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 fmind/dot --skill threat-modelgit clone --depth 1 https://github.com/fmind/dotWrote 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/fmind/dot/threat-model)<a href="https://agentmods.dev/skills/fmind/dot/threat-model"><img src="https://agentmods.dev/badge/skills/fmind/dot/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/skills/fmind/dot/threat-model"><img src="https://agentmods.dev/badge/skills/fmind/dot/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 | $0.00017 | $0.00708 |
| Opus 5.5 | $0.00007 | $0.00283 |
| Sonnet 5.5 | $0.00003 | $0.00142 |
| Haiku 4.5 | $0.00002 | $0.00071 |
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 12d 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 — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Threat Model
Identify the few plausible abuse paths that should change the design, plan, or verification strategy; code-security runs the scanners, whose output supports but never replaces attack-path reasoning, and incident-response handles a live breach.
Rules
- Model only what changes decisions: scope the system and the decision the model informs; map assets, actors, flows, and trust boundaries from evidence, then keep only abuse cases with a concrete path (attacker capability → entry point → missing control → asset impact). Drop category-only concerns.
- Default to read-only analysis: never probe live systems, run exploit code, access customer data, rotate credentials, or change security controls without explicit authorization.
- Ground the model in facts: never invent endpoints, attackers, compliance obligations, or exploitability; promote high-impact unknowns to verification tasks, not confirmed vulnerabilities.
- Respect intended autonomy: distinguish an actor's authorized capabilities from an attacker gaining them. Do not prescribe permission prompts or rewrite harness settings merely because execution is powerful (this workstation runs agents in bypass mode by choice). Hand agent, retrieval, and model abuse cases to ai-red-team with both the legitimate operation and the boundary the attacker must not cross.
- Prefer design over warnings: misuse-resistant types, secure defaults, least privilege, isolation, and fail-closed behavior beat rules every caller must remember.
- Feed delivery: report ranked abuse paths, existing and required controls with how each is verified, residual risks, and owner decisions; add required controls and tests to the plan or spec.
Documentation
- Upstream: the
codex-securityplugin inopenai/pluginsships a same-namethreat-model; preview it, never install it beside this skill (vendor-skill policy). - Companion skills: sops-secrets (secret design), system-prompts (prompt-injection boundaries for agents), skill-security-review (third-party skill supply chain), production-readiness (launch gate).
- Adapted from Trail of Bits sharp-edges, gstack CSO.
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.
- 12d ago Changed · -13 lines 2d9874b98608
- 14d ago Changed 4479d31a4946
- 15d ago Changed · -1 lines · -4 tokens per session cd1f5f8277c9
- 1mo ago Changed · +1 lines · -25 tokens per session 490d9470729f
- 1mo ago Changed · +2 lines 2b431b5abfd0
- 1mo ago First seen · 42 lines · 46 tokens per session scan A 1670b29428d6
threat-model is a skill published in the GitHub repository fmind/dot (12 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 708 once invoked, about $0.0001 per session on Opus 5.5. 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
dotfiles-bootstrap
Bootstrap a workstation with the dotfiles framework. Takes a GitHub user / owner+repo / explicit clone URL and runs dot init (which shells out to chezmoi) with the right safety prompts. Honors the active agent profile (ask / plan / apply / audit) so it defaults to dry-run in safer modes and full apply in apply.
vibe
Delegate a coding task to a cheap AI model (Mistral Vibe by default, but any provider Vibe knows about — DeepSeek, Gemini Flash, etc.) and supervise the result via git diff. Claude orchestrates, the cheap model codes. Claude consumes 500-1500 tokens per delegation regardless of how many file reads the delegate does…
go-stack
Build Go projects, libraries, CLIs, TUIs, web apps, or ADK agents with the standard package layout and pinned tooling.
python-stack
Build typed Python projects with uv, Ruff, ty, pytest, Litestar, and Typer. Use for packages, CLIs, web apps, tests, typing, or API verification.
hugo
Canonical Hugo static-site stack with the Hextra docs theme — Hugo Modules, mise tasks, dprint, lefthook, and GitHub Pages deploy. Use for documentation sites, project docs, and static websites.
k8s-local
Create and manage local Kubernetes clusters (k3d or kind) and deploy to them with kubectl, helm, helmfile, and skaffold. Use for local k8s cluster setup, dev loops, and debugging.