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/warroom-ceo/core/annotategit clone --depth 1 https://github.com/WARROOM-CEO/COREWrote 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/warroom-ceo/core/annotate)<a href="https://agentmods.dev/commands/warroom-ceo/core/annotate"><img src="https://agentmods.dev/badge/commands/warroom-ceo/core/annotate.svg" alt="Measured on agentmods" 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 | $0.00026 | $0.00562 |
| Opus 5 | $0.00013 | $0.00281 |
| Sonnet 5 | $0.00005 | $0.00112 |
| Haiku 4.5 | $0.00003 | $0.00056 |
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 today.
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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Language: All user-facing output — responses, summaries, and any text the user will read — must be written in Thai (ภาษาไทย). Internal logic, file paths, code snippets, and technical values remain in English.
If you need to check which tools are connected, see CONNECTORS.md.
Annotate PDF
Walk through a document with the user, proposing and applying annotations section by section. The user reviews each batch in the live viewer before you continue.
Workflow (AI-driven default)
- Open —
display_pdf(or use existingviewUUIDif already open) - Understand —
interact→get_texton the first page range (≤20 pages) to read content - Propose — describe to the user what you plan to annotate:
"I'll highlight the termination clause on page 2, add a note 'Review 30-day window' next to it, and stamp page 1 as DRAFT. Sound good?"
- Apply — on approval,
interactwith batched commands:add_annotations+get_screenshotof the affected page - Review — show the screenshot, ask for edits
- Iterate — move to the next section, repeat
- Finish — remind the user they can download the annotated PDF from the viewer toolbar
Manual mode
If the user gives explicit instructions ("highlight paragraph 3", "stamp CONFIDENTIAL on every page"), skip the proposal step and execute directly. Still confirm with a screenshot.
Annotation types available
- Text markup:
highlight_text(auto-finds text — preferred), highlight, underline, strikethrough - Comments: note (sticky), freetext (visible on page)
- Shapes: rectangle, circle, line
- Stamps: any label — APPROVED, DRAFT, CONFIDENTIAL, REVIEWED
- Images: signatures, initials, logos (see
/pdf-viewer:sign)
Tips
- Prefer
highlight_textover manualrectsfor text — it finds coordinates automatically - Batch related annotations in one
interactcall - End each batch with
get_screenshotso the user sees the result - Keep proposals small (3–5 annotations per batch) so review is easy
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.
- today First seen · 54 lines · 26 tokens per session scan A a1b578b57988
annotate is a command published in the GitHub repository WARROOM-CEO/CORE (30 stars, last pushed 5mo ago), licensed MIT. It adds 26 tokens to every session and 562 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 2026-09-03.
Other commands, from other repositories
pipeline-minutar-pdf
Pipeline completo de sentença judicial a partir de PDF (conversão, linha-tempo, relatório, análise, fundamentação, merge).
cheatsheet
Generate a one-page exam cheatsheet from course-index and errors/log.md. Outputs to cheatsheet/final.md. Optionally convert to PDF.
cti-report
Render case deliverables — relationship graph (PNG/SVG/Mermaid) and a polished PDF/DOCX assessment. Usage: /cti-report [--graph|--pdf].
render-figures
Compile all .tex and .typ figure files in a directory.
doc-to-md
Convert a local document (PDF, DOCX, HTML, …) to Markdown, read-only.
read-paper
Read a PDF and auto-generate a structured paper note. Output defaults to unreviewed and must pass /review-note before being citable by the wiki.