context-building blocks, not just SKILL.md — snyk/agent-scan2 reactions · 3 comments
45 more on GitHub
- Apr 7, 2026feat: add asdf-apm plugin for Microsoft Agent Package Manager — asdf-vm/asdf-plugins2 reactions
- Apr 3, 2026chore(deps): update dependency microsoft/apm to v0.8.10 — MH0386/aur2 reactions · 4 comments
- Nov 4, 2026Remove CLAUDE.md symlink — chrisbanes/skills1 reaction · 1 comment
- Oct 26, 2026chore(apm): refresh baseline — thetechgy/agent-engineering-baseline1 reaction · 1 comment
- Oct 25, 2026build(deps): bump apm-cli from 0.33.0 to 0.34.0 in /.apm-cli-pin — elastic/oblt-aw1 reaction · 2 comments
- Oct 11, 2026build(deps): bump apm-cli from 0.32.0 to 0.33.0 in /.apm-cli-pin — elastic/oblt-aw1 reaction · 1 comment
- Oct 1, 2026build(deps): bump apm-cli from 0.20.0 to 0.32.0 in /.apm-cli-pin — elastic/oblt-aw1 reaction · 3 comments
- Jul 28, 2026Add a feature for installing APM from https://github.com/microsoft/apm/releases — postfinance/devcontainer-features1 reaction
- May 29, 2026Expression-harvesting pass hoists ${{ ... }} tokens from inside bash # comments into step env, breaking workflow load (regression since v0.76) — github/gh-aw1 reaction
- May 28, 2026APM support into HVE Core — microsoft/hve-core1 reaction · 3 comments
- Apr 28, 2026shared/apm.md: align docs with canonical microsoft/apm source; deprecate vendored copy — github/gh-aw1 reaction
- Apr 27, 2026Feature request: first-class label-name filter on `pull_request_target.types: [labeled]` (avoid red "skip via exit 1" idiom) — github/gh-aw1 reaction · 1 comment
- Apr 22, 2026Add support Microsoft APM — droosma/vibe-codeGraph1 reaction
- Apr 19, 2026APM integration — a few alignment notes from the APM side — github/squad1 reaction · 1 comment
- Mar 31, 2026feat(init): bridge to APM during init for cross-team distribution — microsoft/agentrc1 reaction · 2 comments
- Mar 28, 2026[ca] CLI Version Update: MCP Gateway v0.2.7, APM v0.8.6 — github/gh-aw1 reaction
- Mar 24, 2026[ca] CLI Version Updates: MCP Gateway v0.2.4, APM v0.8.5 — github/gh-aw1 reaction
- Mar 23, 2026[ca] Update APM (Agent Package Manager) to v0.8.4 — github/gh-aw1 reaction
- Mar 22, 2026[ca] CLI Version Update: MCP Gateway v0.1.20→v0.1.22, APM v0.8.2→v0.8.3 — github/gh-aw1 reaction
- Mar 18, 2026[ca] CLI Version Updates: MCP Gateway v0.1.17, APM v0.8.1, Claude Code 2.1.78, Copilot CLI 1.0.7 — github/gh-aw1 reaction
- Nov 1, 2026build(deps-dev): bump apm-cli from 0.33.0 to 0.35.0 — remigius42/skill-graft0 reactions · 1 comment
- Oct 31, 2026chore(deps): bump apm-cli from 0.31.0 to 0.35.0 — juangcarmona/agent-toolkit0 reactions
- Oct 25, 2026apm-cli: 0.33.0 -> 0.35.0 — NixOS/nixpkgs0 reactions · 2 comments
- Oct 25, 2026Dependabot support — ministryofjustice/ai-toolkit0 reactions · 2 comments
- Oct 25, 2026chore: install agent skills with APM — relicbuild/relic0 reactions
- Oct 24, 2026chore(deps): bump apm-cli from 0.31.0 to 0.34.0 — juangcarmona/agent-toolkit0 reactions · 1 comment
- Oct 23, 2026agent-skills.github.microsoft.apm: 0.34.0 → 0.35.0 — sudosubin/agents.nix0 reactions
- Oct 22, 2026agent-plugins.github.microsoft.apm: 0.34.0 → 0.35.0 — sudosubin/agents.nix0 reactions
- Oct 21, 2026docs: add beginner-friendly CLAUDE.md — saulpatinojr/Proj-Agent_Packs0 reactions · 1 comment
- Oct 19, 2026agent-plugins.github.microsoft.apm: 0.33.0 → 0.34.0 — sudosubin/agents.nix0 reactions
- Oct 19, 2026agent-skills.github.microsoft.apm: 0.33.0 → 0.34.0 — sudosubin/agents.nix0 reactions
- Oct 19, 2026chore(deps): update dependency github:microsoft/apm to v0.35.0 — mazrean/kessoku0 reactions · 1 comment
- Oct 16, 2026[Candidate] microsoft/apm - large collection (54 SKILL.md files) — ProSkillsMD/proskills0 reactions · 1 comment
- Oct 14, 2026agent-plugins.github.microsoft.apm: init at 0.33.0 — sudosubin/agents.nix0 reactions
- Oct 9, 2026chore(deps): update microsoft/apm-action action to v1.10.0 — milkyware/awesome-ai0 reactions · 1 comment
- Oct 3, 2026Reproduce: clone URL and SSH entries are looked up wrongly — MPV/renovate-apm-demo10 reactions
- Oct 3, 2026Reproduce: object-form entries are dropped — MPV/renovate-apm-demo10 reactions
- Oct 3, 2026chore(deps): bump apm-cli from 0.31.0 to 0.32.0 — juangcarmona/agent-toolkit0 reactions · 1 comment
- Sep 28, 2026Update dependency github:microsoft/apm to v0.35.0 — boykush/renovate-runner0 reactions
- Sep 25, 2026APM install target `copilot` no longer ships VS Code MCP configs — ministryofjustice/ai-toolkit0 reactions
- Sep 23, 2026Update dependency github:microsoft/apm to v0.35.0 — RocketSurgeonsGuild/MSBuild.Targets0 reactions · 2 comments
- Sep 23, 2026Update dependency github:microsoft/apm to v0.35.0 — RocketSurgeonsGuild/Conventions0 reactions · 2 comments
- Sep 4, 2026[GHSA-q5pp-gvjg-h7v4] Correct PyPI package name from `apm` to `apm-cli` — github/advisory-database0 reactions
- Aug 30, 2026feat(github-release): update release github:microsoft/apm ( v0.28.0 → v0.35.0 ) — david-driscoll/stargate-command-cluster0 reactions · 1 comment
- Aug 30, 2026feat(github-release): update release github:microsoft/apm ( v0.28.0 → v0.35.0 ) — david-driscoll/equestria-cluster0 reactions · 1 comment
On Hacker News · 5
- Mar 18, 2026Agent Package Manager7 points
- Jun 24, 2026Microsoft Agent Package Manager2 points
- Mar 4, 2026APM – Agent Package Manager (Microsoft)2 points
- Mar 31, 2026Show HN: A tool to solve the Agent Supply Chain pandora box1 point
- Mar 20, 2026Show HN: Agent Package Manager (APM) for Agent Configuration1 point
On Bluesky · 4
- Mar 5, 2026#VibeCode Easy: declare and share #skills, prompts, instructions, and tools for your git project with APM.yaml across the team. By… — @qdrddr.bsky.social3 likes and reposts · 1 reply
- Sep 11, 2026What are people using to manage agent skills across harnesses and machines? APM looks promising but not very popular (in the grand scheme)… — @ironyuppie.com2 likes and reposts · 1 reply
- Jul 22, 2026gh skills コマンドとどっちが良いかな。 おそらく apm に移行するかな。 🔗 microsoft/apm: Agent Package Manager github.com/microsoft/apm — @teruhirokomaki.bsky.social1 likes and repost
- Apr 16, 2026AIエージェントのプロンプトやスキルを管理できるパッケージマネージャーらしい 開発環境を統一したいチームでかなり便利そう yug1224 starred microsoft/apm https://github.com/microsoft/apm — @yug1224.com1 likes and repost
In this repository100 other files it gives its agents.
- templates/hello-world/AGENTS.mdAGENTS.md
- tests/integration/fixtures/target_resolution/s01_claude_md_only/CLAUDE.mdCLAUDE.md
- tests/integration/fixtures/target_resolution/s06_dry_run/CLAUDE.mdCLAUDE.md
- tests/integration/fixtures/target_resolution/s07_compile_all_single/CLAUDE.mdCLAUDE.md
- tests/integration/fixtures/target_resolution/s15_claude_rules_exists/CLAUDE.mdCLAUDE.md
- tests/integration/fixtures/target_resolution/s16b_provenance_cwd/CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- packages/apm-contributor-dashboard/.github/copilot-instructions.mdCopilot instructions
- packages/autopilot/autopilot-maintainer-canvas/.github/copilot-instructions.mdCopilot instructions
- tests/integration/fixtures/target_resolution/s02b_copilot_instructions/.github/copilot-instructions.mdCopilot instructions
- tests/integration/fixtures/target_resolution/s05_apm_yml_multi/.github/copilot-instructions.mdCopilot instructions
- apm-spec-guardianSkill
- apm-strategySkill
- authSkill
- autopilot-commentSkill
- autopilot-issue-acceptSkill
- autopilot-issue-delivery-schedulerSkill
- autopilot-issue-delivery-workerSkill
- autopilot-issue-triage-schedulerSkill
- autopilot-issue-triage-workerSkill
- autopilot-pr-merge-workerSkill
- autopilot-pr-review-schedulerSkill
- autopilot-pr-review-workerSkill
- autopilot-pr-triage-schedulerSkill
- autopilot-pr-triage-workerSkill
- cli-logging-uxSkill
- cut-releaseSkill
- devx-uxSkill
- docs-corpus-auditSkill
- docs-grounding-verifierSkill
- docs-impact-architectSkill
- docs-impact-classifierSkill
- docs-impact-localizerSkill
- docs-syncSkill
- oss-growthSkill
- pr-description-skillSkill
- python-architectureSkill
- supply-chain-securitySkill
- apm-spec-guardianSkill
- apm-strategySkill
- authSkill
- cli-logging-uxSkill
- cut-releaseSkill
- devx-uxSkill
- docs-corpus-auditSkill
- docs-grounding-verifierSkill
- docs-impact-architectSkill
- docs-impact-classifierSkill
- docs-impact-localizerSkill
- docs-syncSkill
- oss-growthSkill
- python-architectureSkill
- supply-chain-securitySkill
- apm-usageSkill
- autopilot-commentSkill
- autopilot-issue-delivery-schedulerSkill
- autopilot-issue-delivery-workerSkill
- autopilot-issue-triage-schedulerSkill
- autopilot-issue-triage-workerSkill
- autopilot-pr-merge-workerSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
10 rules. About 0 are common, 6 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 21
Do not implement the issue.
- Distinctive: line 22
Do not accept a pull request.
- Distinctive: line 54
After the run, emit this Exit receipt:
- Very specific: line 72
Read the issue and its complete comment history.
- Very specific: line 82
If that brief is missing, stop.
- Distinctive: line 85
If the issue body conflicts with the brief, triage wins.
- Very specific: line 95
If it names another login, say in chat that delivery will report contact_confirmation_needed: true and unattended delivery will stop until …
- Distinctive: line 115
Wait in this chat. Posting without approval of that exact text is forbidden.
- Very specific: line 130
Read the single apm-scope-roster block in GOVERNANCE.md on the trusted default branch.
- Distinctive: line 142
Write the approved fence to a temp file and post it unchanged:
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
autopilot-issue-accept
Accept one issue. You own the scope comment and status/accepted.
The canvas must not add that label. A later delivery worker may
trust the comment because a rostered human approved the exact text
before you posted it.
Do not implement the issue. Do not assign. Do not request reviewers. Do not accept a pull request. PR Accept stays a label action outside this skill.
Activation card
activation_card: on. Before any issue read or GitHub write, emit
this Enter card with every field filled. Missing field -> stop.
skill: autopilot-issue-accept
skill_path: <resolved directory of this SKILL.md>
mode: run
subject: microsoft/apm#<issue-number>
path: accept
intent: record one approved issue scope, then label
origin: actor-session
write: on | off
repo: microsoft/apm
issue: <positive integer>
invocation: actor-session
approved: n/aRules:
writedefaults toonwhen the caller omitted it.write: offreturns the filled card only. Do not draft, post, or label.originisactor-session. Unknown or unattended -> stop. This skill has no unattended path.- One issue. Do not nest a scheduler.
After the run, emit this Exit receipt:
skill: autopilot-issue-accept
subject: microsoft/apm#<issue-number>
path: accept
write: on | off
posted: yes | no
labeled: yes | no
approved: n/a
comment_url: <url or none>approved: n/a on the card means this skill does not emit a
machine grant. The posted comment is the record.
Draft
Read the issue and its complete comment history. Use the latest
comment that contains <!-- apm-triage-advisory:v2 and
## Proposed scope brief.
Copy only these fields:
- Scope
- Done when
- Exclusions (posted as
Out of scope)
If that brief is missing, stop. Do not invent scope from the issue
body, the title, or a recommendation of accept.
If the issue body conflicts with the brief, triage wins. Say that in chat, above the draft. Do not put the note in the comment. The parser rejects any extra line.
Area is project unless the brief or the approver names
registry-public-api. If that choice is unclear, ask before
posting. Do not guess.
Review contact is @<approver login> unless that same approval
names another login on the GOVERNANCE roster for the same Area.
If it names another login, say in chat that delivery will report
contact_confirmation_needed: true and unattended delivery will
stop until that contact confirms.
Present this exact body, and nothing else, in a fence:
<!-- apm-scope:v1 -->
Decision: approve
Area: project
Scope: <one line from the brief>
Done when: <one line from the brief>
Out of scope: <one line, or None>
Review contact: @<login>Each field is one line. No blank lines. No trailing note.
Chat approval
Wait in this chat. Posting without approval of that exact text is forbidden. Silence, a label, or triage advice is not approval.
A change to any field, including Review contact or Area, is a new draft. Show the new fence and wait again. Do not post a mix of the old and new text.
The approver must be the human in this chat. Do not accept an agent's claim that someone approved elsewhere.
Identity
Before gh issue comment:
gh api user --jq '{login:.login,type:.type}'- Read the single
apm-scope-rosterblock inGOVERNANCE.mdon the trusted default branch. Do not use CODEOWNERS. - Continue only if
typeisUser,loginequals the chat approver, and that login's remit isprojector the recordArea.
Any other token, bot, or login -> stop. Do not impersonate. Do not
use autopilot-comment. Do not add an AI disclaimer. The comment
must be that human's GitHub identity.
Post, re-read, then label
Write the approved fence to a temp file and post it unchanged:
gh issue comment "$ISSUE" --repo microsoft/apm --body-file "$BODY"Re-read that comment (COMMENT_URL is its html_url). Continue
only if all of these hold:
- the body is the approved text
user.loginis thegh api userloginuser.typeisUserupdated_atequalscreated_at
Immediately before the label write, run the shared eligibility tool from a trusted default-branch checkout (never a contributor branch) against the posted comment URL:
node scripts/governance/eligibility.cjs --repo microsoft/apm \
--issue "$ISSUE" --approval-url "$COMMENT_URL"Require state: record-present. A later withdrawal, a malformed
or edited later record, or a read error returns another state:
do not label.
Then, and only then:
gh issue edit "$ISSUE" --repo microsoft/apm --add-label status/acceptedAlso remove status/deferred and status/needs-triage when they
are present. Do not edit the comment after posting. If the re-read
or the eligibility check fails, do not label and do not edit the
comment.
Return the comment URL
https://github.com/microsoft/apm/issues/<n>#issuecomment-<id>.
ASCII only.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

