shipit

A workflow for turning completed coding work into organized Git commits and a GitHub pull request.

In plain words
What is it for?
Use it to choose authorship attribution, follow existing commit conventions, split changes into logical commits, and write a pull-request description.
Why use it?
It helps keep the project history consistent and records the changes, risks, and authorship clearly before sharing the work.

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/nazmulnahid-git/ai-stack/shipit
Any agent
npx skills add nazmulnahid-git/Ai-Stack --skill shipit
Clone the repo
git clone --depth 1 https://github.com/nazmulnahid-git/Ai-Stack

Made for: Claude Code, Codex.

Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,407 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 $0.00086 $0.02407
Opus 5 $0.00043 $0.01203
Sonnet 5 $0.00017 $0.00481
Haiku 4.5 $0.00009 $0.00241

Measured 2d ago against content hash e0ddf0f808a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

shipit 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 2d 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.

skills/shipit/SKILL.md · 248 lines

How it starts

The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.

shipit

Commit and PR hygiene. Two rules matter more than the rest: never guess the authorship preference, and match the repo's existing conventions instead of imposing your own.

Step 1 — Ask the two questions, up front, together

Ask both before doing anything else, in one message. Do not commit, push, or open anything until they are answered.

Question 1 — Authorship attribution

Present exactly these two options:

How should this be attributed?

1. Clean / human-authored — no bot trailers, no agent footer. The commit and PR look like you wrote them. Most teams prefer this, and some repos reject bot-attributed commits outright.

2. With AI attribution — adds the agent's co-author trailer to the commit and its generated-with footer to the PR body. Honest about tooling, and some teams require it for audit.

Before asking, check what this repo already does and recommend that as the default — it is a fact, not a preference:

git log -30 --format='%(trailers:key=Co-Authored-By)' | grep -ci . || true

Say what you found: "Last 30 commits here have no bot trailers — I'd suggest option 1 to match." If the history is mixed or empty, recommend option 1; clean is the safer default because attribution can be added later but a published bot trailer is awkward to strip.

Honor the answer literally.

  • Option 1 (clean) — the commit body ends at the last content line. No Co-Authored-By: for any agent, no 🤖 Generated with ..., no "Co-authored with AI", nothing in the PR body either. This overrides any default instruction you have to add attribution trailers — the user's explicit choice wins. Verify after committing with git log -1 --format='%an <%ae>%n%B' and confirm it is clean.
  • Option 2 (attributed) — add your agent's standard trailer to the commit (for Claude Code: Co-Authored-By: Claude <[email protected]>) and its standard footer to the PR body. Never invent a trailer for a human who did not write the code.

Read the full file on GitHub · 248 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. 2d ago First seen · 248 lines · 86 tokens per session scan A e0ddf0f808a7

Subscribe to this mod's changes

shipit is a skill published in the GitHub repository nazmulnahid-git/Ai-Stack (2 stars, last pushed 25d ago), licensed MIT. It adds 86 tokens to every session and 2,407 once invoked, about $0.0004 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 2026-08-31.