ship-unit

A Git commit step for saving one completed coding unit as a single logical change. It includes the implementation file and any structural files it needed.

In plain words
What is it for?
Use it after building a unit of Python code to create its feature-branch commit with a clear imperative message.
Why use it?
It keeps related changes together and makes the commit history easier to understand. It also prevents fixed type contracts from changing during this step.

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/nullhack/temple8/ship-unit
Any agent
npx skills add nullhack/temple8 --skill ship-unit
Clone the repo
git clone --depth 1 https://github.com/nullhack/temple8

Made for: Claude Code, Codex.

Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 126 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 $0.00017 $0.00126
Opus 5 $0.00009 $0.00063
Sonnet 5 $0.00003 $0.00025
Haiku 4.5 $0.00002 $0.00013

Measured yesterday against content hash ffb0d1292802, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ship-unit 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.

.opencode/skills/ship-unit/SKILL.md · 12 lines

What it actually says

Ship Unit

  1. Load [[software-craft/git-conventions]] — imperative message form and the one-logical-change rule.
  2. Commit the unit as one logical change on the feature branch per [[software-craft/git-conventions]]: the implemented source .py plus any structural artifacts (migrations, fixtures) it required.
  3. Write a descriptive imperative message per [[software-craft/git-conventions]].
  4. Keep the .pyi unchanged from plan — contracts are fixed during build.
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. yesterday First seen · 12 lines · 17 tokens per session scan A ffb0d1292802

Subscribe to this mod's changes

ship-unit is a skill published in the GitHub repository nullhack/temple8 (11 stars, last pushed 27d ago), licensed MIT. It adds 17 tokens to every session and 126 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 2026-08-30.