A command that prepares a structured release checklist after code review and commit, covering deployment checks, rollback, monitoring, feature flags, rollout, and release notes.

Use it before deployment to create a ship plan and deployment command for the user to run; it does not deploy the application itself.

It gathers the feature's specification, design, tasks, validation result, and review decision so deployment preparation is based on the recorded project details.

ship — Command for Claude Code by loiane

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.

Clone the repo

git clone --depth 1 https://github.com/loiane/specs-driven-development-spring-angular

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/loiane/specs-driven-development-spring-angular/ship/github.svg)](https://agentmods.dev/commands/loiane/specs-driven-development-spring-angular/ship)

Your own site

<a href="https://agentmods.dev/commands/loiane/specs-driven-development-spring-angular/ship"><img src="https://agentmods.dev/badge/commands/loiane/specs-driven-development-spring-angular/ship/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/loiane/specs-driven-development-spring-angular/ship"><img src="https://agentmods.dev/badge/commands/loiane/specs-driven-development-spring-angular/ship.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,027 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.

Model	Per session	Once invoked
Fable 5.1	$0.00018	$0.01027
Opus 5.5	$0.00007	$0.00411
Sonnet 5.5	$0.00004	$0.00205
Haiku 4.5	$0.00002	$0.00103

Measured 1mo ago against content hash 6952be998146, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo 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.

.claude/commands/ship.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/ship

Phase: 8 — ship (post-commit, pre-deploy hygiene) Owning agent: .claude/agents/spring-code-reviewer.md (reused; no new persona) Skills used: shipping-and-launch, spring-security-baseline, flyway-or-liquibase-detection

Purpose

After /review approves the diff and the user commits, produce a structured ship plan that verifies pre-deploy gates, captures rollback + observability + flag posture, plans the staged rollout, and drafts release notes. The agent never deploys — it prints the deploy command for the user to run.

Inputs

<feature-id> (optional). Defaults to the most recent feature with an 08-code-review.md verdict of Approve or Approve with waivers.
Optional --base <ref> (defaults to origin/main) for diff and release-note generation.

Reads

.specs/<feature-id>/01-spec.md — ## Goal, AC list, any open Q-NNN.
.specs/<feature-id>/03-design.md — migration plan, security posture, any open Q-NNN.
.specs/<feature-id>/04-tasks.md — files_in_scope for diff-scope check.
.specs/<feature-id>/07-validation-report.md — verdict must be PASS.
.specs/<feature-id>/08-code-review.md — verdict must be Approve or Approve with waivers.
.specs/_baseline.json — for regression check.
git diff <base>...HEAD and git log <base>..HEAD — for migration classification, new-endpoint detection, release-note drafting.
.claude/skills/shipping-and-launch/SKILL.md (authoritative behavior).
.claude/templates/ship-plan.template.md.

Writes

.specs/<feature-id>/09-ship-plan.md.

Process

Resolve feature. If no <feature-id>, pick the most recent feature with 08-code-review.md verdict Approve*. Refuse if none.
Verify pre-ship gates (per shipping-and-launch skill): validation PASS, review Approve*, zero unresolved Q-NNN, no baseline regression, every changed file is in some task's files_in_scope. Halt at the first FAIL with the specific recovery command.
Classify migrations. Walk src/main/resources/db/migration/** (Flyway) or the changelog (Liquibase) hunks in the diff. Tag each script: forward-only safe / expand / contract / breaking. Halt on breaking without an ADR.
Inventory new surface. New REST endpoints, message handlers, scheduled tasks, external HTTP clients. For each, verify a MeterRegistry registration exists in the diff. Halt on missing metric.
Render the ship plan. Fill .claude/templates/ship-plan.template.md — every section non-empty (n/a allowed only with a one-line reason).
Surface human-required inputs as Q-NNN. Flag owner, alert thresholds, rollout cohorts. Halt until the user answers; do not invent.
Draft release notes. Two sections: external (plain English, ≤ 3 bullets, edited by the user before publishing) and internal (diff summary, AC list, ADR links, migration class, flag name, dashboard).
Print deploy command. Suggest the team's release-pipeline trigger or kubectl rollout / mvn deploy line. The agent never executes it.

Read the full file on GitHub · 54 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.

1mo ago First seen · 54 lines · 18 tokens per session scan A 6952be998146

Subscribe to this mod's changes

ship is a command published in the GitHub repository loiane/specs-driven-development-spring-angular (62 stars, last pushed 3d ago), licensed MIT. It adds 18 tokens to every session and 1,027 once invoked, about $0.0001 per session on Opus 5.5. 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.

DevOps and cloud Git and workflow Java Releases TDD angular github-copilot spec-driven-development spring-boot

create-feature-branch

Create and switch to a conventionally named feature branch.

jabrena/plinth · 11 tokens

create-worktree

Create an isolated Git worktree on a new conventionally named branch.

jabrena/plinth · 14 tokens

devkit.github.review-pr

Provides comprehensive GitHub pull request review with code quality, security, and best practices analysis. Use when reviewing a PR before merging.

giuseppe-trisciuoglio/developer-kit · 26 tokens

devkit.github.create-pr

Creates a GitHub pull request with branch creation, commits, and detailed description. Use when you need to submit changes for review.

giuseppe-trisciuoglio/developer-kit · 26 tokens

sddp-implement

Command description: Implement the current feature tasks. Argument hint: [optional: phase or task to start from] Command category: feature-delivery Prerequisites: spec, plan, tasks, checklists:complete-if-present.

attilaszasz/sdd-pilot · 0 tokens

wrap

The session-scoped landing step after ship: flips board rows, merges green PRs, checks deploys, tidies worktrees, prints the skim-first report. Use when the operator says to wrap up, close out the session, or land the work: 'wrap up', 'close out', 'session wrap', 'land it', 'tổng kết session', 'wrap lại đi'. Also the…

dwarvesf/dwarves-kit · 105 tokens

ship

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/ship

Purpose

Inputs

Reads

Writes

Process

What this file has done since we first saw it

Other commands, from other repositories

create-feature-branch

create-worktree

devkit.github.review-pr

devkit.github.create-pr

sddp-implement

wrap