DEV Community

Cover image for I Open-Sourced the Most Overkill Claude Code Setup — 15 Agents, 17 Hooks, 60-99% Token Savings
Itachi
Itachi

Posted on

I Open-Sourced the Most Overkill Claude Code Setup — 15 Agents, 17 Hooks, 60-99% Token Savings

I kept burning through Claude Code's Max plan limits way too fast. So I built an entire optimization and quality enforcement system and open-sourced it.

🔗 claude-god-mode on GitHub

The Problem

Claude Code is incredible, but it has three fundamental issues:

  1. Token consumption is brutal — hitting limits on the $200/mo Max plan with single complex prompts
  2. AI writes disconnected code — beautiful modules that compile and pass tests but are never imported or called anywhere
  3. AI writes fake tests — 87% coverage that would pass even if you deleted the feature

The Solution: An Autonomous Pipeline

Every layer runs without manual intervention:

Layer Tool Savings
CLI Output RTK 60-90%
Code Indexing jCodeMunch 95%+ (at 50MB RAM)
Tool Output Context Mode 98%
Prompt Compression Headroom ~50%
Context Pruning Cozempic 30-70%
Output Verbosity Caveman 60-75%

Combined: 2-10x more usage from the same plan.

15 Specialized Agents

Not generic "write code" agents — epistemically specialized:

  • Adversarial Coach — tries to BREAK your code. Never praises.
  • Red Team — you tell it what security you added, it attacks those claims
  • Spec Interviewer — asks 40+ questions before you write a line
  • Integration Enforcer — blocks "done" if code has zero callers
  • Test Authenticator — catches fake tests (tautological assertions, mock theater, happy-path-only)
  • Tree of Thought — explores 3+ approaches before committing
  • UI Architect — fetches real components from 7 MCP libraries instead of writing CSS from scratch
  • Design Critic — screenshots the running app and scores visual quality

17 Deterministic Hooks

Unlike CLAUDE.md rules (which Claude can ignore), hooks are mechanical:

  • Secret scanning on prompts AND file writes
  • Destructive command blocking (rm -rf, git reset --hard, DROP TABLE)
  • --no-verify prevention (Claude was bypassing git hooks!)
  • Branch protection warnings on main/master
  • Loop detection with escalating guidance
  • Session handover between sessions
  • Orphan code detection at completion

The Connectivity Fix

The #1 AI coding failure: writing code that compiles but nothing calls.

My setup enforces:

  • Pre-write: name where the new file will be imported before writing it
  • Post-write: verify with LSP tools that the code has callers
  • Completion gate: Stop hook blocks "done" if new exports have zero references

One Command Install

curl -fsSL https://raw.githubusercontent.com/Itachi-1824/claude-god-mode/main/install.sh | bash
Enter fullscreen mode Exit fullscreen mode

Interactive installer — asks before installing each tool. Copies agents, merges hooks, configures MCP servers.

MIT licensed. Star it if it helps ⭐

github.com/Itachi-1824/claude-god-mode

Top comments (0)