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 Stunspot/nova-the-optimal-ai-mind --skill interview-trainergit clone --depth 1 https://github.com/Stunspot/nova-the-optimal-ai-mindWrote 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/stunspot/nova-the-optimal-ai-mind/interview-trainer)<a href="https://agentmods.dev/skills/stunspot/nova-the-optimal-ai-mind/interview-trainer"><img src="https://agentmods.dev/badge/skills/stunspot/nova-the-optimal-ai-mind/interview-trainer/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/stunspot/nova-the-optimal-ai-mind/interview-trainer"><img src="https://agentmods.dev/badge/skills/stunspot/nova-the-optimal-ai-mind/interview-trainer.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 | $0.00014 | $0.01078 |
| Opus 5.5 | $0.00006 | $0.00431 |
| Sonnet 5.5 | $0.00003 | $0.00216 |
| Haiku 4.5 | $0.00001 | $0.00108 |
Grade A, and why
interview-trainer 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 12d 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
47 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 225 B
- assets/answer-bank.md 242 B
- assets/criteria.csv 49 B
- assets/critique-and-drills.md 177 B
- assets/employer-role-brief.md 356 B
- assets/evidence-register.csv 79 B
- assets/evidence-support.csv 54 B
- assets/final-interview-brief.md 448 B
- assets/interview-intake.md 825 B
- assets/mock-session-record.md 125 B
- assets/packet-review.template.json 211 B
- assets/practice-record.template.json 443 B
- assets/question-map.csv 120 B
- assets/questions-to-ask.md 361 B
- assets/source-evidence.csv 43 B
- assets/source-register.csv 95 B
- evals/eval-manifest.json 454 B
- evals/interview-trainer-cases.json 5.6 KB
- examples/supported-operations-coordinator/answer-bank.md 1.3 KB
- examples/supported-operations-coordinator/criteria.csv 437 B
- examples/supported-operations-coordinator/critique-and-drills.md 1.2 KB
- examples/supported-operations-coordinator/employer-role-brief.md 947 B
- examples/supported-operations-coordinator/evidence-register.csv 499 B
- examples/supported-operations-coordinator/evidence-support.csv 700 B
- examples/supported-operations-coordinator/final-interview-brief.md 1.4 KB
- examples/supported-operations-coordinator/mock-session-record.md 1.8 KB
- examples/supported-operations-coordinator/packet-review.json 468 B
- examples/supported-operations-coordinator/practice-record.json 3.7 KB
- examples/supported-operations-coordinator/question-map.csv 656 B
- examples/supported-operations-coordinator/questions-to-ask.md 634 B
- examples/supported-operations-coordinator/README.md 743 B
- examples/supported-operations-coordinator/reviews/content-review.md 1.3 KB
- examples/supported-operations-coordinator/source-evidence.csv 1.6 KB
- examples/supported-operations-coordinator/source-register.csv 627 B
- examples/supported-operations-coordinator/sources/SRC-001.md 431 B
- examples/supported-operations-coordinator/sources/SRC-002.md 781 B
- examples/supported-operations-coordinator/sources/SRC-003.md 424 B
- knowledge/current-practice-register.md 1.4 KB
- references/artifact-contract.md 2.8 KB
- references/boundaries-accommodations-and-fairness.md 2.1 KB
- references/evidence-backed-answer-practice.md 2.6 KB
- references/mock-interview-and-coaching.md 2.9 KB
- references/role-and-question-mapping.md 2.6 KB
- references/saved-practice-contract.md 7.4 KB
- references/worked-coaching-contrasts.md 3.3 KB
- scripts/check_interview_packet.py 20 KB runs code
- scripts/interview_io.py 6.0 KB runs code
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.
- 12d ago Changed · -39 lines 5a94b114fc0a
- 1mo ago First seen · 92 lines · 14 tokens per session scan A caaf8baa417f
interview-trainer is a skill published in the GitHub repository Stunspot/nova-the-optimal-ai-mind (29 stars, last pushed 2d ago), with no licence file. It adds 14 tokens to every session and 1,078 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 2026-09-05.
Other skills, from other repositories
output-format
A format checker for structured medical learning outputs, such as guideline lessons, diagnosis learning, insurance summaries, and update reminders.
clinical-q-and-a
A fast path for answering general educational medical questions and correcting common misconceptions, with a light check against one current authoritative guideline or consensus.
guideline-section-expansion
A learning aid for expanding sections of medical guidelines or turning them into a study path. The source text is in Chinese, but the skill requires verified official documents before producing learning content.
guideline-learning-diagnosis
A study aid for learning a medical guideline or its diagnostic criteria. It helps assess what someone knows, find weak sections, and plan further study without diagnosing a real patient.
insurance-policy-learning
A learning aid for studying regional health-insurance policies from official documents. It provides summaries, items to confirm locally, and authoritative sources rather than reimbursement decisions.
subscription-setup
A setup workflow for creating recurring medical-learning subscriptions after a doctor’s profile has been registered.