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-costly-commitment-screeninggit 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-costly-commitment-screening)<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/apply-costly-commitment-screening"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-costly-commitment-screening/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-costly-commitment-screening"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-costly-commitment-screening.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 | $0.00081 | $0.01964 |
| Opus 5 | $0.00041 | $0.00982 |
| Sonnet 5 | $0.00016 | $0.00393 |
| Haiku 4.5 | $0.00008 | $0.00196 |
Grade A, and why
apply-costly-commitment-screening 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apply Costly Commitment Screening
When many people request your scarce time or mentorship and a conversation cannot reliably reveal their genuine commitment level, require a specific, costly, objectively verifiable unit of self-directed output before engaging — because completing that output is a filter that only genuinely committed people pass, while a conversation alone can be passed by anyone regardless of actual follow-through.
Why This Is Best Practice
Why best: This is the mirror image of costly signaling: instead of the scarce-resource holder sending a costly signal to attract others (as in apply-talent-value-signaling), the scarce-resource holder here designs a costly test and lets others sort themselves by whether they complete it — a mechanism formally known in economics as screening. The specific design requirement is that the test cost almost nothing to the genuinely committed (who were going to produce that output anyway on the path to their actual goal) while being prohibitively effortful for someone who wants access or validation without genuine follow-through — this asymmetry in the cost of completing the test is what makes it an effective filter, not the specific content of the test itself.
Spence, "Job Market Signaling" (1973): Spence's foundational work on informational asymmetry established that when one party cannot directly verify another party's underlying quality (motivation, ability, genuine commitment), a costly action that is cheap for the genuine type and expensive for the non-genuine type can substitute for direct verification — because only someone who actually possesses the underlying quality would find the action worth the cost. Requiring a completed body of self-directed work before offering scarce mentorship applies exactly this logic in the reverse direction from a company signaling to attract talent: here, the party requesting access is the one whose type needs to be revealed.
Rothschild & Stiglitz, "Equilibrium in Competitive Insurance Markets" (1976): This companion body of economic theory to Spence's signaling work formalized "screening" — the specific mechanism where the party who lacks information (here, the mentor, who cannot directly observe a requester's true commitment level) designs a menu or test that different underlying types will respond to differently, allowing the uninformed party to sort applicants by type without needing to assess commitment directly through conversation or claims. A completed, verifiable body of work (a specific count of finished attempts) is precisely this kind of screening device: it requires no judgment call from the mentor and produces a hard, binary sorting outcome.
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 · 65 lines · 81 tokens per session scan A 876925af4f36
apply-costly-commitment-screening is a skill published in the GitHub repository jeffreytse/grimoire-core (4 stars, last pushed 24d ago), licensed MIT. It adds 81 tokens to every session and 1,964 once invoked, about $0.0004 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.
prompt-2-data
Generate comprehensive synthetic relational data for any specified subject with multiple normalized CSV files maintaining referential integrity.
infrastructure-as-code
Domain: DevOps & Cloud Engineering.
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.