Godmode

Godmode — Autonomous AI Coding Agent for Claude Code, Cursor, Codex & Gemini

Your AI writes code. Godmode makes it write *great* code — then proves it.

Godmode turns any AI coding assistant into an autonomous engineering loop — 135 skills that measure every change, keep what improves, and revert what doesn't — installable on Claude Code, Codex, Cursor, Gemini CLI, OpenCode, pi, omp, and Amp.

Real capture, live pi session — a win kept, a regression caught and reverted. More demos ↓
TL;DR: Install with claude plugin install godmode. Say /godmode optimize my API and walk away. It measures, iterates, keeps improvements, reverts failures, and stops when done.

See It In Action

Real captures from live pi sessions (zai/glm-5.3, recorded with vhs) — tapes and targets in demo/.

1. Skill routing — request to matched skill

*godmode Tier-1 matching routes a checkout rate-limiting request to the ratelimit skill.*

Transcript (accessible text fallback)

2. Optimize loop — real keep, real revert

*baseline 189ms, lru_cache KEEP at 0ms, fib(32) regression DISCARD at 517ms, reverted with git reset — real metric, real revert.*

Transcript (accessible text fallback)

3. Goal-bridge — machine-checkable completion contract

*a failing test goes red to green under a 4-field contract (metric / threshold / evidence / rollback) with exit-0 proof.*

Transcript (accessible text fallback)

The three captures above are real sessions; the blocks below are illustrative output shapes of other skills — not captured transcripts.

More output shapes (illustrative, not captured runs)

Performance Optimization — 847ms to 198ms, fully autonomous

Multi-Agent Build — 4 agents, isolated worktrees, clean merge

Security Audit — STRIDE + OWASP + red team

Every finding comes with code evidence, severity,…