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/Kin9Zeus/senior-engineer-skillsWrote 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/kin9zeus/senior-engineer-skills/snr-threatmodel)<a href="https://agentmods.dev/commands/kin9zeus/senior-engineer-skills/snr-threatmodel"><img src="https://agentmods.dev/badge/commands/kin9zeus/senior-engineer-skills/snr-threatmodel/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/kin9zeus/senior-engineer-skills/snr-threatmodel"><img src="https://agentmods.dev/badge/commands/kin9zeus/senior-engineer-skills/snr-threatmodel.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 | $0.00031 | $0.00380 |
| Opus 5.5 | $0.00012 | $0.00152 |
| Sonnet 5.5 | $0.00006 | $0.00076 |
| Haiku 4.5 | $0.00003 | $0.00038 |
Grade A, and why
snr-threatmodel 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 2d 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.
What it actually says
Threat Model
Subject: $ARGUMENTS
Load security-hardening and follow references/threat-modelling.md. For AI
features also load ai-security; for infrastructure, cloud-security.
The four questions
- What are we building? Sketch the data flow: actors, processes, data stores, external services, and the trust boundaries between them. Mark where untrusted input enters, where secrets live, and where data leaves.
- What can go wrong? STRIDE at each boundary — Spoofing, Tampering, Repudiation, Information disclosure, Denial of service, Elevation of privilege. Add the platform case: what if our host, CI or secrets store is breached?
- What are we doing about it? One control per threat, with an owner. Prefer preventive controls; add detective ones (alerts) where prevention is partial.
- Did we do a good job? One test per control — an automated test, a configuration check or a drill. A control with no test is a hope.
Output
A table: # · Boundary · Threat (STRIDE) · Impact · Likelihood · Control · Test · Owner,
ordered by risk, followed by the residual risks the user must explicitly accept
and What I could not verify. Save it beside the code (e.g. docs/threat-model.md)
so it is reviewed when the design changes.
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.
- 2d ago First seen · 32 lines · 31 tokens per session scan A de1ac4f3405f
snr-threatmodel is a command published in the GitHub repository Kin9Zeus/senior-engineer-skills (3 stars, last pushed 2d ago), licensed MIT. It adds 31 tokens to every session and 380 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 2026-10-24.
Other commands, from other repositories
gate
Run every objective gate this project can prove and report the real N/N. Use before claiming any screen or component is done.
compose
Compose a document from a reading pattern when no canonical type fits, as Markdown in the user's repository. Use when invoked as /document-design-system:compose. Produce designed HTML or PDF only when asked.
adr
Write an architecture decision record as Markdown in the user's repository. Use when invoked as /document-design-system:adr. Produce designed HTML or PDF only when asked.
test-report
Write a point-in-time test report as Markdown in the user's repository. Use when invoked as /document-design-system:test-report. Produce designed HTML or PDF only when asked.
change-request
Write a change request as Markdown in the user's repository. Produce designed HTML or PDF only when asked.
estimate
Write a basis of estimate as Markdown in the user's repository. Produce designed HTML or PDF only when asked.