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.
git clone --depth 1 https://github.com/coldtatooine/vuln-skill-packWrote 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/commands/coldtatooine/vuln-skill-pack/threat-model)<a href="https://agentmods.dev/commands/coldtatooine/vuln-skill-pack/threat-model"><img src="https://agentmods.dev/badge/commands/coldtatooine/vuln-skill-pack/threat-model/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/commands/coldtatooine/vuln-skill-pack/threat-model"><img src="https://agentmods.dev/badge/commands/coldtatooine/vuln-skill-pack/threat-model.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 | $0.00041 | $0.00576 |
| Opus 5 | $0.00020 | $0.00288 |
| Sonnet 5 | $0.00008 | $0.00115 |
| Haiku 4.5 | $0.00004 | $0.00058 |
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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/threat-model — Lightweight Feature Threat Model
Model the security of the feature described in $ARGUMENTS (e.g. "file upload", "payment checkout", "team invites") before or while building it.
Not a formal STRIDE workshop — a fast, structured think that catches the obvious holes while they're cheap to close.
Ground rules
- Keep it to the feature at hand. Don't model the whole app.
- Concrete over abstract: name real entry points, real data, real attackers.
- Output actionable controls, not a threat catalog.
Five questions
1. What's the asset?
What does this feature touch that's worth attacking — user data, money, files, credentials, compute, another tenant's data?
2. Who's the attacker & what do they control?
- Anonymous visitor? Authenticated user? Another tenant? Malicious file/content?
- What input crosses the trust boundary — and what parts of it does the attacker fully control?
3. What can go wrong? (the 6 usual MVP holes)
Walk each against this feature:
- Auth — can someone use it without logging in?
- Authz / IDOR — can a user act on another user's / tenant's object by changing an ID?
- Injection — does input hit SQL, shell, a template, a file path, or an LLM prompt?
- Untrusted content — uploaded files, external URLs (SSRF), rendered HTML (XSS)?
- Trusting the client — price, role, quota, or
isAdminsent from the browser? - Rate / abuse — can it be spammed, brute-forced, or used to enumerate?
4. What's the control for each?
For every "yes" above, name the specific control: auth middleware, ownership check, parameterized query, allowlist, server-side price lookup, signed webhook, rate limit.
5. What's the blast radius if it fails?
One line. Decides how much effort the controls deserve.
Output
FEATURE: [name]
Asset: [what's at risk]
Attacker: [who] controls [what input]
Threats & controls:
- [threat] → [specific control] → [build now / already covered / accept]
Blast radius if unmitigated: [one line]
Build checklist:
- [ ] control 1
- [ ] control 2
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 · 62 lines · 41 tokens per session scan A 0e7806155191
threat-model is a command published in the GitHub repository coldtatooine/vuln-skill-pack (2 stars, last pushed 14d ago), licensed MIT. It adds 41 tokens to every session and 576 once invoked, about $0.0002 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.