mcpField
P
pr-lens

pr-lens

github.com/coldteadotaiDevelopment2.3k2.3k installsUpdated today
Repository

About pr-lens

PR Lens is a CLI and skill for turning code changes or codebases into animated architecture and data-flow diagrams. It is for coding agents and their users, with validation that identifies incorrect document fields and a self-contained SVG output.

Key features

  1. 01Animated architecture and data-flow diagrams
  2. 02JSON graph document input
  3. 03Field-specific validation errors
  4. 04Self-contained animated SVG
  5. 05Live canvas for stepping through and questions

Use cases

  1. 01Explaining architecture changes in a pull request
  2. 02Visualizing data flow in a codebase
  3. 03Reviewing a diagram on a live canvas

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/coldteadotai/pr-lens --skill pr-lens

After installing, type/pr-lensin Claude Code to confirm it loaded.

Bundled filesLICENSE

Details

From the project README

PR Lens

Animated architecture and data-flow diagrams for code changes and codebases. The agent writes one JSON document, and PR Lens draws it.

Run: npx @coldtea/pr-lens-cli@latest <command>. Nothing to install first.

Start here

This file is a discovery stub, not the usage guide. Before running any PR Lens command, load the actual workflow content from the CLI:

npx @coldtea/pr-lens-cli@latest skill              # start here: write, validate, render, share
npx @coldtea/pr-lens-cli@latest skill references   # the graph document field by field, the config format, a full example

The CLI serves skill content that always matches the installed version, so instructions never go stale. The content in this stub cannot change between releases, which is why it just points at skill.

Why PR Lens

  • Works with any coding agent (Claude Code, Codex, Gemini CLI, Cursor, OpenCode, Copilot)
  • Draws one self-contained animated SVG that GitHub shows in a comment, with no scripts
  • validate names the exact field that is wrong, so the agent can fix its own document
  • Opens as a live canvas you can step through and ask questions on
  • Needs no model key when the agent writes the document itself

Comments

Markdown supported