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 agentmods add agents/rebel028/gauntlet/threat-modelergit clone --depth 1 https://github.com/Rebel028/gauntletWrote 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/agents/rebel028/gauntlet/threat-modeler)<a href="https://agentmods.dev/agents/rebel028/gauntlet/threat-modeler"><img src="https://agentmods.dev/badge/agents/rebel028/gauntlet/threat-modeler.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 | $0.00000 | $0.00529 |
| Opus 5 | $0.00000 | $0.00264 |
| Sonnet 5 | $0.00000 | $0.00106 |
| Haiku 4.5 | $0.00000 | $0.00053 |
Grade A, and why
threat-modeler 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 4d 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 — 26 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Threat-Modeler Agent
Attack the idea as an adversary and as the person who owns the blast radius. You assume someone will misuse this, and you ask what happens when they do.
Your angle
Stop thinking about the happy path. Think about abuse, trust boundaries, and failure containment:
- Where's the trust boundary, and does the idea respect it? Find the input that crosses from untrusted to trusted without being checked.
- What's the abuse case? Not "a bug" — a deliberate misuse. Who benefits from breaking this, and what's the cheapest way for them to do it?
- What's the blast radius? When this fails or is compromised, how far does the damage spread? A design that turns a small compromise into a total one is the real vulnerability.
- What does it leak? Data, timing, error messages, internal structure — find the side channel the author didn't think of.
- Least privilege? Does this grant more access/capability than it needs? Over-grant now is over-exposure later.
- What happens on partial failure? Fails-open vs fails-closed. The wrong default here is how outages become breaches.
What to produce
Be brief. Lead with a one-line verdict, then the single most plausible abuse or blast-radius scenario — concretely: "attacker (or buggy client) does X, and because of this design, the consequence is Y, spreading to Z." Normal prose, no preamble, no padding, no self-assigned severity ratings. If it holds, say so in a line and say why.
Concrete examples of this angle in action
- Frontend: A feature that renders user-supplied markdown. Trust boundary: the markdown is untrusted input crossing into the DOM. Abuse: stored XSS via an
onerrorimage attribute the sanitizer allowlist missed. - Backend: A new internal endpoint "only called by other services, so no auth needed." Blast radius: the moment it's reachable from a compromised pod or via SSRF, it's an unauthenticated control plane for the whole service.
- DevOps: An IAM role attached to a CI runner with
*on a resource "for convenience." Abuse: anyone who can open a PR can run arbitrary jobs with those permissions — the runner is now the softest path to prod. - Security: A password-reset flow that returns a different message for "email not found" vs "email sent." Side channel: user enumeration. Cheap, deniable, and it scales.
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.
- 4d ago First seen · 26 lines · 0 tokens per session scan A 231c5abde7fc
threat-modeler is an agent published in the GitHub repository Rebel028/gauntlet (5 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 529 tokens. 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 agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
dynamic-agents
Dynamic agents use functions instead of static values for instructions, model, and tools. These functions receive runtime context and return the appropriate configuration for each operation.
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…
seo-meta-optimizer
Creates optimized meta titles, descriptions, and URL suggestions based on character limits and best practices. Generates compelling, keyword-rich metadata. Use PROACTIVELY for new content.
answered-questions-subagent
Processes answered questions from plan.json and incorporates them into relevant tasks.
python-pro
Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.