ship

A command for delivering completed software work with validation and documentation. It can prepare a preview, commit changes, create a pull request, or prepare a production deployment.

In plain words
What is it for?
Use it to verify finished work, run tests and checks, generate delivery and deployment documents, create a pull request or commit, and prepare deployment steps.
Why use it?
It gathers final checks and delivery information in one workflow so completed work is easier to review and hand over. It also checks tasks, tests, code quality, security, and build results.

Command

Part of the workflow plugin — 6 commands shipped together

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 commands/stefan-jansen/claude-code-toolkit/ship
Clone the repo
git clone --depth 1 https://github.com/stefan-jansen/claude-code-toolkit

Or install workflow, the plugin that ships this one along with the rest of its 6 commands.

Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 440 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 $0.00007 $0.00440
Opus 5 $0.00003 $0.00220
Sonnet 5 $0.00001 $0.00088
Haiku 4.5 $0.00001 $0.00044

Measured 3d ago against content hash 6f2e1bf3a3fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ship 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 3d 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.

plugins/workflow/commands/ship.md · 74 lines

What it actually says

Work Delivery

Validate, document, and deliver completed work.

Options: $ARGUMENTS

Modes

  • --preview: Show what would be delivered (no changes)
  • --pr: Create pull request with documentation
  • --commit: Commit to current branch
  • --deploy: Prepare for production deployment

Process

  1. Readiness Check

    • Find active work unit
    • Verify all tasks completed
    • Check git status (clean/dirty)
  2. Quality Validation

    • Run test suite (>80% coverage required)
    • Execute linting/type checking
    • Security scan
    • Build verification
  3. Generate Documentation

    • DELIVERY.md: What was built, architecture, metrics
    • CHANGELOG.md: Added/changed/fixed
    • DEPLOYMENT.md: Prerequisites, steps, rollback
  4. Execute Delivery

    • PR: Generate description, include metrics, link issues
    • Commit: Stage changes, create conventional commit
    • Deploy: Final validation, env config, monitoring setup
  5. Memory Reflection

    • Analyze work unit for learnings
    • Prompt for /memory-update to capture:
      • Decisions made
      • Lessons learned
      • New conventions
      • Dependencies added
  6. Archive Work Unit

    • Update status to completed
    • Record delivery method
    • Move to archives

Quality Gates

All must pass:

  • ✅ Tests pass with >80% coverage
  • ✅ No critical lint/security issues
  • ✅ Documentation complete
  • ✅ Build successful

Commit Format

feat|fix|docs: Brief description

Detailed explanation of changes.

🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <[email protected]>
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. 3d ago First seen · 74 lines · 7 tokens per session scan A 6f2e1bf3a3fd

Subscribe to this mod's changes

ship is a command published in the GitHub repository stefan-jansen/claude-code-toolkit (85 stars, last pushed 1mo ago), licensed MIT. It adds 7 tokens to every session and 440 once invoked, about $0.0000 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.