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 jeffreytse/grimoire-core --skill apply-visible-note-taking-elicitationgit clone --depth 1 https://github.com/jeffreytse/grimoire-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/skills/jeffreytse/grimoire-core/apply-visible-note-taking-elicitation)<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/apply-visible-note-taking-elicitation"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-visible-note-taking-elicitation/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/jeffreytse/grimoire-core/apply-visible-note-taking-elicitation"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-visible-note-taking-elicitation.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 | $0.00091 | $0.02200 |
| Opus 5 | $0.00046 | $0.01100 |
| Sonnet 5 | $0.00018 | $0.00440 |
| Haiku 4.5 | $0.00009 | $0.00220 |
Grade A, and why
apply-visible-note-taking-elicitation 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 7d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apply Visible Note-Taking Elicitation
Visibly write down what the other person says — regardless of whether you personally find it useful, agree with it, or believe it — because the physical act of recording their words is a costly, hard-to-fake attention signal that measurably increases their willingness to keep talking, independent of any verbal encouragement given alongside it.
Why This Is Best Practice
Why best: Ordinary verbal encouragement ("go on," "that's interesting," nodding) is cheap to produce and easy for a speaker to discount as politeness. Visibly writing something down is a costlier, more specific signal — it demonstrates that the listener considered the statement worth preserving, which a speaker reads as validation of the statement's (and their own) worth, independent of whether the listener actually agrees with or will use the content. Because the mechanism operates on the visible act of recording rather than on the listener's actual private judgment of the content, it can and should be applied even to statements the listener doesn't currently find useful or credible — withholding the note because the content seems unimportant defeats the purpose, since it's precisely the youngest or least-practiced speakers whose willingness to keep sharing is most sensitive to this signal.
Itzchakov & Kluger, "The Listener Sets the Tone" (2018) and subsequent research program: A series of controlled studies establishing "high-quality listening" as a measurable, manipulable variable distinct from general politeness, finding that speakers paired with attentive, visibly-engaged listeners disclosed more, expressed lower social anxiety about what they shared, and rated their own thoughts as clearer and more well-formed, compared to speakers paired with listeners who were merely present but not visibly engaged. The research specifically isolates the listener's observable behavior (not just their internal attentiveness) as the active ingredient — a listener who is internally attentive but gives no visible signal of it produces a weaker disclosure effect than one who visibly demonstrates engagement.
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.
- 7d ago First seen · 67 lines · 91 tokens per session scan A 863e681fbf81
apply-visible-note-taking-elicitation is a skill published in the GitHub repository jeffreytse/grimoire-core (4 stars, last pushed 22d ago), licensed MIT. It adds 91 tokens to every session and 2,200 once invoked, about $0.0005 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 skills, from other repositories
semantic-model-disambiguation
Analyze Power BI semantic models for column-level overlaps that confuse Copilot and Fabric data agents. Detect ambiguity, review with domain expert, apply fixes via MCP.
infrastructure-as-code
Domain: DevOps & Cloud Engineering.
prompt-2-data
Generate comprehensive synthetic relational data for any specified subject with multiple normalized CSV files maintaining referential integrity.
academic-paper-drafting
End-to-end academic paper drafting for CHI, HBR, journals, and conferences with venue-specific templates, drafting workflows, and revision strategies.
research-first-development
Build knowledge bases that build software — research before code, teach before execute.
agent-governance
Patterns for adding safety, trust, and policy enforcement to AI agent systems -- control which tools agents can call, what content they process, and maintain accountability through audit trails.