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 OKHP3/skillz --skill threat-modelinggit clone --depth 1 https://github.com/OKHP3/skillzWrote 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/okhp3/skillz/threat-modeling)<a href="https://agentmods.dev/skills/okhp3/skillz/threat-modeling"><img src="https://agentmods.dev/badge/skills/okhp3/skillz/threat-modeling/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/okhp3/skillz/threat-modeling"><img src="https://agentmods.dev/badge/skills/okhp3/skillz/threat-modeling.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 | $0.00099 | $0.01164 |
| Opus 5 | $0.00049 | $0.00582 |
| Sonnet 5 | $0.00020 | $0.00233 |
| Haiku 4.5 | $0.00010 | $0.00116 |
Grade A, and why
threat-modeling 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 6d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Threat modeling
Threat modeling asks what could go wrong here while the answer is still cheap to act on. Code review finds the bug you wrote; threat modeling finds the defence you never designed.
Four questions structure the whole exercise:
- What are we building?
- What can go wrong?
- What are we going to do about it?
- Did we do a good enough job?
The output is a short list of decisions, not a risk register nobody reads.
1. Draw the system and mark the trust boundaries
You cannot reason about attacks without knowing where untrusted things meet trusted things.
Sketch: the components, the data flows between them, the datastores, and — most importantly — the trust boundaries those flows cross. A boundary is anywhere the level of trust changes: internet to your edge, your service to a third party, one tenant's data to another's, user to admin.
Keep it to one diagram someone can hold in their head. See diagramming.
Done when: every trust boundary in the design is marked.
2. Name the attackers and what they want
Generic "hackers" produces generic mitigations. Be specific about who and why:
- An anonymous internet user: the largest population, lowest capability
- A legitimate user acting maliciously: has valid credentials. Most under-modelled, and the source of most real access-control failures
- A compromised account: a real user whose credentials were stolen
- A malicious or compromised insider: has infrastructure access
- A compromised dependency: code you did not write, running with your privileges
For each, what would they want here? Data, money, disruption, access to something else? An attacker with no motive for your system is not worth designing against.
Done when: each attacker has a stated capability and objective.
3. Walk each element with a prompt list
Systematic beats creative. Use STRIDE against each component and flow:
| Threat | Ask | |
|---|---|---|
| S | Spoofing | Can someone pretend to be another user or service? |
| T | Tampering | Can data be modified in transit or at rest? |
| R | Repudiation | Could someone deny an action, and could you prove otherwise? |
| I | Information disclosure | Can data leak to someone who should not see it? |
| D | Denial of service | Can someone make it unavailable, cheaply? |
| E | Elevation of privilege | Can someone gain rights they should not have? |
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.
- 6d ago First seen · 112 lines · 99 tokens per session scan A c5055b21e564
threat-modeling is a skill published in the GitHub repository OKHP3/skillz (3 stars, last pushed yesterday), licensed MIT. It adds 99 tokens to every session and 1,164 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
vastai-sdk
Vast.ai Python SDK — high-level API for GPU instances, volumes, serverless endpoints, and billing.
pm-aarrr
A post-launch product-growth workflow based on AARRR: acquiring users, activating them, retaining them, earning revenue, and gaining referrals.
pm-docs
A workflow for producing product documents such as PRDs, BRDs, and MRDs. These are structured documents describing what a product needs, its business case, and its market.
product-marketing-copywriter
A marketing-copy tool that analyzes audience problems and product benefits, then creates promotional headlines and body text. Marketing copy is writing intended to explain and promote a product.
pm-position
A guided process for defining a product’s market position, value, audience, competitive difference, business model, pricing, and revenue plan. The instructions are written mainly in Chinese.
pm-retro
A retrospective workflow for reviewing a finished agile iteration, recording what happened, and choosing improvements for the next cycle.