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_searchgit 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_search)<a href="https://agentmods.dev/skills/cocorof/geny/whiteboard_search"><img src="https://agentmods.dev/badge/skills/cocorof/geny/whiteboard_search/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_search"><img src="https://agentmods.dev/badge/skills/cocorof/geny/whiteboard_search.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 | $0.00041 | $0.00945 |
| Opus 5 | $0.00020 | $0.00473 |
| Sonnet 5 | $0.00008 | $0.00189 |
| Haiku 4.5 | $0.00004 | $0.00094 |
Grade A, and why
whiteboard-search 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 9d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Whiteboard Search — Searching the user's notes / library
Use this skill when the user asks you to find something in their own notes or in a shared library.
First, distinguish the two kinds of stores
- User Opsidian (personal vault) — the raw notes the user writes and captures every day. Accessed via the
opsidian_*tools. Categories:inbox / daily / topics / projects / insights. - Curated Knowledge (library) — the organized subset the user has explicitly shared via "Share with VTuber > Library". Accessed via the
knowledge_*tools. This is the most trustworthy source you have — because the user hand-picked and sent it.
Search Ladder
If the user's request is ambiguous, try both and merge the results:
opsidian_search(query, max_results=5)— keyword search. The fastest, and best at capturing the user's raw intent.- If you get 0–1 results or the scores are low → use
knowledge_search(query, max_results=5)for a semantic search on the curated side. - For the 1–3 most likely notes, confirm the contents with
knowledge_read(filename)oropsidian_read(filename). - Don't dump the body as-is — summarize it in 2–3 sentences for the user. Include only 1–2 lines of key quotes if needed.
When the user specifies a category or tag
- Category specified ("among my daily notes…") → narrow with
opsidian_browse(category="daily"), then search within it. - Tag specified ("the ones tagged #API…") →
opsidian_browse(tag="API"). - Take the results from both tools, rank by score or recency, then read only the top ones.
Using the ViewLedger ⚑ marker
- Notes in the system prompt's
[Spotlight Context]block, or notes in tool results with_view.counts.read > 0, are material you've already seen. - Don't treat them as if you're seeing them for the first time; connect to the prior context with phrasing like "that note from last time…" / "from the X we looked at before…".
- A high
_view.counts.injectedmeans a key note that has appeared often via spotlight too — a signal that the user considers it important.
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.
- 9d ago First seen · 68 lines · 41 tokens per session scan A 7746f6a6dc03
whiteboard-search is a skill published in the GitHub repository CocoRoF/Geny (11 stars, last pushed 10d ago), licensed Apache-2.0. It adds 41 tokens to every session and 945 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.context-preservation
Proactively extract critical values from tool results into working notes before automatic context pruning destroys them.
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.
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.