audit
On-demand security audit — OWASP, secrets, dependencies, IaC security
On-demand code review — review current changes, a diff range, or specific files
> /plugin marketplace add lgbarn/shipyard > /plugin install shipyard@shipyard
How it fires
How this command gets triggered: by you, by Claude, or both.
/reviewContext preview
What this command does when you run it.
On-demand code review — review current changes, a diff range, or specific files
description: "On-demand code review — review current changes, a diff range, or specific files" disable-model-invocation: true argument-hint: "[target] — file, diff range (main..HEAD), or current (default: uncommitted changes)"
You are executing an on-demand code review. Follow these steps precisely.
<prerequisites>
Extract from the command:
If no target and no uncommitted changes exist, ask the user what they want reviewed.
1. Check if `.shipyard/` exists (optional — this command works anywhere). 2. If `.shipyard/config.json` exists, read `model_routing.review` for model selection. 3. Otherwise, use default model: **sonnet**. 4. Follow **Worktree Protocol** (see `docs/PROTOCOLS.md`) — detect worktree context.
</prerequisites>
<execution>
Based on the target, collect the code to review:
If the diff is empty, inform the user and stop.
Assemble context per **Agent Context Protocol** (see `docs/PROTOCOLS.md`):
Dispatch a **reviewer agent** (subagent_type: "shipyard:reviewer") with:
</execution>
<output>
Display the review report to the user.
If findings exist, offer follow-up: > "Would you like me to: > - Fix the critical/important issues > - Review additional files or a different scope > - Run a security audit on the same scope (`/shipyard:audit`)"
</output>
A Claude Code plugin for structured project execution. Plan work in phases, build with parallel agents and TDD, review with security audits and quality gates, and ship with confidence.
Repo: lgbarn/shipyard
On-demand security audit — OWASP, secrets, dependencies, IaC security
Explore requirements through Socratic dialogue and capture project definition
Execute plans using fresh subagents with review gates
Investigate bugs and failures with systematic root-cause analysis