suwappubot: Command for Claude Code

.claude/commands/ship.md

ship is a command for Claude Code from 0xSoftBoi/suwappubot. It costs 43 tokens per session (2,285 once invoked), scanned C, original, Apache-2.0.

A command for taking code changes through branch creation, commit, pull request, continuous integration, merge, deployment, and runtime checks. Continuous integration runs automated checks on proposed code changes.

In plain words
What is it for?
Use `/ship` to release current changes, monitor CI and deployment, check service health, inspect logs, and fix deployment failures.
Why use it?
It verifies not only that code was merged, but also that the deployed services are running that exact code and have clean logs.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md; positional $N argument.

This is 0xSoftBoi/suwappubot's own configuration. It tells Claude Code how to work on suwappubot itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything suwappubot configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is (cd "$d" && ../node_modules/.bin/bun install --frozen-lockfile >/dev/null 2>&1) \.

Reuse

Borrowing it

Nothing to install: this file belongs to 0xSoftBoi/suwappubot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/0xSoftBoi/suwappubot/main/.claude/commands/ship.md
Clone the repo
git clone --depth 1 https://github.com/0xSoftBoi/suwappubot

Made for: Claude Code.

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/0xsoftboi/suwappubot/ship.svg)](https://agentmods.dev/commands/0xsoftboi/suwappubot/ship)
Your own site
<a href="https://agentmods.dev/commands/0xsoftboi/suwappubot/ship"><img src="https://agentmods.dev/badge/commands/0xsoftboi/suwappubot/ship.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,285 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00043 $0.02285
Opus 5 $0.00022 $0.01143
Sonnet 5 $0.00009 $0.00457
Haiku 4.5 $0.00004 $0.00229

Measured 8d ago against content hash 339b57635d47, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade C, and why

ship scanned grade C with 2 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -s https://python-api-production-8526.up.railway.app/health | python3 -m json.tool

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s https://python-api-production-8526.up.railway.app/health | python3 -m json.tool
.claude/commands/ship.md · 176 lines

How it starts

The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ship Skill

Runs the full ship loop. Two rules that outrank everything below:

  1. Do NOT merge while CI is red.
  2. Shipping does not end at "merged." It ends when the deployed system is verified running the code you merged, and its logs are clean. Steps 6-8 are not optional epilogue — they are where every failure this repo has actually hit gets caught.

Optional arg: a PR title. If omitted, infer a concise conventional-commit title from the diff.

Why this skill is shaped like this

Every cheap gate proves something NARROWER than what we want to conclude:

Gate Reads as Actually proves
Railway deploy SUCCESS the code works a container built and started
A green deploy with a loose install deps are correct drift is undetectable here
CI green on your branch main is green nothing about main
Service status SUCCESS running current code some build, of some commit, sometime
/health 200 the bot booted that host answered
No ImportError in logs nothing is wrong no ImportError

So verify the specific thing, per service, and then read the logs. Never generalise one green signal into a claim about a different component.

Step 0 — Pre-flight (CLAUDE.md mandatory checklist)

REPO=$(git rev-parse --show-toplevel); cd "$REPO"
git rev-parse --abbrev-ref HEAD
git rev-parse --git-common-dir              # a worktree? then NEVER rebase
ls .git/*.lock 2>/dev/null || echo "no locks"
git stash list | head
git status --short
git status --short | grep -iE "node_modules|\.next/|dist/" && echo "ARTIFACTS — gitignore first, stop" || true
git fetch origin main -q && git rev-list --left-right --count origin/main...HEAD

If on main, branch first — never commit straight to main.

Step 1 — Format, parse, and LOCKFILE check (CI gates on all three)

PYF=$(git status --short | awk '{print $2}' | grep '\.py$')
[ -n "$PYF" ] && python3 -c "import ast; [ast.parse(open(f).read()) for f in '''$PYF'''.split()]; print('parse ok')"
[ -n "$PYF" ] && black --line-length=100 $PYF

If you changed ANY package.json, you must regenerate its lockfile — CI runs bun install --frozen-lockfile in showcase/, terminal/, webapp/, api-ts/ and mobile. A missing lockfile update fails CI even when every deploy is green. Use the bun version CI pins (see .github/workflows/test.yml) — a lockfile written by a different bun can fail the frozen check on its own:

BUN_PIN=$(grep -m1 'bun-version:' .github/workflows/test.yml | awk '{print $2}')
npm i --no-save bun@"$BUN_PIN" >/dev/null 2>&1
for d in showcase terminal webapp api-ts; do
  [ -f "$d/bun.lock" ] || continue
  (cd "$d" && ../node_modules/.bin/bun install --frozen-lockfile >/dev/null 2>&1) \
    && echo "$d lockfile OK" || echo "$d LOCKFILE DRIFT — run: (cd $d && bun install) and commit"
done

Read the full file on GitHub · 176 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 · 176 lines · 43 tokens per session scan C 339b57635d47

Subscribe to this mod's changes

ship is a command published in the GitHub repository 0xSoftBoi/suwappubot (3 stars, last pushed today), licensed Apache-2.0. It adds 43 tokens to every session and 2,285 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other commands, from other repositories