review-flow: Skill for Claude Code

.claude/skills/ship/SKILL.md

ship is a skill for Claude Code from DGouron/review-flow. It costs 50 tokens per session (1,046 once invoked), scanned A, original, MIT.

A command that prepares and finalizes a code change by running checks, creating a conventional commit, pushing the branch, and optionally opening or merging a pull request.

In plain words
What is it for?
Use it when you want to verify, commit, and push a branch, or create and optionally merge a pull request.
Why use it?
It combines the repeated release steps and stops before committing or pushing when required checks fail.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Claude Code.

This is DGouron/review-flow's own configuration. It tells Claude Code how to work on review-flow itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything review-flow configures →

Reuse

Borrowing it

Nothing to install: this file belongs to DGouron/review-flow. 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/DGouron/review-flow/master/.claude/skills/ship/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/DGouron/review-flow

Made for: Claude Code.

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.

agentmods badge for ship

README.md
[![agentmods](https://agentmods.dev/badge/skills/dgouron/review-flow/ship.svg)](https://agentmods.dev/skills/dgouron/review-flow/ship)
Your own site
<a href="https://agentmods.dev/skills/dgouron/review-flow/ship"><img src="https://agentmods.dev/badge/skills/dgouron/review-flow/ship.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,046 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 warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Tool Misuse · line 107
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00050 $0.01046
Opus 5 $0.00025 $0.00523
Sonnet 5 $0.00010 $0.00209
Haiku 4.5 $0.00005 $0.00105

Measured 8d ago against content hash bc2e12f76781, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 8d 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/SKILL.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ship — Commit & Push

Activation

This skill activates with /ship. It chains verification, commit, push, and optionally PR creation and merge.

Optional arguments

/ship                   # Commit + push (no PR)
/ship pr                # Commit + push + gh pr create
/ship pr merge          # Commit + push + gh pr create + gh pr merge --admin --squash

Workflow

Step 0: Quality Gates (BLOCKING)

BEFORE any commit, run:

yarn verify

yarn verify runs: TypeScript check + Biome lint + Vitest tests.

If it fails: display the errors and STOP. Do not proceed until all quality gates pass.


Step 1: Analysis

git status --short
git branch --show-current
git log --oneline -5

Guards:

  • If branch = master: STOP — the protect-main-push.sh hook blocks push to master. Create a feature branch first.
  • If nothing to commit: inform and stop.

Step 2: Staging

  • If files are not staged, list them and add them by name (never git add -A or git add .)
  • NEVER include .env, credentials, secrets, or lock files unless explicitly requested
  • NEVER include files unrelated to the current change

Preferred pattern:

git add src/usecases/foo.usecase.ts src/tests/units/usecases/foo.usecase.test.ts

Step 3: Commit

Infer the message from the staged changes. Follow Conventional Commits:

<type>(<scope>): <description>
Type Usage
feat New feature
fix Bug fix
refactor Refactoring (no feature or fix)
test Tests only
docs Documentation only
chore Maintenance, dependencies
style Formatting (no logic change)
perf Performance improvement
ci CI/CD changes

Rules:

  • Header max 72 characters
  • Description in lowercase, no trailing period
  • Scope optional in parentheses, must match bounded context name when applicable

Commit via heredoc (preserves formatting):

git commit -m "$(cat <<'EOF'
feat(webhook): add GitHub signature validation

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>
EOF
)"

Read the full file on GitHub · 168 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.

  1. 8d ago First seen · 168 lines · 50 tokens per session scan A bc2e12f76781

Subscribe to this mod's changes

ship is a skill published in the GitHub repository DGouron/review-flow (42 stars, last pushed today), licensed MIT. It adds 50 tokens to every session and 1,046 once invoked, about $0.0003 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.