Borrowing it
Nothing to install: this file belongs to stevengonsalvez/agents-in-a-box. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/stevengonsalvez/agents-in-a-box/main/.claude/skills/ship-it/SKILL.mdgit clone --depth 1 https://github.com/stevengonsalvez/agents-in-a-boxWrote 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.
[](https://agentmods.dev/skills/stevengonsalvez/agents-in-a-box/ship-it)<a href="https://agentmods.dev/skills/stevengonsalvez/agents-in-a-box/ship-it"><img src="https://agentmods.dev/badge/skills/stevengonsalvez/agents-in-a-box/ship-it/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.
<a href="https://agentmods.dev/skills/stevengonsalvez/agents-in-a-box/ship-it"><img src="https://agentmods.dev/badge/skills/stevengonsalvez/agents-in-a-box/ship-it.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00096 | $0.02733 |
| Opus 5 | $0.00048 | $0.01367 |
| Sonnet 5 | $0.00019 | $0.00547 |
| Haiku 4.5 | $0.00010 | $0.00273 |
Grade A, and why
ship-it 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.
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.
How it starts
The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ship-it
Conductor skill. Runs in the main loop (interactive steps stay interactive). The only expensive part, heavy review fan-out, runs as a dynamic Workflow.
/commit ──▶ gh pr create ──▶ REVIEW (lite|heavy) ──▶ fix ALL ──▶ re-REVIEW
▲ │
└── loop ────┘ until 0
│
CI green ──▶ gh pr merge --merge
Arguments
/ship-it [lite|heavy] [pr-number]
lite(default): single-pass PR review. Cheap, fast.heavy: ce-style multi-persona fan-out + Codex cross-model peer.pr-number: skip commit/PR-create, start at the review loop on that PR.
Model routing (hard rules)
| Role | Model |
|---|---|
| Conductor, commit/PR/merge mechanics | session model |
| Review agents (both tiers) | Opus, always (Fable only if Stevie says so in chat) |
| Codex peer (heavy only) | Codex, high reasoning effort (put the literal --effort high in the peer prompt, see Step 3) |
| Applying mechanical fixes | Sonnet (fast-worker) for well-specified edits; main loop for judgment calls |
Review is the safety net: never route review to Sonnet or Haiku. lite's
single pass runs inline only when the session model is Opus-class (Opus or
Fable); on a Sonnet/Haiku session, spawn a code-reviewer agent with
model: opus instead of reviewing inline.
Step 1: Commit
Invoke the /commit skill (Skill tool). It owns cleanup, atomic staging by
named paths, signed commits, push. Do not reimplement any of it here.
If the working tree is already clean and the branch is pushed, skip ahead.
Step 2: Pull request
BRANCH=$(git branch --show-current)
git fetch origin
# Sync against the PR's OWN base, never a hardcoded main (stacked PRs exist).
# Resolution order: caller-supplied base > this branch's OPEN PR > repo default.
# `gh pr view` with no number is deliberately NOT used: it resolves a merged or
# closed PR too, handing back a stale base.
BASE="${SHIP_IT_BASE:-}"
[ -n "$BASE" ] || BASE=$(gh pr list --head "$BRANCH" --state open \
--json baseRefName --jq '.[0].baseRefName' 2>/dev/null)
[ -n "$BASE" ] || BASE=$(gh repo view --json defaultBranchRef \
--jq .defaultBranchRef.name)
git merge "origin/$BASE" # MERGE, never rebase a pushed PR branch
gh pr list --head "$BRANCH" --state open --json number,url # reuse existing PR if open
gh pr create --fill --base "$BASE" # otherwise create, onto the SAME base
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 · 232 lines · 96 tokens per session scan A 7e70a4b1decd
ship-it is a skill published in the GitHub repository stevengonsalvez/agents-in-a-box (23 stars, last pushed today), licensed MIT. It adds 96 tokens to every session and 2,733 once invoked, about $0.0005 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.
Other skills, from other repositories
chinese-commit-conventions
A Chinese-language convention for writing Git commit messages, based on Conventional Commits, a standard format that tools can use to classify changes and build changelogs.
github-automation
GitHub workflow automation, PR management, issue tracking, and code review coordination. Integrates with GitHub Actions and repository management. Use when: PR creation, code review, issue management, release automation, workflow setup. Skip when: local-only changes, non-GitHub repositories.
git-advanced-workflows
Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
block-no-verify-hook
Configure a PreToolUse hook to prevent AI agents from skipping git pre-commit hooks with --no-verify and other bypass flags. Use when setting up Claude Code projects that enforce commit quality gates.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.