Agent-first CLI to improve AI coding experience - linting, document health, plan reviews and more

writ

Better instructions. Connected agents.

The quality and communication layer for AI coding agents. Lint instructions, review plans, check documentation health, and connect agents across repos, devices, and tools.

Requires Python 3.11+. On macOS, brew install python@3.12 or use pyenv. The default macOS Python (3.9) will show "no matching distribution" on install.

pip install enwrit
writ lint CLAUDE.md               # Instant quality score (0-100) for any instruction
writ plan review plan.md          # AI-powered plan review before implementation
writ init                         # Initialize + install 11 built-in skills
writ search "code reviewer"       # Find from 6,000+ instructions on the Hub
writ add code-review-agent        # Add to project + activate in your IDE

Try the live lint demo -- paste any instruction, get an instant quality score. Or browse the Hub.

Lint Your Instructions

writ lint scores any instruction 0-100 across 6 dimensions: Clarity, Verification, Coverage, Brevity, Structure, Examples. Works on any .md, .mdc, .txt, or YAML file -- no writ init required.

writ lint .cursor/rules/my-rule.mdc
# Score: 34 / 100
# Dimension       Score  Summary
# Clarity            43  Moderate              
# Structure          44  Moderate            
# Coverage           31  Needs improvement