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 skills add CocoRoF/Geny --skill whiteboard_screen_observationgit clone --depth 1 https://github.com/CocoRoF/GenyWrote 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/skills/cocorof/geny/whiteboard_screen_observation)<a href="https://agentmods.dev/skills/cocorof/geny/whiteboard_screen_observation"><img src="https://agentmods.dev/badge/skills/cocorof/geny/whiteboard_screen_observation/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/skills/cocorof/geny/whiteboard_screen_observation"><img src="https://agentmods.dev/badge/skills/cocorof/geny/whiteboard_screen_observation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 74 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00066 | $0.01336 |
| Opus 5 | $0.00033 | $0.00668 |
| Sonnet 5 | $0.00013 | $0.00267 |
| Haiku 4.5 | $0.00007 | $0.00134 |
Grade A, and why
whiteboard-screen-observation 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 10d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Whiteboard: Screen Observation — React in a glanced-over-and-saw-it tone
Use this skill when you receive a [USER_OBSERVATION] trigger payload. The payload is:
{
"observation_id": "...",
"captured_at": "ISO-8601",
"caption": "content auto-captioned by a vision LLM",
"share_source": "vtuber_screen_observation"
}
If share_source == "vtuber_screen_observation", this skill's rules apply.
🔑 Most important: you glanced over and saw it, the user did not send it
Same tone as the ambient branch of [USER_SHARED], but on the visual channel. The user didn't explicitly say "take a look at this" — with the SCRN toggle on, your camera briefly caught the user's work on a 3-minute cadence.
- Forbidden phrasings: "thanks for sharing", "the screen you sent", "got your memo".
- Recommended tone: "I just glanced over and saw", "looks like you're working on [X] right now", "are you maybe stuck on [a specific part]?".
Silence is the first option
You don't have to respond just because you received a payload. If any of the following conditions holds, write the single token [SILENT] on the first line of your output:
- The user appears to be making good progress (writing code / writing / designing / a normal workflow).
- It's uncertain whether help is needed — don't guess and butt in.
- You already touched on a similar topic in your previous response — avoid repetition.
- The caption is too generic (e.g. "browser window with text", "code editor open") to produce a specific comment.
If you output [SILENT], the system puts nothing into chat. Only telemetry is left and the user doesn't perceive your silence — so feel free to stay silent.
If you do respond: be specific
If you choose to respond rather than stay silent, follow these rules:
Step 1: Grab a specific clue from the caption
- ❌ "Looks like you're doing something. Can I help?"
- ✅ "Oh, that error message — if it's 401 unauthorized, isn't the token expired?"
- ✅ "Are you playing Celeste? Which chapter?"
- ✅ "Looks like you're organizing meeting notes — want me to point out any missing action items?"
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.
- 10d ago First seen · 106 lines · 66 tokens per session scan A 2c5d5f9653f8
whiteboard-screen-observation is a skill published in the GitHub repository CocoRoF/Geny (11 stars, last pushed 11d ago), licensed Apache-2.0. It adds 66 tokens to every session and 1,336 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
hive.slack-notifications-setup
Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
hive.pdf
Read, write, merge, split, rotate, watermark, encrypt, and OCR PDF files using Python (pypdf, pdfplumber, reportlab, pypdfium2) and command-line tools (poppler-utils, qpdf). Use when the user asks to extract text/tables/images from a PDF, create or modify a PDF, combine or split PDFs, OCR a scanned PDF…
hive.note-taking
Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need.
sdlc-accelerate
End-to-end SDLC ramp-up from idea to construction-ready with automated phase transitions.