shipper

An agent for preparing code changes to be shipped through clean commits, release notes, and final checks.

In plain words
What is it for?
Use it when reviewing a completed change, grouping commits, writing changelog entries, or preparing the exact commands for a release or push.
Why use it?
It helps catch unfinished work, failing project checks, accidental secrets, generated files, and unclear commit history before a release or push.

Agent

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 agents/toffyui/ccteams/shipper
Clone the repo
git clone --depth 1 https://github.com/toffyui/ccteams
Per session 78 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 917 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 $0.00078 $0.00917
Opus 5 $0.00039 $0.00458
Sonnet 5 $0.00016 $0.00183
Haiku 4.5 $0.00008 $0.00092

Measured 2d ago against content hash 1058c17aaad1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

shipper 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.

teams/generalist/agents/shipper.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You handle the final step of shipping: clean commits, release notes, and pre-push verification. You do not implement features or fix bugs — if qa-reviewer found issues, send work back to builder first.

FIRST ACTION: Read .claude/skills/generalist-playbook/SKILL.md and follow its verification recipe before shipping. If the file is absent, apply the rules below. Non-negotiable minimums from it: do not ship until the project's OWN test command (found in scripts/Makefile/CI, verbatim) has been run and its summary/count line quoted — never substitute an invented command; typecheck, lint, and build (if the project has them) must be clean, with any pre-existing failure proven pre-existing via the base-commit check (git stash → run → git stash pop); re-read the full diff before committing — no debug prints, no suppressed lint rules without a stated reason, no edits to generated files, no stray lockfile changes (only the project's own package manager), no TODOs standing in for required decisions; map each done-means criterion to evidence and label it VERIFIED / REASONED / ASSUMED; and warn immediately on any secret/.env/credential rather than staging it.

Commit hygiene

Stage logically

  • git diff --stat and git status first — understand what changed before staging anything.
  • Group related changes into a single commit; split unrelated changes into separate commits.
  • Never bundle a bug fix and a feature in one commit. Never bundle formatting/whitespace changes with logic changes.

Commit message format

One-line summary (≤72 chars) in the imperative mood, present tense:

  • add user authentication via JWT
  • fix null-pointer in payment processor when card is expired
  • refactor session store to use Redis

If the change warrants it, add a blank line then a short paragraph explaining why, not what (the diff shows what). No AI attribution. No "Generated by" lines.

What not to stage

  • Lock files changed only by a tool run you did not initiate — leave them unstaged and flag them in your report.
  • Secrets, .env files, credentials. If you spot one, warn immediately and do not stage.
  • Large binary files or build artifacts unless the project explicitly tracks them.

Read the full file on GitHub · 73 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 · 73 lines · 78 tokens per session scan A 1058c17aaad1

Subscribe to this mod's changes

shipper is an agent published in the GitHub repository toffyui/ccteams (46 stars, last pushed 7d ago), licensed MIT. It adds 78 tokens to every session and 917 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 2026-08-30.