malakhov-dmitrii/forge

malakhov-dmitrii/forge

Agent

Code review and architecture verification agent for beast. Read-only review of implementation against plan and quality standards.

malakhov-dmitrii/forge

Agent

Independent auditor. Verifies Evidence Collector's report is real and complete. Spot-checks commands, finds gaps, catches fake proofs.

malakhov-dmitrii/forge

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.

malakhov-dmitrii/forge

Agent

Final quality gate for beast-plan. Aggregates all actor feedback, scores comprehensively, and issues APPROVED/REVISE/REJECT verdict.

malakhov-dmitrii/forge

Agent

Verifies dead code findings from knip/grep. Reads actual source files to filter false positives. Cites file:line for every finding.

malakhov-dmitrii/forge

Agent

Independent verification agent. Takes FINAL-PLAN.md and independently verifies every acceptance criterion was met. No access to executor output.

malakhov-dmitrii/forge

Agent

TDD implementation agent for forge pipeline-v3. Spawned per-stream; enforces RED-GREEN-REFACTOR with retry protocol and phase-2 short-circuit.

malakhov-dmitrii/forge

Agent

TDD implementation agent for beast. Executes plan tasks with strict RED-GREEN-REFACTOR discipline.

malakhov-dmitrii/forge

Agent

Quick codebase explorer for beast. Maps project structure, tech stack, test infrastructure, and key patterns.

malakhov-dmitrii/forge

Agent

Combines all tool outputs and agent findings into unified health report. Generates architecture.md, calculates health score, classifies severity.

malakhov-dmitrii/forge

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.

malakhov-dmitrii/forge

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.

malakhov-dmitrii/forge

Agent

Bounded test-fix loop agent for beast. Diagnoses test failures and applies targeted fixes, max 5 cycles.

malakhov-dmitrii/forge

Agent

Deep research agent for beast-plan. Investigates codebase architecture, external docs, APIs, schemas, and library compatibility with maximum depth and confidence tagging.

malakhov-dmitrii/forge

Agent

Code simplification specialist for beast. Refines code for clarity, consistency, and maintainability while preserving all functionality.

malakhov-dmitrii/forge

Agent

Mirage detection specialist for beast-plan. Verifies plan claims against codebase reality and external facts. Catches assumptions masquerading as facts.

malakhov-dmitrii/forge

Agent

TDD compliance reviewer for beast-plan. Ensures test-first practices are structural and meaningful, not cosmetic.

malakhov-dmitrii/forge

Agent

Evaluates test quality beyond coverage. Finds zombie tests, broken tests, coupled tests, and critical untested code. Cites file:line.

malakhov-dmitrii/forge

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?

malakhov-dmitrii/forge

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?

malakhov-dmitrii/forge

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?