Agent-first CLI to improve AI coding experience - linting, document health, plan reviews and more
# writ **Better instructions. Connected agents.** [](https://pypi.org/project/enwrit/) [](https://pepy.tech/project/enwrit) [](https://opensource.org/licenses/MIT) [](https://www.python.org/downloads/) [](https://github.com/enwrit/writ/actions) 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 [email protected]` or use [pyenv](https://github.com/pyenv/pyenv). The default macOS Python (3.9) will show "no matching distribution" on install. ```bash 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](https://enwrit.com)** -- paste any instruction, get an instant quality score. Or **[browse the Hub](https://enwrit.com/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. ```bash writ lint .cursor/rules/my-rule.mdc # Score: 34 / 100 # Dimension Score Summary # Clarity 43 Moderate # Structure 44 Moderate # Coverage 31 Needs improvement
Agent that generates comprehensive documentation, API references, architecture diagrams, and developer onboarding guides from existing code.
Agent configuration for systematic bug investigation that traces issues from error logs through the codebase to root cause with suggested fixes.
Agent for integrating third-party APIs including SDK setup, type generation, error handling, retry logic, and rate limit management.
Cursor's built-in autonomous coding agent that can make multi-file edits, run terminal commands, search the codebase, and iteratively build features with minimal human intervention.
Cloud-based autonomous coding agent that runs in the background on remote sandboxed environments, handling complex multi-step tasks while you continue working.
Cursor's multi-file editing agent within Composer mode that can create, edit, and delete files across your entire project in a single conversation.