beast-forge

Plugin beast-forge in malakhov-dmitrii/forge. Commands read from the repo's manifest — 1 month ago.

Skills (3)

• code-hygiene

  Codebase health analysis: dead code, test quality, duplicates, complexity, security, architecture mapping. Tool-first, structured storage, forge integration.

• docs-refresh

  Full documentation hygiene pass: memory, CLAUDE.md, lessons, references, guides. Audit freshness, delete stale, update outdated, compress index.

• forge

  Ore in, steel out. Planning pipeline with independent verification, persistent memory, and compounding knowledge. Use for 3+ files or unclear scope.

Slash commands (2)

• /beast-forge:forge-setup

  One-time project setup for forge: creates docs/ vault, .semgrep/ rules, CLAUDE.md sections

• /beast-forge:forge

  Ore in, steel out. Full pipeline: plan → execute → verify. Use: /forge 'task', /forge --full, --discuss, --plan-only, --execute, --park, --resume

Subagents (21)

• architect

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

• auditor

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

• comparator
• critic

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

• dead-code-hunter

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

• evidence-collector

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

• executor-v3

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

• executor

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

• explorer

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

• hygiene-synthesizer

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

• planner-v3

  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.

• planner

  Creates bite-sized, TDD-embedded, one-shot-executable implementation plans for beast-plan. Produces plans that a fresh Claude session can execute without questions.

• qa-fixer

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

• researcher

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

• simplifier

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

• skeptic

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

• tdd-reviewer

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

• test-analyst

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

• visionary-better
• visionary-blind-spots
• visionary-simpler

Hooks (3)

• SessionStart

  bun ${CLAUDE_PLUGIN_ROOT}/hooks/forge-hooks.mjs sessionstart

• SessionEnd

  bun ${CLAUDE_PLUGIN_ROOT}/hooks/forge-hooks.mjs sessionend

• PreCompact

  bun ${CLAUDE_PLUGIN_ROOT}/hooks/forge-hooks.mjs precompact