HN Showcase
Back to browse
GitHub Repository

Browser-first markdown plan review. Start local web review in one command, then let your agent continue through MCP.

5 starsTypeScript

MD Feedback – Review AI Plans in Markdown via MCP

by yeominux·Mar 3, 2026·1 point·0 comments
Visit ProjectView on HN

AI Analysis

●●SolidNiche GemShip It

MCP-integrated review gates for AI agents—annotation-driven handoffs save context across sessions.

Strengths
  • •3 annotation types (Fix/Question/Highlight) map directly to MCP tools, eliminating translation friction
  • •Explicit markdown hierarchy ensures agent follows plan first, then applies memos—architectural clarity
  • •Session handoffs + checkpoints preserve review progress, not just output—beats copy-paste context
Weaknesses
  • •Audience strictly limited to heavy Claude/agent IDE users (Cursor, Copilot) with MCP workflows
  • •1 star on GitHub—unproven adoption; unclear if engineers prefer this over inline comments in IDE
Target Audience

AI-assisted developers using Claude Code, Cursor, or similar agent IDEs

Similar To

Cursor · Continue.dev · Sourcegraph Cody

Similar Projects

Developer Tools●●Solid

Skill to annotate any Markdown file for AI feedback

You can hit /plannotator-annotate or run a local CLI to open a Markdown file in an annotation UI, make deletions/replacements/comments (even attach images), and export feedback as structured markdown that an agent can act on. It's a focused, practical tool for teams that already use agent plan modes — neat UX touches (browser UI + blocking CLI flow) but it stops short of broader integrations like PRs or VCS hooks that would make it indispensable.

Niche GemShip It
ramoz
103mo ago