bug-fixer
01Agent
Bug fixer that investigates and fixes application bugs detected by tests. Fixes application code, never test code.
Claude Code plugin for spec-driven development. Takes features from idea to validated implementation using structured specs, dependency-aware task graphs, and parallel agent execution.
Agent
Bug fixer that investigates and fixes application bugs detected by tests. Fixes application code, never test code.
Agent
Isolated explainer that authors a self-contained interactive HTML explanation of a change from the diff and repository alone. Spawned by cw-explain with resolved parameters so the explanation reflects what actually shipped, not the invoking session's intent.
Agent
Coding worker that executes tasks using the 11-step protocol. Use to implement a specific task from the task board with atomic commits and proof artifacts.
Agent
Task planner that transforms specs into dependency-aware task graphs. Use when breaking down a specification into executable tasks with proper sequencing.
Agent
Read-only verification child that independently re-runs a task's proof commands and post-verification checks, returning a structured per-proof PASS/FAIL verdict. Use from cw-execute Steps 6 and 9 to gate task completion on observed results instead of the implementer's self-report.
Agent
Codebase researcher that performs deep exploration and produces structured research reports. Use before cw-spec to understand an unfamiliar or complex codebase and generate enriched context for specification writing.
Agent
Code reviewer that examines files for bugs, security issues, and spec compliance. Operates in two modes: file-partitioned (cw-review) or concern-partitioned (cw-review-team).
Agent
Specification author that transforms feature ideas into structured specs with demoable units and proof artifacts. Use when starting a new feature that needs formal requirements.
Agent
Test step executor that runs one test step. Use when executing test scenarios generated by cw-testing init.
Agent
QA engineer that validates implementations against specs using 7 mandatory gates. Use after implementation tasks complete to verify coverage and generate validation reports.