What is autopilot-issue-delivery-worker?

An implementation worker for one already-selected microsoft/apm GitHub issue. It can work within an accepted scope when permitted, rather than choosing issues or managing the queue.

Use it to reproduce and implement an accepted issue, or to produce the required no-write plan when writing is disabled.

It separates authorized implementation from triage and ensures the worker handles only one issue with the required governance checks.

How microsoft/apm configures Claude Code and Codex

About the project

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.

microsoft/apm · 4,133 stars · on GitHub · microsoft.github.io

Reuse

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.

Copy the file

curl -O https://raw.githubusercontent.com/microsoft/apm/main/.agents/skills/autopilot-issue-delivery-worker/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/microsoft/apm

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/microsoft/apm/autopilot-issue-delivery-worker/github.svg)](https://agentmods.dev/skills/microsoft/apm/autopilot-issue-delivery-worker)

Your own site

<a href="https://agentmods.dev/skills/microsoft/apm/autopilot-issue-delivery-worker"><img src="https://agentmods.dev/badge/skills/microsoft/apm/autopilot-issue-delivery-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/microsoft/apm/autopilot-issue-delivery-worker"><img src="https://agentmods.dev/badge/skills/microsoft/apm/autopilot-issue-delivery-worker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 114 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,794 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00114	$0.01794
Opus 5.5	$0.00046	$0.00718
Sonnet 5.5	$0.00023	$0.00359
Haiku 4.5	$0.00011	$0.00179

Measured 1mo ago against content hash 75609428a685, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

autopilot-issue-delivery-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.

.agents/skills/autopilot-issue-delivery-worker/SKILL.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

autopilot-issue-delivery-worker

Per-issue implementation worker. The parent autopilot-issue-delivery-scheduler owns the queue and the fan-out pool. You own exactly one ISSUE_NUMBER.

Do not pick more issues. Do not fill other slots.

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-delivery-worker
skill_path: <resolved directory of this SKILL.md>
mode: run
subject: microsoft/apm#<issue-number>
path: delivery
intent: implement one already-selected issue
origin: unattended | actor-session
write: on | off
repo: microsoft/apm
issue: <positive integer>
invocation: agentic-workflow | actor-session

Rules:

write defaults to on when the caller omitted it.
write: off returns the filled template only. Do not assign, comment, label, edit, or open a PR.
write: on may assign @me (actor-session only) and implement inside the accepted scope. Unattended never assigns and never implements.
origin fail-closed unknown -> unattended.
One issue. Do not nest a scheduler path.

After the run, emit this Exit receipt:

skill: autopilot-issue-delivery-worker
subject: microsoft/apm#<issue-number>
path: delivery
write: on | off
assigned: yes | no | skipped
pushed: yes | no
approved: n/a

Inputs

ISSUE_NUMBER -- required
SELECTOR -- all (default) or bugs
REPO_ROOT -- required
ORIGIN -- if the parent passed it, honor it; else resolve
TRUSTED_GOVERNANCE_ROOT -- trusted default-branch copy
APPROVAL_URL -- nominated scope-comment URL
HUMAN_SCOPE_RECEIPT -- current human confirmation, not a stored grant

ORIGIN and assignment

Resolve ORIGIN before any GitHub write:

Caller ORIGIN / INVOCATION_MODE
GH_AW_* or GITHUB_ACTIONS -> unattended
gh api user --jq .login succeeds -> actor-session
Else unattended (fail closed)

INTENT is implement.

When ORIGIN is actor-session, assignment is a hard gate. It is the public signal of which user is working this issue. GitHub allows multiple assignees, so a read-then-add is not a claim. Before reproduce, edits, or a PR:

Read the full file on GitHub · 188 lines

Files

What ships with it

22 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.

Changes

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 First seen · 188 lines · 114 tokens per session scan A 75609428a685

Subscribe to this mod's changes

autopilot-issue-delivery-worker is a skill published in the GitHub repository microsoft/apm (4,133 stars, last pushed yesterday), licensed MIT. It adds 114 tokens to every session and 1,794 once invoked, about $0.0005 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.

Claude Code Git and workflow Project management ai-agents codex-cli context-engineering github-copilot prompt-engineering

apm: Skill for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

autopilot-issue-delivery-worker

Activation card

Inputs

ORIGIN and assignment

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

work-the-frontier

gsd-quick

gsd-complete-milestone

gsd-quick-batch

gsd-workspace

gsd-inbox