ship

ship is a command for coding agents from vakovalskii/ontoship. It costs 47 tokens per session (344 once invoked), scanned A, original, MIT.

A guided development process that takes a software change from an idea through research, planning, implementation, testing, review, and deployment. It uses a worktree, which is a separate working copy of a Git repository, to isolate the change.

In plain words
What is it for?
Use it to deliver a feature or fix through development and production, including task breakdown, written specifications, automated tests, code review, and deployment checks.
Why use it?
It breaks a change into tracked stages and keeps checks such as tests, specifications, and independent review from being skipped.

Command

Part of the ontoship plugin — 3 skills, 5 commands shipped together

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 commands/vakovalskii/ontoship/ship
Clone the repo
git clone --depth 1 https://github.com/vakovalskii/ontoship

Or install ontoship, the plugin that ships this one along with the rest of its 3 skills, 5 commands.

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/commands/vakovalskii/ontoship/ship.svg)](https://agentmods.dev/commands/vakovalskii/ontoship/ship)
Your own site
<a href="https://agentmods.dev/commands/vakovalskii/ontoship/ship"><img src="https://agentmods.dev/badge/commands/vakovalskii/ontoship/ship.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 344 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 5.1 $0.00047 $0.00344
Opus 5 $0.00023 $0.00172
Sonnet 5 $0.00009 $0.00069
Haiku 4.5 $0.00005 $0.00034

Measured 5d ago against content hash df4cbf9fa4ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 5d 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.

commands/ship.md · 24 lines

What it actually says

Drive the change described in $ARGUMENTS through the OntoShip dev-flow.

Follow the dev-flow skill end to end:

  1. Research — understand from facts (logs, traces, code); reproduce before fixing.
  2. Tasks — decompose into tracked tasks.
  3. Goal — crystallize one clear goal + "done" criterion.
  4. Spec — write it as markdown in the KB via kb-curate (node_type, frontmatter, typed links documents:[src/…]). Search the KB first (kb-search) — don't duplicate.
  5. Isolate — work in a dedicated git worktree.
  6. Implement — code to the spec.
  7. Tests — write/adjust unit + E2E.
  8. Independent review — run an independent model (e.g. Codex CLI, read-only) over the diff.
  9. Dev-tests — MR + commits into dev; run the full suite. Red → fix, don't merge.
  10. Prod-tests — E2E/smoke against the real prod contour.
  11. Ship — merge dev → main and deploy (build-before-stop + healthcheck-poll).

Keep the gates (tests + independent review). Don't skip the spec — it's the carrier of knowledge, not a throwaway ticket.

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. 5d ago First seen · 24 lines · 47 tokens per session scan A df4cbf9fa4ef

Subscribe to this mod's changes

ship is a command published in the GitHub repository vakovalskii/ontoship (76 stars, last pushed 10d ago), licensed MIT. It adds 47 tokens to every session and 344 once invoked, about $0.0002 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.