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.
npx agentmods add skills/backnotprop/plannotator/plannotatornpx skills add backnotprop/plannotator --skill plannotatorgit clone --depth 1 https://github.com/backnotprop/plannotatorWhat 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 | $0.00073 | $0.03289 |
| Opus 5 | $0.00036 | $0.01644 |
| Sonnet 5 | $0.00015 | $0.00658 |
| Haiku 4.5 | $0.00007 | $0.00329 |
Grade A, and why
plannotator 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 yesterday.
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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plannotator CLI Reference
Plannotator is a local, browser-based review layer for agent workflows: it opens plans, diffs, and documents in an annotation UI, the human marks them up, and the structured feedback comes back to you on stdout. It installs as a single plannotator binary plus per-host hooks, so plan review fires automatically when you exit plan mode; every other surface is launched explicitly from the CLI. A session runs on a random localhost port (fixed port 19432 in remote mode) and blocks until the reviewer submits feedback, approves, or closes the tab.
This skill is the knowledge layer. The plannotator-review, plannotator-annotate, and plannotator-last skills are thin launchers for the three most common actions; use this reference when you need to pick the right command or flags yourself.
Choose the command
| The user wants | Run |
|---|---|
| Review a plan you produced | Nothing. Plan review opens automatically on plan exit via hooks. Never run bare plannotator yourself. |
| Review current code changes | plannotator review |
| Review a GitHub PR or GitLab MR | plannotator review <PR_URL> |
| Annotate a markdown, text, config, or HTML file | plannotator annotate <file> |
| Annotate a web page | plannotator annotate <https-url> |
| Annotate a running local app (dev server) | plannotator annotate <http://localhost:PORT/> |
| Pick a file to annotate from a folder | plannotator annotate <folder/> |
| Annotate your latest assistant message | plannotator last |
| Browse past plan decisions | plannotator archive |
| Export or share a Guided Review | plannotator guide export / plannotator guide share |
| Reopen or list live sessions | plannotator sessions |
Session model
Every review or annotate command starts a local web server, opens the browser, and blocks until the human decides. That can take minutes. Launch it with a long (or no) command timeout, or in the background, then read stdout when the process exits. Do not kill the process to "finish" a review; a session that ends without a decision reads as no feedback.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 186 lines · 73 tokens per session scan A 13731ec9b7ae
plannotator is a skill published in the GitHub repository backnotprop/plannotator (8,256 stars, last pushed 2d ago), licensed Apache-2.0. It adds 73 tokens to every session and 3,289 once invoked, about $0.0004 per session on Opus 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 2026-08-30.
Other skills, from other repositories
southwest
Search Southwest Airlines fares and points pricing via Patchright browser automation. SW is not in any GDS or API. Covers all fare classes, Companion Pass value, and fare drop monitoring.
seatmaps
Aircraft seat maps, cabin dimensions, and seat recommendations via SeatMaps.com and AeroLOPA. Search by flight number or airline+aircraft via agent-browser.
google-flights
Browser-automated Google Flights search via agent-browser. All airlines including Southwest. Cash prices, schedules, economy/business comparison, market selection.
vrbo
Search VRBO (Vrbo / Expedia Group) vacation rentals including entire homes, condos, and cabins via Patchright browser automation. VRBO sits behind Akamai Bot Manager so plain HTTP and standard Playwright get a 429 bot wall. Use for whole-home or group stays, multi-bedroom rentals, and Airbnb-vs-VRBO comparisons.…
american-airlines
Check American Airlines AAdvantage balance, elite status, and loyalty points via Patchright. Handles email 2FA with 6-box code entry. Uses persistent browser profiles to skip 2FA on subsequent runs.
web-scraper
Scrape, crawl, and extract data from websites. Use when users ask to scrape web pages, extract content, crawl websites, or collect data from the internet.