ship-feature

ship-feature is a skill for Claude Code, Codex from tahirraufkeeyu/software-development-agent-stack--sdas. It costs 61 tokens per session (2,397 once invoked), scanned A, original, MIT.

A one-pass preparation workflow for a single finished software feature before committing it to version control.

In plain words
What is it for?
Use it on uncommitted feature work to generate behavior tests, review the combined code and tests, and write a Conventional Commits message. It does not run the commit.
Why use it?
It combines test creation, code review, and commit-message drafting so you can check the change and prepare it for a pull request in one report.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it on uncommitted feature work to generate behavior tests, review the combined code and tests, and write a Conventional Commits message. It does not run the commit.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tahirraufkeeyu/software-development-agent-stack--sdas/ship-feature
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.

Any agent
npx skills add tahirraufkeeyu/software-development-agent-stack--sdas --skill ship-feature
Clone the repo
git clone --depth 1 https://github.com/tahirraufkeeyu/software-development-agent-stack--sdas

Made for: Claude Code, Codex.

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-feature

README.md
[![agentmods](https://agentmods.dev/badge/skills/tahirraufkeeyu/software-development-agent-stack--sdas/ship-feature/github.svg)](https://agentmods.dev/skills/tahirraufkeeyu/software-development-agent-stack--sdas/ship-feature)
Your own site
<a href="https://agentmods.dev/skills/tahirraufkeeyu/software-development-agent-stack--sdas/ship-feature"><img src="https://agentmods.dev/badge/skills/tahirraufkeeyu/software-development-agent-stack--sdas/ship-feature/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.

agentmods 80×15 button for ship-feature

Your own site · 80×15
<a href="https://agentmods.dev/skills/tahirraufkeeyu/software-development-agent-stack--sdas/ship-feature"><img src="https://agentmods.dev/badge/skills/tahirraufkeeyu/software-development-agent-stack--sdas/ship-feature.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,397 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.
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 $0.00061 $0.02397
Opus 5 $0.00030 $0.01198
Sonnet 5 $0.00012 $0.00479
Haiku 4.5 $0.00006 $0.00240

Measured 8d ago against content hash 21c41756d5b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ship-feature 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.

departments/developers/skills/ship-feature/SKILL.md · 213 lines

How it starts

The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When to use

  • Developer has finished writing a feature but has not yet committed.
  • User says "ship this", "get this ready to commit", "wrap this up", or "prep this for PR".
  • A feature branch has uncommitted work and the user wants the full pre-commit gate (tests + review + message) in a single flow.
  • A teammate asks to hand off work and wants a one-shot summary of what changed and whether it is safe to land.

Do not use this for multi-feature branches (run once per feature), merge conflict resolution, or releasing/tagging (see deploy-checklist). Do not use this to actually run git commit — this orchestrator produces the message, it does not execute the commit.

Chained skills

  1. test-writer — reads the new/changed production code, infers repo test conventions, generates AAA tests for every observable behaviour, and emits the test file path(s).
  2. code-review — reviews the combined diff (production + generated tests) against the security/correctness/performance/testing/observability checklist and returns severity-labelled findings.
  3. commit-message — takes the staged diff (now including tests) and produces a Conventional Commits subject plus body.

Inputs

  • A path or glob identifying the changed production code (e.g. src/pricing/discount.ts, or "whatever is in git diff").
  • Optional: the feature's ticket id (JIRA-1234, GH-456) for the commit footer.
  • Optional: the target base branch if not main/master (defaults to the repo's default branch).

Outputs

  • Generated test file(s) written in the location dictated by the repo's convention (via test-writer).
  • .sdas/artifacts/developers/ship-feature-report.md containing:
    • The list of test files generated and the behaviours they pin down.
    • The full code-review output (verdict, findings table, inline suggestions).
    • The proposed commit message (subject + body + footers) ready to paste into git commit -F.
    • A final Status: line: ready-to-commit or halted-high-severity.

Read the full file on GitHub · 213 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 · 213 lines · 61 tokens per session scan A 21c41756d5b2

Subscribe to this mod's changes

ship-feature is a skill published in the GitHub repository tahirraufkeeyu/software-development-agent-stack--sdas (18 stars, last pushed 4mo ago), licensed MIT. It adds 61 tokens to every session and 2,397 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.