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 commands/backnotprop/plannotator/annotategit 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 | $0.00024 | $0.03555 |
| Opus 5 | $0.00012 | $0.01777 |
| Sonnet 5 | $0.00005 | $0.00711 |
| Haiku 4.5 | $0.00002 | $0.00356 |
Grade A, and why
annotate 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 — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The /plannotator-annotate command opens files, URLs, or folders in the Plannotator annotation UI.
What you can annotate
| Input | Command | What happens |
|---|---|---|
| Markdown file | plannotator annotate README.md |
Opens the file directly |
| Plain-text file | plannotator annotate config.yaml |
Opens the file directly, rendered as plain text |
| HTML file | plannotator annotate docs/guide.html |
Renders the HTML directly |
| URL | plannotator annotate https://docs.stripe.com/api |
Fetches the page, converts to markdown, then opens |
| Local app URL | plannotator annotate http://localhost:5173 |
Opens your running dev app live and annotates it in place |
| Folder | plannotator annotate ./docs/ |
Opens a file browser showing all supported files |
Supported file types
Beyond .md, .mdx, .txt, .html, and .htm, annotate accepts common plain-text config and data formats: .yaml, .yml, .json, .jsonc, .json5, .toml, .ini, .cfg, .conf, .properties, .csv, .tsv, .log, .xml, and .env.example. These render exactly like .txt — as plain text you can select and annotate.
.env is deliberately not supported: it commonly holds secrets, and annotate's version history copies file contents into the data dir (~/.plannotator/history/). Use .env.example for the secret-free template. Source-code files (.ts, .py, …) are also excluded — use plannotator review for code.
Slash command (inside an agent session)
/plannotator-annotate path/to/file.md
/plannotator-annotate https://docs.stripe.com/api
/plannotator-annotate ./specs/
The agent runs plannotator annotate <arg> under the hood. The annotation UI opens in the browser. When you submit, feedback is returned to the agent as structured output.
You do not have to pass a bare path. Extra words around a path are fine (/plannotator-annotate look at docs/spec.md please opens docs/spec.md), and a purely natural-language request (/plannotator-annotate the aim doc) hands off to the agent, which works out the file you mean and re-runs the command with a concrete target. If several of your words each name a real file, Plannotator errors and lists the candidates instead of guessing, so name exactly one target per invocation.
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 · 262 lines · 24 tokens per session scan A 46bdbd65a866
annotate is a command published in the GitHub repository backnotprop/plannotator (8,256 stars, last pushed 2d ago), licensed Apache-2.0. It adds 24 tokens to every session and 3,555 once invoked, about $0.0001 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 commands, from other repositories
kg-ingest
Ingest a source document into the Knowledge Graph - extract entities, concepts, create wiki pages.
kg-init
Initialize a new Knowledge Graph with raw/ and wiki/ structure.
kg-lint
Health check the Knowledge Graph - find orphans, contradictions, gaps, stale claims.
kg-project
Create a new project in the Knowledge Graph with ADR tracking.
kg-query
Query KG (supports: active, recent, search , decisions , plan ).
kg-setup
Configure Knowledge Graph path and create config file.