An orchestrated workflow that takes a GitHub issue through planning, implementation, review, testing, deployment, end-to-end checks, and log review until a pull request is merged. A GitHub issue is a tracked piece of work, and a pull request is a proposed code change for review.

Use it with an issue number or URL to run the defined pipeline, pausing only when human approval is required.

It coordinates the full issue-to-merge process, saves its state to files, and can resume after a crash or interruption without losing progress.

ship-issue — Skill for Claude Code by mhylle

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 mhylle/claude-skills-collection --skill ship-issue

Clone the repo

git clone --depth 1 https://github.com/mhylle/claude-skills-collection

Made for: Claude Code.

Or install devflow, the plugin that ships this one along with the rest of its 38 skills, 13 agents, 5 hooks.

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/mhylle/claude-skills-collection/ship-issue/github.svg)](https://agentmods.dev/skills/mhylle/claude-skills-collection/ship-issue)

Your own site

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

Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 6,355 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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	$0.00088	$0.06355
Opus 5	$0.00044	$0.03178
Sonnet 5	$0.00018	$0.01271
Haiku 4.5	$0.00009	$0.00636

Measured 11d ago against content hash d0f02137c623, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ship-issue 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 11d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/cloud_review.py, scripts/dashboard.py, scripts/merge_brief.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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-issue/SKILL.md · 318 lines

How it starts

The opening of the file, as written. The whole thing — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/ship-issue — Issue-to-Merge Pipeline Orchestrator

You are the ship-issue orchestrator, running in the Fable 5 main session. Your goal: take one GitHub issue from reference to merged PR through the nine pipeline stages — preflight, plan, implement, review, ci, cloud_review, deploy, e2e, logs — pausing only at the two human gates. You are the single writer of run state (ADR-0009): every state mutation goes through python3 skills/ship-issue/scripts/run_state.py; everything else (dashboard, readers) only reads state.json and events.jsonl.

Binding contracts — conform to these, do not reinvent them:

references/stage-contracts.md — the nine stage contracts and both gates; gates are not stages
references/run-state-schema.md — state.json, events.jsonl, pause semantics, time summary
references/config-schema.md — the target-repo config preflight validates
references/model-tiering.md — pinned model tiers; fresh task on the same pinned tier
references/prompt-rules.md — per-tier prompt style for every task you dispatch

Arguments

Accept an issue number (142) or a full GitHub issue URL (https://github.com/<owner>/<repo>/issues/142). Ingest the issue with:

gh issue view <n> --json number,title,url,body

The issue's number, title, url, and body are the run's founding inputs.

Resume on re-invocation — check FIRST

Before starting anything new, scan .ship-issue/runs/*/state.json in the target repo for an existing run of this issue whose events.jsonl contains no run_completed and no run_aborted event. If one exists, this invocation is a resume, not a new run:

python3 skills/ship-issue/scripts/run_state.py resume-check --run-dir <run-dir>

Continue at the printed resume point:

RESUME_AT: gate:gate_1 — re-present Gate 1 with the persisted plan and wait for the decision. The elapsed wait is gate wait, already covered by the open gate-wait window.
RESUME_AT: stage:<s> — re-enter stage <s>. If a work window was open at the crash, resume-check has already recorded the dead window as a crash_gap_recorded event and opened a fresh work window.

Read the full file on GitHub · 318 lines

Files

What ships with it

11 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.

11d ago First seen · 318 lines · 88 tokens per session scan A d0f02137c623

Subscribe to this mod's changes

ship-issue is a skill published in the GitHub repository mhylle/claude-skills-collection (18 stars, last pushed 8d ago), licensed MIT. It adds 88 tokens to every session and 6,355 once invoked, about $0.0004 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.

Git and workflow Project management

mcore-split-pr

Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.

NVIDIA/skills · 25 tokens

shiplog

Recap of everything shipped since the last run - cross-repo PRs, security fixes, star deltas, and X traction, synthesized into a digest article and a ready-to-post shiplog in your voice.

aeonfun/aeon · 46 tokens

llxprt-issue-workflow

Use this skill when asked to address, fix, or work on a GitHub issue in the llxprt-code repository. Covers the complete issue lifecycle - branch setup, gh CLI usage, test-first planning, subagent delegation and review loops, the full verification cycle (including the stepfun-37 smoke test), open code review (ocr), PR…

vybestack/llxprt-code · 87 tokens

ship-issue