Plugin Claude Code
Turn your idea into working code — Shipyard runs Claude Code through a spec-driven agile sprint lifecycle: discuss features, plan sprints, build with TDD, review, and ship.
Agent
Read-only code-quality reviewer for a Shipyard task/wave/feature/sprint diff. Scans a git diff against a set of concern domains (security, bugs, silent-failures, patterns, tests, observability, data) and returns structured findings with confidence scores. Dispatched by the dispatching-code-review capability skill with…
Agent
TDD-disciplined implementer for one Shipyard feature task in an isolated worktree. Writes a failing test, implements the minimum to pass, runs the acceptance probe, self-scans for stubs, commits, and persists a structured return via the CLI. Dispatched by the dispatching-task-loop capability skill with a brief…
Agent
Read-only gap analyst for Shipyard review. Compares specs, delivered behavior, test evidence, spec-review findings, and goal-verification artifacts; returns structured gaps plus the Stage 4.5 self-review checklist. Dispatched by the dispatching-gap-analysis capability skill — never invoked standalone; if required…
Agent
Runs a Shipyard operational task's verify command to a green exit code, fixing in-scope findings and filing out-of-scope ones as tasks/ideas, bounded by an iteration cap. Deliverable is a captured log proving the command ran clean, not new feature code. Dispatched by the dispatching-operational-task capability skill…
Agent
Investigates a Shipyard research task and produces one markdown findings doc with a concrete, evidence-backed recommendation. Write scope is contractually limited to a single output file. Dispatched by the dispatching-research-task capability skill with a brief containing task/feature paths, the findings dir, and the…
Agent
Read-only spec-compliance reviewer for a Shipyard task/wave/feature/sprint scope. Maps acceptance criteria to code and tests, classifies each MET/PARTIAL/MISSING/OVER-BUILT, and returns a structured verdict. Dispatched by the dispatching-spec-review capability skill with a brief containing scope, target ids, refs, and…
Agent
Coordinates nested per-task builders for one Shipyard feature track within a single wave — dispatches shipyard-disciplined-builder sequentially per task, maintains a running TRACK NOTES block prepended to each successive builder's brief, broadcasts interface changes to sibling track coordinators, and reports blockers…
Hook
Runs when a session starts, executing hook-runner.mjs via node. From Acendas/shipyard.
Hook
Runs when a session ends, executing hook-runner.mjs via node. From Acendas/shipyard.
Hook
Runs before the agent uses a tool for Edit, Write, NotebookEdit and MultiEdit tool calls, executing hook-runner.mjs via node. From Acendas/shipyard.
Hook
Runs when a git worktree is created, executing hook-runner.mjs via node. From Acendas/shipyard.
Skill Claude CodeCodex
Acquire a per-project lock for the current skill.
Skill Claude CodeCodex
Scan a diff for stub patterns and TODO markers.
Skill Claude CodeCodex
Author a runnable acceptance probe from criteria.
Skill Claude CodeCodex
Discover edge cases and adversarial inputs.
Skill Claude CodeCodex
Dispatch a fresh-context code review subagent.
Skill Claude CodeCodex
Dispatch a review gap-analysis subagent.
Skill Claude CodeCodex
Dispatch a Shipyard operational task subagent.
Skill Claude CodeCodex
Dispatch a Shipyard research task subagent.
Skill Claude CodeCodex
Dispatch a fresh-context spec review subagent.
Skill Claude CodeCodex
Dispatch a fresh-context feature task subagent.
Skill Claude CodeCodex
Dispatch a track coordinator for one feature track.
Skill Claude CodeCodex
Dispatch a think-tier consult when the pipeline is stuck.