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 alpha-omega-security/threat-model --skill threat-model-interviewgit clone --depth 1 https://github.com/alpha-omega-security/threat-modelWrote 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/alpha-omega-security/threat-model/threat-model-interview)<a href="https://agentmods.dev/skills/alpha-omega-security/threat-model/threat-model-interview"><img src="https://agentmods.dev/badge/skills/alpha-omega-security/threat-model/threat-model-interview.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00122 | $0.01300 |
| Opus 5 | $0.00061 | $0.00650 |
| Sonnet 5 | $0.00024 | $0.00260 |
| Haiku 4.5 | $0.00012 | $0.00130 |
Grade A, and why
threat-model-interview 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 8d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Threat Model — Interview (question waves)
Phase 3.4. Iteration is mandatory and the model is finite — better a tight 3-page document than a sprawling 20-page one. Pull questions from the question bank; reword for the project — do not read them verbatim.
Choose a mode
- Interview-first — ask, then draft. Best when a maintainer is actively engaged and answers return quickly.
- Draft-first (usually more efficient) — write v1 entirely from public artifacts (recon + surface), tag every claim, and collect the unresolved questions in §1.18. Hand the maintainer a document to react to rather than a questionnaire to fill in. Best when maintainer time is scarce or asynchronous.
Wave discipline
- Never dump every question at once — a maintainer will not answer 30 in one go, and the answers will be shallow if they do. Ask in waves of 3–7, prioritized by which answers most shape the rest of the model.
- Wave 1 is always scope + intended use — everything depends on it — plus the
two questions that reshape multiple sections and are almost never documented:
- the configuration-support question (support posture for every security- relevant knob, especially a default that voids a §1.11 property, reshaping §1.6/§1.11/§1.13/§1.17);
- the no-surprise side-effects question (the negative claims from the
surface pass — sockets, spawning, signal handlers, env reads, global state).
If a prior
SECURITY.md/"threat model" doc exists, also ask the coexistence question in wave 1.
- Subsequent waves drill into trust boundaries, adversary model, dependencies,
properties provided/not-provided, and known misuses/non-findings. Prioritize
any
unresolvedrows in the surface contract-dimension matrix by expected triage volume and impact; numeric boundaries, callback trust, serialization, and failure atomicity commonly outrank low-volume edge cases.
Frame every question as a proposed answer
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.
- 8d ago First seen · 100 lines · 122 tokens per session scan A 6cb45d9d8c82
threat-model-interview is a skill published in the GitHub repository alpha-omega-security/threat-model (54 stars, last pushed 20d ago), licensed MIT. It adds 122 tokens to every session and 1,300 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
copilotkit-upgrade
Use when migrating a CopilotKit v1 application to v2 -- updating package imports, replacing deprecated hooks and components, switching from GraphQL runtime to AG-UI protocol runtime, and resolving breaking API changes.
notifications
Send notifications through the unified notification router.
telegram-setup
Connect a Telegram bot to the Vellum Assistant gateway with automated webhook registration and credential storage.
chat-complex-documents
Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…
vellum-skills-catalog
Discover bundled skills and search/install community skills from the skills.sh registry.
experiment-tracking-swanlab
Provides guidance for experiment tracking with SwanLab. Use when you need open-source run tracking, local or self-hosted dashboards, and lightweight media logging for ML workflows.