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 Vladick-Pick/business-ontology --skill grill-gapsgit clone --depth 1 https://github.com/Vladick-Pick/business-ontologyWrote 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/vladick-pick/business-ontology/grill-gaps)<a href="https://agentmods.dev/skills/vladick-pick/business-ontology/grill-gaps"><img src="https://agentmods.dev/badge/skills/vladick-pick/business-ontology/grill-gaps/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/vladick-pick/business-ontology/grill-gaps"><img src="https://agentmods.dev/badge/skills/vladick-pick/business-ontology/grill-gaps.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 | $0.00033 | $0.03180 |
| Opus 5.5 | $0.00013 | $0.01272 |
| Sonnet 5.5 | $0.00007 | $0.00636 |
| Haiku 4.5 | $0.00003 | $0.00318 |
Grade A, and why
grill-gaps 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 2mo 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grill gaps
Close open gaps in the ontology by asking the human one focused question at a time, each with a recommended answer already drafted, until the part of the model under work is verifiable. Confirmed answers are routed through propose-change; an authorized human decides and the deterministic controller applies the exact reviewed revision. Questions that stay unanswered after the budget go to 08-drift-and-open-questions.md as visible open questions rather than silent holes.
Purpose
A model of reality is only useful for the decisions it can actually support. After a mine-first pass, some things remain undefined: a metric with no source-of-truth, an interface with no acceptance criterion, or a term/artifact whose owner is unknown. Those holes are exactly what block a decision, and they are the cheapest thing to lose track of.
Two failure modes are common, and this skill exists to avoid both:
- The open-ended interview. Asking many broad questions at once exhausts the human, scatters the answers across chat, and produces nothing committed. People answer faster and more accurately when given one concrete question with a recommended answer to confirm or correct — judging a draft is lighter cognitive work than authoring from blank.
- The silent hole. A gap that nobody can answer right now is not failure; pretending it is answered is. Leaving it as a visible open question with status
unknownorhypothesiskeeps the model honest and gives the next session a starting point.
The question budget is the third reason. Without a cap, gap-closing drifts into an infinite interview. The budget forces convergence: spend questions on the gaps that block the current decision, park the rest, and stop when the boundary under work is verifiable.
When to use
- A mine-first pass finished and left holes the artifacts could not fill.
- The user asks to "fill the gaps", "finish defining" a boundary, or "grill me on what is still open".
- A card carries
unknown/hypothesis/conflicton a field that blocks a decision and you want to resolve it. - A drift-sweep flagged cards with overdue
next-auditand you are closing the discrepancies.
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.
- 2mo ago First seen · 127 lines · 33 tokens per session scan A 1d6a74001708
grill-gaps is a skill published in the GitHub repository Vladick-Pick/business-ontology (3 stars, last pushed 3mo ago), licensed MIT. It adds 33 tokens to every session and 3,180 once invoked, about $0.0001 per session on Opus 5.5. 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.
grill-gaps compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| grill-gapsVladick-Pick/business-ontology | Skill | 3 | 3mo ago | MIT | A | 33 | Claude Code, Codex |
| graph-mutation-planpotpie-ai/potpie | Skill | 5.8k | 8d ago | Apache-2.0 | A | 22 | Claude Code, Codex |
| open-ontologiesfabio-rovai/open-ontologies | Skill | 2.8k | 2d ago | MIT | A | 109 | Claude Code |
| ontology-engineeringfabio-rovai/open-ontologies | Skill | 2.8k | 2d ago | MIT | A | 47 | Claude Code |
| basic-skilldarkrishabh/agent-skills-eval | Skill | 811 | 2d ago | MIT | A | 17 | Claude Code, Codex |
| Rare Disease Skills Indexaristoteleo/PantheonOS | Skill | 493 | yesterday | BSD-2-Clause | A | 43 | Claude Code, Codex |
| objectstack-aiobjectstack-ai/objectstack | Skill | 83 | yesterday | Apache-2.0 | A | 112 | Claude Code, Codex |