ship-pr

A five-stage workflow for turning a GitHub issue into a pull request, including understanding the request, designing the change, coding, reviewing, and checking it before merge.

In plain words
What is it for?
Use it when implementing an agentdeck issue as deck-dev. It guides the pull request description, implementation, self-review, checks, and readiness for merging.
Why use it?
It prevents code from being written before the requested change is understood and designed. It also prompts the developer to check paths that tests may not cover.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/agentdecksdk/agentdeck/ship-pr
Any agent
npx skills add agentdecksdk/agentdeck --skill ship-pr
Clone the repo
git clone --depth 1 https://github.com/agentdecksdk/agentdeck

Made for: Claude Code, Codex.

Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,668 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00072 $0.01668
Opus 5 $0.00036 $0.00834
Sonnet 5 $0.00014 $0.00334
Haiku 4.5 $0.00007 $0.00167

Measured 2d ago against content hash ef2bb978d60d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ship-pr 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 2d 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.

.claude/skills/ship-pr/SKILL.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ship a PR

Design the diff before writing it. The design binds nothing by itself, so Stage 1 stops and waits for the orchestrator to check it against the brief before Stage 2 touches source. Self-review is a checklist, not reflection: an unanswered question fails the stage, same as an unrun command.

Checklist

Copy this into your own response and check off each stage as you complete it:

Ship progress:
- [ ] 0. Understand: spec gate, engineering docs, seed the worktree
- [ ] 1. Design: PR body sections, then stop and wait for the design gate
- [ ] 2. Implement: match the analog, stay in budget (references/implement.md)
- [ ] 3. Self-review: ten shape questions plus the coverage question (references/self-review.md)
- [ ] 4. Gate: make check green, gh pr ready

Freedom per stage

Thinking is high freedom. Verification and output are low: a checklist or a template you improvise is not one.

stage freedom why
0 Understand LOW on the spec gate, HIGH on reading the gate is binary: Done when and scope bounds present, or stop and comment
1 Design LOW on format, HIGH on content CI parses the budget block; what argument goes in it is judgment
2 Implement HIGH open field. Over-specifying here does real damage, and the issue this skill ships from puts it out of scope
3 Self-review LOW a checklist you can improvise is not a checklist
4 Gate LOW exact commands, fragile sequence

Register

Every instruction below, and in references/, carries exactly one of these:

register wording carries
CONSTRAINT MUST / NEVER what breaks if violated, named alongside it
EXPECTATION "the reviewer checks X" which finding class the miss earns
JUDGMENT "default is X, deviate when Y" nothing; your call

A CONSTRAINT without a stated consequence is a preference, not a CONSTRAINT: rewrite it or demote it.

Stages

stage freedom / register does writes
0. Understand LOW / CONSTRAINT on the gate Read the issue as spec. Spec gate below. Seed the worktree. nothing, or a gate comment
1. Design LOW / CONSTRAINT on format PR body sections, then stop. references/design.md draft PR, then wait
2. Implement HIGH / JUDGMENT Match the analog, stay in budget, test what the change exposes. references/implement.md source, tests, CHANGELOG
3. Self-review LOW / CONSTRAINT Ten shape questions plus the coverage question, answered in writing. references/self-review.md the answers, visible in your response
4. Gate LOW / CONSTRAINT make check green, compact the body, gh pr ready. Below. ready PR

Read the full file on GitHub · 137 lines

Files

What ships with it

3 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.

  1. 2d ago First seen · 137 lines · 0 tokens per session scan A ef2bb978d60d

Subscribe to this mod's changes

ship-pr is a skill published in the GitHub repository agentdecksdk/agentdeck (2 stars, last pushed 3d ago), licensed MIT. It adds 72 tokens to every session and 1,668 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 2026-08-31.