A ruleset and review/audit commands encouraging coding agents to reuse existing solutions before adding code.
Project overview
It combines a necessity/reuse ladder with explicit safeguards and host-specific command and lifecycle-hook integration.
Project type
AI Agent · AI Coding · Prompt Engineering
Use cases
Coding & Development
Deployment
Refer to project documentation
License
MIT
Best for
Developers reviewing agent changes for unnecessary code while retaining essential behavior and safeguards.
Key capabilities
The ruleset asks the agent to understand the real flow, then consider necessity, existing code, standard libraries, native features and installed dependencies before writing new code.
The instructions require preserving trust-boundary validation, data-loss handling, security and accessibility while reducing unnecessary code; this is a rule to verify, not a guarantee that every agent change remains safe.
Provides commands to review current git diffs or audit the entire repository for over-engineering and output a delete-list.
Allows users to set the aggressiveness of the rules (lite, full, ultra, off) via commands or environment variables.
Limitations and risks
Commands and slash functions only work on skill-capable hosts; other adapters only load the always-on ruleset without the commands.
Node.js must be on the non-interactive shell's PATH for lifecycle hooks to work properly.
GitHub project description: Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
README: You ask for a date picker. Your agent installs flatpickr, writes a wrapper component, adds a stylesheet, and starts a discussion about timezones.
README: Works with 20 agents
README: ~54% less code (up to 94%) · ~20% cheaper · ~27% faster · 100% safe
README: Before writing code, the agent stops at the first rung that holds: ``` 1. Does this need to exist? → no: skip it (YAGNI) 2. Already in this codebase? → reuse it, don't rewrite 3.…