Claude Leverage

Make any repo AI-first - write sustainable code from the start, or refactor a legacy codebase to prepare it for agent-driven development.

Convention layer (AGENTS.md) is also read by any AGENTS.md-aware tool - Cursor, Windsurf, Copilot…
A small, opinionated AI-coding-agent suite for Claude Code and Codex CLI:
deterministic security hooks, cross-tool skills, and self-maintaining
conventions that keep a repo safe for the *next* agent to modify.
Complements skills-based plugins like the official superpowers plugin;
it does not try to replace them.

Contents

- The problem it solves
- Who it's for
- Quick start
- Install
- What you get
- How it works
- Benchmarks
- How it compares
- What's inside
- Why one repo for two tools
- Honest history
- Verify, update, uninstall
- License

The problem it solves

Shipping at velocity with AI agents is easy. Shipping in a way that the *next*
agent (human or AI) opening the repo in six months can still safely modify is
the hard part. That second part is what the hooks, conventions, and skills here
automate - not just at session start, but continuously as the repo grows.

Without a stackWith claude-leverage

Context dies between sessions - every agent re-learns the repo from scratch.
AIDEV anchors + the context-surface hook surface the right facts at the moment of edit.

Docs drift out of sync with the code until nobody trusts them.
Self-maintenance nudges flag missing AGENTS.md, stale anchors, and code↔docs drift while it's still cheap to fix.

Big tasks lose the plot; the why behind decisions evaporates.
Durable memory: ADRs and distilled session logs carry intent across sessions.

Nothing stands between a careless agent and a leaked secret or a force-push.
Deterministic shell hooks block secrets, force-push, and --no-verify before…