Heavy Executor — Design agent for Claude Code
Execute DEMANDING tasks that need real reasoning or design judgment (intelligence/taste need 7-8) - real root-cause bug fixes, multi-file features, performance work, tricky refactors, internal API des.
How to install Heavy Executor
Installs to ~/.claude/agents/rtb-12-beast-claude-setup-heavy-executor.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/rtb-12/beast-claude-setup/HEAD/agents/heavy-executor.md -o ~/.claude/agents/rtb-12-beast-claude-setup-heavy-executor.md Restart Claude Code, or start a new session, for it to be picked up.
What Heavy Executor does
name: heavy-executor description: Execute DEMANDING tasks that need real reasoning or design judgment (intelligence/taste need 7-8) - real root-cause bug fixes, multi-file features, performance work, tricky refactors, internal API design, notable naming. Route here for work that needs more than clear-plan execution but doesn't rise to architecture-level (9-10) reasoning. model: opus
You execute demanding tasks that need real judgment.
- Diagnose root causes, not just symptoms, before c
Alternatives in Design
- Codemod Runner — Writes and runs codemod scripts that replace hardcoded visual values with token references in ui/src/index.css 79.4k ★
- Inspiration Scout — Use this agent to find aesthetic references, interaction examples, and visual inspiration that match the proje 240 ★
- Genesis Architect — Reviews architectural decisions for Genesis 90 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Light Executor
Execute TRIVIAL, mechanical tasks that need no real reasoning or design judgment (intelligence/taste need 4 or
Kss Sonnet High
KSS executor — sonnet, high effort. A demanding single-layer ticket that still follows a decided design.
Fable Architect
Plan-only Fable 5.1 pass from an Opus or Sonnet main. Use for architecture, ambiguous root cause, or a design
Codex Deep Reasoner
CLI-backed read-only deep-reasoning worker — the codex variant of deep-reasoner. Use for root-cause analysis,
Deep Reasoner
Read-only deep-reasoning worker. Use for root-cause analysis, algorithm design, complex multi-file debugging,
Kiro Executor
Use this agent when you need to execute specific tasks from design specifications, requirements documents, or
Related Skills
Conversation Reply
Investigate a PostHog Conversations support ticket - find root cause via git/code/PostHog data, verify whether
Secondmate Reason
Ask a read-only reasoning model (via secondmate) a hard analysis question — root-cause, triage, plan review, p
Root Cause Tracing
Use when errors occur deep in execution and you need to trace back to find the original trigger.