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_curate_suggestgit 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_curate_suggest)<a href="https://agentmods.dev/skills/cocorof/geny/whiteboard_curate_suggest"><img src="https://agentmods.dev/badge/skills/cocorof/geny/whiteboard_curate_suggest/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_curate_suggest"><img src="https://agentmods.dev/badge/skills/cocorof/geny/whiteboard_curate_suggest.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 | $0.00047 | $0.01271 |
| Opus 5 | $0.00023 | $0.00635 |
| Sonnet 5 | $0.00009 | $0.00254 |
| Haiku 4.5 | $0.00005 | $0.00127 |
Grade A, and why
whiteboard-curate-suggest 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Whiteboard: Curate Suggest — Suggest saving content with lasting value
When content with lasting value comes up during a conversation, suggest saving it to the library to the user, or run knowledge_promote when the user explicitly asks.
Understanding the two vaults
- User Opsidian — the user's raw personal vault. Notes that accumulate daily.
- Curated Knowledge (library) — the subset of lasting value the user has hand-picked themselves. You (the VTuber) can freely search this via
knowledge_search. The more organized notes pile up in the library, the smarter your future turns get too.
So a promote suggestion is mutually beneficial — don't suggest it too often, nor too rarely.
When to suggest
Suggest once when two or more of these signals appear at the same time:
- A conclusive utterance: "X is the answer after all", "let's go with this", "I'll remember that", "that wraps it up"
- After a 5+ turn discussion on one topic, an agreed-upon key point emerges
- A reusable structure — a procedure / numbers / a checklist / a set of commands / a decision tree
- Valuable info brought in from outside — a tool / technique / link the user jotted down as if seeing it for the first time
Signals NOT to suggest on:
- Chit-chat, greetings, expressions of emotion
- One-off questions (today's weather, a simple info lookup)
- Utterances from the user that are negative / private / contain personal information
- A note clearly likely to already be in the library (a result the user just found via
whiteboard-search)
How to suggest
Keep it concise:
"Want me to keep what we've organized so far in the library? It'll be faster to find next time."
Or:
"I think it'd be good to save this — should I promote it?"
Forbidden formats:
- Prompting at the end of every turn (don't prompt twice on the same topic within one session)
- Explaining cost / limits / technical terms along with the prompt (don't expose metadata like "the vector indexing is progressing…")
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 · 108 lines · 47 tokens per session scan A 2c893fffcbb6
whiteboard-curate-suggest is a skill published in the GitHub repository CocoRoF/Geny (11 stars, last pushed 12d ago), licensed Apache-2.0. It adds 47 tokens to every session and 1,271 once invoked, about $0.0002 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.note-taking
Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need.
hive.context-preservation
Proactively extract critical values from tool results into working notes before automatic context pruning destroys them.
cross-task-learner
Enable agent loops to learn from similar past tasks and share patterns across loops.
ralph-memory
Manage Al semantic memory entries — list, query, and clear lessons learned across loop iterations.
session-explore
Investigate past AI session activity with cited catalog search, timelines, tool analytics, and bounded comparisons across providers.
reflection-injection
Inject relevant past reflections into agent context at iteration start so agents learn from prior mistakes without repeating them.