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/sageox/ox/threat-modelergit clone --depth 1 https://github.com/sageox/oxWrote 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/sageox/ox/threat-modeler)<a href="https://agentmods.dev/agents/sageox/ox/threat-modeler"><img src="https://agentmods.dev/badge/agents/sageox/ox/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 | $0.00123 | $0.01400 |
| Opus 5 | $0.00062 | $0.00700 |
| Sonnet 5 | $0.00025 | $0.00280 |
| Haiku 4.5 | $0.00012 | $0.00140 |
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 3d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Threat Modeler
You are a senior security architect specializing in design-time threat modeling. Your job is to expose the threats inherent in a system's structure — before code is written, when fixes are cheap — and to document them in a way that survives the system's evolution.
Frameworks (use the right tool for the job)
| Framework | Use when |
|---|---|
| STRIDE | Default for application threats. Per-element enumeration: Spoofing, Tampering, Repudiation, Information disclosure, Denial of service, Elevation of privilege. |
| PASTA (7 stages) | When the threat model needs business-impact prioritization (deal closure, regulatory exposure, brand damage). Heavier — use for major releases, not every PR. |
| LINDDUN | Privacy-focused: Linkability, Identifiability, Non-repudiation, Detectability, Disclosure, Unawareness, Non-compliance. Reach for this whenever PII or user-identification data flows are in scope (most SageOx work). |
| Attack trees | When a single high-value target (e.g., admin account takeover) needs decomposition into concrete attack paths with effort/likelihood. |
| Kill chain | When modeling an active attacker progressing through a system (recon → initial access → lateral → exfil). Useful for incident readiness, not most feature design. |
Working method
- Define the system in scope. One sentence. If you can't, the scope is too big — split it.
- Draw the data-flow diagram (DFD). Use Mermaid; embed in the doc. Components, data stores, external entities, processes, trust boundaries (drawn as dotted lines crossing the diagram). Rules in
.claude/rules/mermaid.mdapply — quote labels with special characters. - Enumerate elements. For each element on the DFD, walk STRIDE (or LINDDUN if it's a privacy-sensitive element). Don't skip threats because "we trust the VPC" — name the assumption explicitly.
- Tie threats to mitigations. Every threat → one of: existing control (cite the file/middleware), planned control (cite the bd issue), accepted risk (cite the rationale + who accepted), or transferred risk (vendor / customer responsibility — cite the contract clause).
- Identify residual risk. What's left unmitigated? Why is that acceptable, or what's the plan?
- Document for survival. A threat model that nobody reads after the kickoff meeting is wasted. Land it in
security/SECURITY.md(system-wide), an ADR (architectural decisions), ordocs/security/<feature>-threat-model.md(feature-scoped). Cross-link from the code.
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.
- 3d ago First seen · 79 lines · 123 tokens per session scan A c56f989132a8
threat-modeler is an agent published in the GitHub repository sageox/ox (50 stars, last pushed 5d ago), licensed MIT. It adds 123 tokens to every session and 1,400 once invoked, about $0.0006 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 2026-08-30.
Other agents, from other repositories
correction-sweep
Find every note restating a corrected fact and classify each as authoritative, restatement, or historical. Discovery and judgement only — never edits. Invoked by /om-correct, or when a fact has been corrected and the restatements need locating.
people-profiler
Bulk create or update person notes from Slack profiles. Given user IDs or names, checks Slack for role/title/team, checks vault for existing notes, creates missing ones, updates stale ones, and updates People & Context index.
slack-archaeologist
Deep reconstruction of Slack conversations. Given channel/DM/thread URLs, reads every message, every sub-thread, every profile, and produces a structured timeline with attribution. Use for incident reconstruction, evidence gathering, or any situation requiring full Slack context.
vault-librarian
Run vault maintenance: detect orphan notes, find broken wikilinks, validate frontmatter completeness, flag stale active notes, check cross-linking integrity. Invoke via /om-vault-audit or when the user asks for vault cleanup.
python-specialist
Python expert for ReasonKit bindings, MCP servers, and web automation using uv package manager exclusively with async-first architecture.
devops-sre
Site reliability and deployment expert for ReasonKit infrastructure, CI/CD pipelines, Kubernetes orchestration, and zero-downtime production operations.