A workflow for taking a code branch through pull-request creation, automated checks, review comments, and merge readiness. A branch is a separate line of code changes, and a pull request is a request to add those changes to the main project.

Use it to ship a branch, create or monitor a pull request, respond to automated review comments, keep checking after fixes, and optionally squash-merge once everything is green.

It removes the need to repeatedly check CI, handle automated review threads, and track whether a pull request is ready. It also stops when a human decision or another blocker is needed.

ship — Skill for Claude Code and Codex by mikecann/agent-skills

Install

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.

Any agent

npx skills add mikecann/agent-skills --skill ship

Clone the repo

git clone --depth 1 https://github.com/mikecann/agent-skills

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/mikecann/agent-skills/ship/github.svg)](https://agentmods.dev/skills/mikecann/agent-skills/ship)

Your own site

<a href="https://agentmods.dev/skills/mikecann/agent-skills/ship"><img src="https://agentmods.dev/badge/skills/mikecann/agent-skills/ship/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/mikecann/agent-skills/ship"><img src="https://agentmods.dev/badge/skills/mikecann/agent-skills/ship.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,768 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	$0.00077	$0.01768
Opus 5.5	$0.00031	$0.00707
Sonnet 5.5	$0.00015	$0.00354
Haiku 4.5	$0.00008	$0.00177

Measured 2mo ago against content hash ae82e48fa5b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ship 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 2mo 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.

skills/ship/SKILL.md · 230 lines

How it starts

The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ship

Take the current branch from "work in progress" to "ready to merge".

This skill is for the full PR babysitting loop:

confirm you are on a real feature branch
find or create the PR
watch CI and review activity
handle automated review comments one by one
push fixes and keep re-checking
stop only when the PR is merge-ready or blocked by something a human must decide

When to Use

Use this when the user wants you to:

ship a branch
create a PR if needed
monitor CI until it settles
deal with AI review bots or automated review comments
keep a PR merge-ready in a loop
squash merge once everything is green

Do not use this for a normal one-off code review or a one-time push.

Core Rules

Work from the current local branch.
- If git branch --show-current is empty, or you are detached, stop and tell the user.
- If you are on main or the repo's default branch, stop and tell the user there is no feature branch to ship.
Use gh for GitHub work.
- Use gh pr view, gh pr create, gh pr checks, gh pr review, and gh api.
- If gh pr view is not enough for review threads, use gh api graphql.
After every push, monitor checks again.
- Do not push and walk away.
Handle automated review comments explicitly.
- Decide whether the comment is valid.
- If valid, implement a fix, push it, reply with what changed, then resolve the thread.
- If not valid, do not change code, reply with why, then resolve the thread.
Do not auto-resolve human reviewer comments unless the user explicitly asked for that.
Do not merge unless the user explicitly asked you to merge when ready.
- If they asked for squash merge, use squash merge.

Workflow

1. Establish PR state

Get the current branch.
Check whether it already has an open PR.
If there is no PR:
- make sure the branch is pushed
- create the PR
- capture the PR number and URL
Report the PR URL to the user once it exists.

If PR creation needs missing information and the repo does not make it obvious, draft a concise title/body from the branch diff and recent commits.

Read the full file on GitHub · 230 lines

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.

2mo ago First seen · 230 lines · 77 tokens per session scan A ae82e48fa5b2

Subscribe to this mod's changes

ship is a skill published in the GitHub repository mikecann/agent-skills (21 stars, last pushed 23d ago), licensed MIT. It adds 77 tokens to every session and 1,768 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 2026-08-30.

Code review Git and workflow Releases

github

GitHub via gh CLI: PRs, issues, reviews, repos, auth.

NousResearch/hermes-agent · 19 tokens

otto-drive-pr

PR mergeability, CI, and live preview.

omnigent-ai/omnigent · 14 tokens

voicestudio-maintainer

Triage GitHub issues, review contributor pull requests, diagnose CI, and prepare explicitly requested releases for VoiceStudio's Electron desktop app and Python backend. Use for repository maintenance work, not ordinary VoiceStudio audio generation.

debpalash/VoiceStudio · 50 tokens

release

Cut a brooks-lint release: set the version in package.json, propagate it across all four plugin manifests and every version-bearing text file (README badges, docs site metadata), write the CHANGELOG entry, validate, then commit, push, tag, and publish the GitHub release. Triggers when the maintainer asks to "release"…

hyhmrright/brooks-lint · 135 tokens

release-pr-review

Review pass on an open release PR (release/ → main) — the step between git-wrapup and release-and-publish when a project releases in gated release PR mode. Reads the PR's commit range through the code-simplifier lens plus a correctness review, verifies whatever an automated reviewer left on the PR, lands fixes as…

cyanheads/obsidian-mcp-server · 136 tokens

explain-pr

Explain a PR: the background problem and the proposed solution.

dyoshikawa/rulesync · 15 tokens