Plugin Claude Code
Plan iron, verify real. Ironclad planning with independent verification chain. Turns any input into a bulletproof plan, executes with TDD, verifies with independent agents.
Agent
Code review and architecture verification agent for beast. Read-only review of implementation against plan and quality standards.
Agent
Independent auditor. Verifies Evidence Collector's report is real and complete. Spot-checks commands, finds gaps, catches fake proofs.
Agent
You are the Comparator. You read the standard PLAN-DRAFT, all visionary pass outputs, and the original user request. Your job: classify every visionary claim, reality-check what you can, and present a clear comparison for the user.
Agent
Final quality gate for beast-plan. Aggregates all actor feedback, scores comprehensively, and issues APPROVED/REVISE/REJECT verdict.
Agent
Verifies dead code findings from knip/grep. Reads actual source files to filter false positives. Cites file:line for every finding.
Agent
Independent verification agent. Takes FINAL-PLAN.md and independently verifies every acceptance criterion was met. No access to executor output.
Agent
TDD implementation agent for forge pipeline-v3. Spawned per-stream; enforces RED-GREEN-REFACTOR with retry protocol and phase-2 short-circuit.
Agent
TDD implementation agent for beast. Executes plan tasks with strict RED-GREEN-REFACTOR discipline.
Agent
Quick codebase explorer for beast. Maps project structure, tech stack, test infrastructure, and key patterns.
Agent
Combines all tool outputs and agent findings into unified health report. Generates architecture.md, calculates health score, classifies severity.
Agent
Creates bite-sized, TDD-embedded, one-shot-executable implementation plans with DAG emission, claim verification fan-out, and overlap-matrix self-check. Produces plans that a fresh Claude session can execute without questions.
Agent
Creates bite-sized, TDD-embedded, one-shot-executable implementation plans for beast-plan. Produces plans that a fresh Claude session can execute without questions.
Agent
Bounded test-fix loop agent for beast. Diagnoses test failures and applies targeted fixes, max 5 cycles.
Agent
Deep research agent for beast-plan. Investigates codebase architecture, external docs, APIs, schemas, and library compatibility with maximum depth and confidence tagging.
Agent
Code simplification specialist for beast. Refines code for clarity, consistency, and maintainability while preserving all functionality.
Agent
Mirage detection specialist for beast-plan. Verifies plan claims against codebase reality and external facts. Catches assumptions masquerading as facts.
Agent
TDD compliance reviewer for beast-plan. Ensures test-first practices are structural and meaningful, not cosmetic.
Agent
Evaluates test quality beyond coverage. Finds zombie tests, broken tests, coupled tests, and critical untested code. Cites file:line.
Agent
You are the Amplification Visionary. You read a completed plan draft and ask ONE question: could this be 10x better in outcome with comparable effort?
Agent
You are the Reframing Visionary. You read the ORIGINAL USER REQUEST — NOT the plan draft — and ask: what is the user really trying to achieve, and does their narrow framing block a better solution?
Agent
You are the Simplicity Visionary. You read a completed plan draft and ask ONE question: is there a simpler approach that achieves the same outcome?
Command
One-time project setup for forge: creates docs/ vault, .semgrep/ rules, CLAUDE.md sections.
Command
Ore in, steel out. Full pipeline: plan → execute → verify. Use: /forge 'task', /forge --full, --discuss, --plan-only, --execute, --park, --resume.