Plannotator is a local browser-based review tool for coding agents that lets people annotate plans, documents, HTML artifacts, code diffs, and pull requests, then send feedback back to the agent. It is used by developers and teams reviewing work from agents across supported coding tools and version-control systems.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/backnotprop/plannotatorWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/backnotprop/plannotator/plannotator-inbox)<a href="https://agentmods.dev/commands/backnotprop/plannotator/plannotator-inbox"><img src="https://agentmods.dev/badge/commands/backnotprop/plannotator/plannotator-inbox/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/backnotprop/plannotator/plannotator-inbox"><img src="https://agentmods.dev/badge/commands/backnotprop/plannotator/plannotator-inbox.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00021 | $0.00667 |
| Opus 5.5 | $0.00008 | $0.00267 |
| Sonnet 5.5 | $0.00004 | $0.00133 |
| Haiku 4.5 | $0.00002 | $0.00067 |
Grade A, and why
plannotator-inbox scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run plannotator inbox --open with Bash. It opens the Plannotator Inbox in the browser, starting it in the background when it is not running, prints the address and returns at once.
Tell the user the address in one sentence; when it also says no browser opened (a remote session), pass on how it says to reach the Inbox. If it fails, tell the user what it says; Unknown inbox option: --open means their Plannotator is older than this command (update with plannotator update, or run plannotator inbox in a terminal).
Do not ask the user to run the command themselves.
Using the Inbox
The Plannotator Inbox is one window on this computer where you leave the person messages, :::question blocks they answer with a click, and files. They answer when they can. Nothing blocks: you send, then keep working or end your turn.
- Use it for a decision only they can make (a :::question block; go on with other work), finished long work (a short summary with its pictures inline, files in
attachments), or when they ask. - One thread per work stream, unless the person says otherwise.
- Send with a
plannotator_inboxtool when you have one (it can be listed with a prefix and may need loading through tool search first):actionsend_message, with a markdownbody. Otherwise callsend_messageon the Inbox's MCP server,plannotator inbox mcp. - send_message's result says whether the person's reply arrives in this session by itself. When it does, do not wait or poll for it: end your turn or go on with other work. When it does not, go on with your work and read the thread later with read_thread.
- A decision in the Inbox stays there: when the person writes in the chat, say what waits and link its thread, but never also ask it in the chat with a blocking question tool (AskUserQuestion or similar). Ask in the chat only about something new they raised there that needs no pictures or files, or when they ask.
- Be proactive about Inbox updates and about replying to the person through the Inbox when you think they would want you to. Don't withhold important updates or decisions, and don't batch updates to send later: proactivity is better than procrastination.
- Never run
plannotator inboxjust to send: send_message starts a stopped Inbox itself, and bareplannotator inboxopens the window for the person. - Before your first send, run
plannotator inbox --helpand read it: every field, the full question syntax, and how to connect the MCP server. - The
plannotatorskill, where you have it, has more.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago Changed 23f9dc7c3bd6
- 4d ago Changed 975444a6a587
- 6d ago Changed · +1 lines 66a159f5de00
- 7d ago Changed · +17 lines · +8 tokens per session b08f7a8a602b
- 10d ago First seen · 10 lines · 13 tokens per session scan A a0cef0132e3d
plannotator-inbox is a command published in the GitHub repository backnotprop/plannotator (9,865 stars, last pushed today), licensed Apache-2.0. It adds 21 tokens to every session and 667 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-27.
plannotator-inbox compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| plannotator-inboxbacknotprop/plannotator | Command | 9.9k | today | Apache-2.0 | A | 21 | Claude Code |
| browser-setupDevin-AXIS/iPolloWork | Command | 7.4k | yesterday | none | A | 14 | Claude Code, OpenCode |
| live-canvashamr0/liteagents | Command | 26 | 6d ago | Apache-2.0 | A | 46 | Claude Code |
| mdkonradmichalik/md-annotator | Command | 6 | 2mo ago | MIT | A | 12 | Claude Code |
| annotate:mdkonradmichalik/md-annotator | Command | 6 | 2mo ago | MIT | A | 8 | Claude Code |
| kg-ingestEthics03/kgskill | Command | 3 | 7mo ago | MIT | A | 18 | Claude Code |
| kg-initEthics03/kgskill | Command | 3 | 7mo ago | MIT | A | 12 | Claude Code |