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-authoringgit 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-authoring)<a href="https://agentmods.dev/skills/alpha-omega-security/threat-model/threat-model-authoring"><img src="https://agentmods.dev/badge/skills/alpha-omega-security/threat-model/threat-model-authoring/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/alpha-omega-security/threat-model/threat-model-authoring"><img src="https://agentmods.dev/badge/skills/alpha-omega-security/threat-model/threat-model-authoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Memory Poisoning · line 33 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
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 | $0.00140 | $0.02912 |
| Opus 5 | $0.00070 | $0.01456 |
| Sonnet 5 | $0.00028 | $0.00582 |
| Haiku 4.5 | $0.00014 | $0.00291 |
Grade A, and why
threat-model-authoring 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 10d 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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Threat Model — Authoring (draft the document)
Phase 3.5. Write the deliverable to the section structure in output-structure.md. Read principles.md first — the style bar is "describe the project as it is, not as it should be," and "write so a human can read it": short, direct sentences (one idea each), plain words, active voice, real verbs over nominalizations, and short bulleted lists or table rows instead of piled-up noun stacks. Target the reading level of good developer documentation, not a research paper — accuracy first, but never at the cost of plain prose.
The deliverable deliberately mixes both kinds of content in one document:
- Unstructured — plain prose and short bulleted lists carrying the reasoning (scope, adversary model, properties provided / not provided, false friends, downstream responsibilities, known misuses).
- Structured — meaningful tables embedded inline: the §1.7 per-input-operand
input-trust table and contract-dimension matrix, the §1.8 output-taint
statements, the §1.17 closed disposition set, and the §1.1 boxed triager
quick-start. (The separate
machine-readable
threat-model.yamlisthreat-model-sidecar's job.)
Assemble from the upstream artifacts
- §1.2/§1.3 from the recon component-family carve and out-of-scope inventory.
- §1.4/§1.5/§1.7/§1.8 from the surface analysis (reachability preconditions, side-effects inventory, per-input-operand table, contract-dimension matrix, output taint).
- §1.6/§1.9/§1.10/§1.11/§1.12/§1.13/§1.14/§1.15 seeded from recon's mined maintainer positions and promoted as interview answers arrive.
- §1.1 header, §1.16, §1.17, §1.18 authored here to bind the whole together.
- Prior-policy back-map appendix from recon whenever
SECURITY.mdor an equivalent authoritative model existed; retain every source claim until a maintainer explicitly approves removing the map.
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.
- 10d ago First seen · 186 lines · 140 tokens per session scan A 1ce135ed415e
threat-model-authoring is a skill published in the GitHub repository alpha-omega-security/threat-model (54 stars, last pushed 22d ago), licensed MIT. It adds 140 tokens to every session and 2,912 once invoked, about $0.0007 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.