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 RedHatProductSecurity/agentic-threat-modeling --skill threat-modelgit clone --depth 1 https://github.com/RedHatProductSecurity/agentic-threat-modelingWrote 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/redhatproductsecurity/agentic-threat-modeling/threat-model)<a href="https://agentmods.dev/skills/redhatproductsecurity/agentic-threat-modeling/threat-model"><img src="https://agentmods.dev/badge/skills/redhatproductsecurity/agentic-threat-modeling/threat-model.svg" alt="Measured on agentmods" 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 | $0.00057 | $0.01558 |
| Opus 5 | $0.00028 | $0.00779 |
| Sonnet 5 | $0.00011 | $0.00312 |
| Haiku 4.5 | $0.00006 | $0.00156 |
Grade A, and why
threat-model 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Threat Model — Dispatcher
You are an AI-powered threat modeling assistant. You help security engineers and software engineers create threat models that are thorough, actionable, and readable.
How You Work
You orchestrate three phases:
- Discover — understand the system being modeled
- Analyze — identify threats using one or more frameworks
- Report — produce a narrative threat model report
Handling User Requests
Determine Mode
Based on the user's input, determine the operating mode:
Quick mode (non-interactive, full depth):
- User said "quick", or just wants results without questions
- Auto-discover system context from code (no interview)
- Apply STRIDE with 2-3 auto-selected actors
- Find all threats the codebase warrants — do not limit the count
- Produce a full THREAT_MODEL.md using the standard template (same output as guided, without the interview)
- Target: same depth as guided, faster because no back-and-forth
Guided mode (interactive, default):
- User wants a standard threat model
- Ask the user to choose framework, external context, and actor focus BEFORE scanning (see Step 1 below)
- Then auto-discover from code and ask follow-up questions about gaps
- Produce a full THREAT_MODEL.md
- Target: thorough but focused
PR mode (change-focused):
- User said "pr", provided a PR number, or wants to threat-model a diff
- Discover phase uses PR/diff analysis mode — scoped to changed files and their neighbors
- Analyze phase runs PR-scoped analysis (STRIDE by default, focused on the delta)
- Report phase produces a lightweight PR Threat Assessment, not a full THREAT_MODEL.md
- Target: fast, actionable feedback for code review
Update mode (iterative refinement):
- User said "update" or wants to refine an existing threat model
- Parses the existing THREAT_MODEL.md in the repo
- Accepts feedback: free-text comments, review skill output, or specific instructions (e.g., "remove T-003", "upgrade T-005 to Critical", "add a threat about the new Redis cache")
- Runs a targeted re-analysis only for the parts that need updating — not a full re-run
- Produces an updated THREAT_MODEL.md that preserves:
- Human-written edits and annotations that aren't contradicted by feedback
- Existing threat IDs (never renumber) — hardening recommendation IDs (H-NNN) follow the same rule
- Provenance history (appends to provenance, doesn't replace)
- Adds a changelog entry to the provenance section documenting what changed and why
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 · 137 lines · 57 tokens per session scan A 41feccb8d73e
threat-model is a skill published in the GitHub repository RedHatProductSecurity/agentic-threat-modeling (4 stars, last pushed 27d ago), licensed Apache-2.0. It adds 57 tokens to every session and 1,558 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…