claude

shipwright-build

TDD implementation with code review, Conventional Commits, and feature branch workflow

14 on GitHubby Sven Rothv0.36.0MITupdated yesterdaydevelopment
/

Plugin shipwright-build from marketplace shipwright in svenroth-ai/shipwright. Commands read from the repo's manifest — today.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Subagents (4)

  • code-reviewer

    Reviews code diffs against section plans. Used by /shipwright-build for section review.

  • doubt-reviewer

    Optional Stage-3 fresh-context adversarial reviewer, biased to DISPROVE. Runs AFTER code-reviewer passes, only for non-trivial touches (migrations, async/concurrency, cross-plugin imports, irreversible ops). Advisory — implementer must address each objection. Used by /shipwright-build Step 6.

  • section-builder

    Autonomous TDD build agent for a single section. Spawned by orchestrator in autonomous mode. Reads spec, writes tests, implements, reviews, commits, and updates dashboard/state.

  • spec-reviewer

    Stage-1 spec-compliance HARD-GATE. Reviews a diff against the section/iterate spec BEFORE the code-reviewer runs. Used by /shipwright-build Step 6.

Hooks (18)

  • SessionStart

    uv run --no-project --with pyyaml --with jsonschema "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/run_if_cache_ready.py" "${CLAUDE_PLUGIN_ROOT}/../../shared/scripts/hooks/capture_session_id.py" "${CLAUDE_PLUGI

  • PreToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/validate_command.sh"

  • SubagentStop

    uv run --no-project "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/write-review-payload-on-stop.py" --review-type spec

  • SubagentStop

    uv run --no-project "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/write-review-payload-on-stop.py" --review-type code

  • SubagentStop

    uv run --no-project "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/cleanup-review-scratch-on-code-reviewer-failure.py"

  • SubagentStop

    uv run --no-project "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/write-review-payload-on-stop.py" --review-type doubt

  • PostToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/check_destructive_migration.sh"

  • PostToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/../../shared/scripts/hooks/check_secrets.sh"

  • PostToolUse

    uv run --no-project "${CLAUDE_PLUGIN_ROOT}/../../shared/scripts/hooks/check_file_size.py"

  • PostToolUse

    uv run --no-project "${CLAUDE_PLUGIN_ROOT}/../../shared/scripts/hooks/mark_plugin_edit.py"

  • PostToolUse

    uv run --no-project "${CLAUDE_PLUGIN_ROOT}/../../shared/scripts/hooks/track_tool_calls.py"

  • Stop

    uv run --no-project "${CLAUDE_PLUGIN_ROOT}/../../shared/scripts/hooks/audit_phase_quality_on_stop.py"

  • Stop

    uv run --no-project "${CLAUDE_PLUGIN_ROOT}/../../shared/scripts/hooks/generate_handoff_on_stop.py"

  • Stop

    uv run --no-project "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/check_documentation.py"

  • Stop

    uv run --no-project "${CLAUDE_PLUGIN_ROOT}/../../shared/scripts/hooks/write_terminal_marker.py"

  • Stop

    uv run --no-project "${CLAUDE_PLUGIN_ROOT}/../../shared/scripts/hooks/bloat_gate_on_stop.py"

  • Stop

    uv run --no-project "${CLAUDE_PLUGIN_ROOT}/../../shared/scripts/hooks/plugin_sync_reminder_on_stop.py"

  • Stop

    uv run --no-project "${CLAUDE_PLUGIN_ROOT}/../../shared/scripts/hooks/track_context_cost.py"

View source on GitHub

More from svenroth-ai/shipwright

All 14 plugins →

shipwright-plan

claude

Deep planning with research, interview, external LLM review, and TDD approach

1 skill · 3 agents · hooks

14

shipwright-iterate

claude

Lightweight SDLC for ongoing changes. Auto-detects intent (feature/change/bug) and runs specs → build → test → commit.

1 skill · 1 agent · hooks

14

shipwright-run

claude

Orchestrate the full Shipwright SDLC pipeline — from user description to deployed application

1 skill · 1 agent · hooks

14

shipwright-security

claude

Security scanning — Semgrep + Trivy + Gitleaks + Shipwright prompt-injection scan (OSS default), with an automated remediation loop and an optional Aikido backend

1 skill · 1 agent · hooks

14

shipwright-test

claude

Profile-aware test runner: unit tests, smoke tests, Playwright E2E, and security scans

2 agents · hooks

14

shipwright-adopt

claude

Onboard an existing (brownfield) repository into the Shipwright SDLC — analyze stack + routes + conventions, generate CLAUDE.md + agent_docs + configs + E2E baseline

1 skill · hooks

14

Similar plugins

mattpocock-skills

claude

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

cli-anything

claude

Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.

5 commands

HKUDS/CLI-Anything 58,665

agent-browser

claude

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

vercel-labs/agent-browser 50,373

Open Code Review

codex

Use Alibaba Open Code Review from local Codex.

2 skills

alibaba/open-code-review 50,068

Maintain shipwright-build?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins14 plugins