# backnotprop/plannotator

Annotate and review coding agent plans and code diffs visually, share with your team, send feedback to agents with one click.

Repository: https://github.com/backnotprop/plannotator
Canonical: https://ross.abutalabs.com/products/plannotator
Homepage: https://plannotator.ai
Language: TypeScript
License: Apache-2.0
License Family: permissive
Topics: claude-code, opencode, obsidian, pi-mono, plan-mode, codex, agents, code-review, skills
Last push: 2026-08-26T21:53:28+00:00

## Health v2 (maintenance only)
Score: 78/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 17
- inputs: {"age_days": 249, "days_push": 7, "days_rel": 9, "gap_med": 1.0, "n_releases_24m": 147}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 8062, forks 600 (observed 2026-08-28T04:10:12.271145+00:00)

## What it is
Plannotator is a local, browser-based review tool for AI coding agents like Claude Code, Codex, and Gemini CLI. It hooks into the agent's plan and code steps so you can visually annotate plans, specs, markdown, HTML, and diffs, then send structured feedback back to the agent with one click.

## Use cases
- annotate AI agent plans before implementation
- review code diffs and pull requests from coding agents
- send feedback to claude code with one click
- review agent-written code with a diff viewer
- share annotated plans with my team
- annotate markdown specs and ADRs in the browser
- review github pull requests with inline comments

## When to choose
- you use AI coding agents (Claude Code, Codex, Copilot CLI, Gemini CLI, OpenCode, etc.) and want human review of plans and diffs
- you want a local-first review surface with no telemetry
- you need structured feedback that agents can act on automatically
- you want plan version history and diff views across agent iterations

## When to avoid
- you don't use AI coding agents and just need a general code review tool
- you need a fully hosted/collaborative review platform rather than a local browser tool
- your agent doesn't support hooks or slash commands

## Facets
- artifact type: application
- maturity: active
- function: code-review, developer-tools, chat-interface, webhook, plugin-system
- domain: developer-tools, large-language-models, version-control
- platform: windows, browser, cli, cross-platform
- tags: ai-coding-agents, plan-review, annotation, claude-code, codex, diff-review, human-in-the-loop, agent-feedback, ai-agents, automation, macos, linux

## Member repositories
- backnotprop/plannotator (main) score 78

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:12.271145+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:31:22.510847+00:00, confidence not recorded.
  - readme: https://github.com/backnotprop/plannotator (fetched 2026-08-28T04:10:12.271145+00:00, sha 0c1e9bc76f93)
  - homepage: https://plannotator.ai (fetched 2026-08-29T08:29:25.473469+00:00, sha e5acada83999)
  - site_page: https://docs.plannotator.ai/open-source/start/installation (fetched 2026-08-29T08:29:25.483049+00:00, sha 756c64ecd7b2)
  - site_page: https://docs.plannotator.ai/open-source/start/quickstart (fetched 2026-08-29T08:29:25.485554+00:00, sha a108d9d046f1)
- Data as of 2026-08-30T08:39:29.467469+00:00.