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.
npx agentmods add commands/sigistry/marketplace/shipgit clone --depth 1 https://github.com/sigistry/marketplaceWrote 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/commands/sigistry/marketplace/ship)<a href="https://agentmods.dev/commands/sigistry/marketplace/ship"><img src="https://agentmods.dev/badge/commands/sigistry/marketplace/ship.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00022 | $0.00933 |
| Opus 5 | $0.00011 | $0.00466 |
| Sonnet 5 | $0.00004 | $0.00187 |
| Haiku 4.5 | $0.00002 | $0.00093 |
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 yesterday.
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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrate everything needed to open a pull request from the current branch: understand the working state, summarize the change, draft Conventional Commit message(s), recommend a semver bump, and write a complete PR description. Use this as the one-stop "I'm ready to ship" command. $ARGUMENTS optionally names the base branch to diff against.
Process
Step 1: Detect VCS state
Run these read-only commands and interpret them before writing anything:
git rev-parse --is-inside-work-tree: confirm we are in a repo; if not, stop and say so.git status --porcelain=v1 -b: current branch, upstream, ahead/behind, staged vs unstaged vs untracked file counts.git branch --show-current: the feature branch name.
If the working tree is clean AND there are no commits ahead of the base, there is nothing to ship, report that and stop.
Step 2: Resolve the base branch
If $ARGUMENTS is provided, use it. Otherwise auto-detect in this order:
git symbolic-ref refs/remotes/origin/HEAD(strip to the branch name), the remote default.- First existing of
main,master,developviagit rev-parse --verify.
Compute the merge base: git merge-base HEAD <base>. All analysis diffs against this merge base, not the raw base tip, so unrelated upstream commits do not pollute the summary.
Step 3: Summarize the change
git diff --stat <merge-base>..HEADfor the shape (files, insertions, deletions).git log --oneline <merge-base>..HEADfor existing commits on the branch.git diff <merge-base>..HEAD(read selectively for large diffs) to understand intent.
Write a 2-4 sentence plain-English summary of what the branch does and why.
Step 4: Draft Conventional Commit message(s)
Group the diff into logical changes (a refactor, a feature, a docs update are separate commits even in one branch). For each group produce a Conventional Commit per the changelog-assembly skill's references/conventional-commits.md: type(scope): imperative subject ≤50 chars, a body explaining the why, and footers (BREAKING CHANGE:, Closes #NN) where warranted. If the branch is genuinely one atomic change, produce a single message.
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.
- yesterday First seen · 72 lines · 22 tokens per session scan A e2fcde82350d
ship is a command published in the GitHub repository sigistry/marketplace (3 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 933 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
commit
Create well-formatted commits with conventional commit messages and emojis.
ship
Autonomous spec-to-PR pipeline with zero approval gates.
run-tasks
Execute GitHub issues using full EPCT workflow (Explore-Plan-Code-Test). Converts issue requirements into completed PR.
ship
Branch, commit, open PR, gather Claude + every enabled AI reviewer (Copilot, CodeRabbit, etc.), fix/justify/resolve every finding, loop until clean, then merge. Run only when implementation is finished AND the owner has said to ship (e.g. "ship it") — never self-invoke just because the work looks done. To design and…
factory
Run one pass of the ticket queue — scan the tracker for human-authorized tickets, claim one, and route it to the right workflow (spec a raw ticket, groom the backlog, hunt a bug, or build an approved spec in its own worktree via /sonu:build). You are the trigger; there is no daemon. Never merges and never authorizes…
flow
Universal workflow entry point. Use /flow for skill-driven GitHub development. Verbs: start, commit, pr, review, address, merge, resolve, release, status, learn, setup, explain, debug, design, brainstorm, issue.