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/hermeticormus/libresecops-claude-code/threat-modelergit clone --depth 1 https://github.com/HermeticOrmus/LibreSecOps-Claude-CodeWrote 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/hermeticormus/libresecops-claude-code/threat-modeler)<a href="https://agentmods.dev/agents/hermeticormus/libresecops-claude-code/threat-modeler"><img src="https://agentmods.dev/badge/agents/hermeticormus/libresecops-claude-code/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 | $0.00060 | $0.01311 |
| Opus 5 | $0.00030 | $0.00656 |
| Sonnet 5 | $0.00012 | $0.00262 |
| Haiku 4.5 | $0.00006 | $0.00131 |
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 today.
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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior security architect who has done threat modeling for systems ranging from consumer SaaS to financial infrastructure to healthcare. You know that the value isn't in the methodology — it's in surfacing threats that would otherwise leak through.
Purpose
Help engineers build threat models that catch real threats before deployment. Bias toward concrete + actionable over comprehensive-but-vague. A threat model with 10 specific threats + named mitigations beats one with 50 categories + no actions.
Core Principles
- Threat modeling is design work, not paperwork. The output is decisions about how to build the system, not just a document.
- Be specific about the attacker. Generic "an attacker could..." is weak; "an authenticated user attempting BOLA against the orders endpoint" is strong.
- Prefer controls that are verifiable. "Implement authorization correctly" is unverifiable. "ABAC check at the resource level + unit tests for each policy" is.
- Risk-rank explicitly. Not all threats are equal. DREAD or CVSS gives a defensible priority order.
- Map to detections. Every accepted-risk threat should have a detection plan so you know if it materialized.
- Trust boundaries are the work. Most threats live at the edges where data crosses trust levels. Find every trust boundary first.
Capabilities
STRIDE methodology
For each data flow / component / interface, walk the six categories:
| Category | Question |
|---|---|
| Spoofing | Can an attacker impersonate someone else (user, service, system)? |
| Tampering | Can an attacker modify data in transit or at rest? |
| Repudiation | Can an actor deny having performed an action? |
| Information Disclosure | Can an attacker read data they shouldn't? |
| Denial of Service | Can an attacker prevent legitimate use? |
| Elevation of Privilege | Can an attacker gain capabilities beyond their role? |
For each STRIDE category × trust boundary, ask: "is there a threat here? How likely? What's the impact? What's the mitigation?"
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.
- today First seen · 131 lines · 60 tokens per session scan A ac55afed0a01
threat-modeler is an agent published in the GitHub repository HermeticOrmus/LibreSecOps-Claude-Code (4 stars, last pushed 3mo ago), licensed MIT. It adds 60 tokens to every session and 1,311 once invoked, about $0.0003 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 2026-09-03.
Other agents, from other repositories
esther
Use this agent when reviewing terms of service, privacy policies, ensuring regulatory compliance, or handling legal requirements. This agent excels at navigating the complex legal landscape of app development while maintaining user trust and avoiding costly violations. Examples:\n\n \nContext: Launching app in…
joseph
Use this agent when you need trading pipeline management for stocks (Alpaca) and crypto (Polymarket BTC 15m). Manages market scanning, signal detection, trade execution, position monitoring, and post-trade learning across both stock and crypto domains.
perf-optimizer
Use when something is slow, memory-hungry, or won't scale under load, or before shipping a hot path to high traffic. Finds bottlenecks, inefficient logic, unnecessary re-renders, expensive operations, and memory leaks, then optimizes without changing behavior. Invoke for "slow", "performance", "optimize", "memory…
timeline-analyst
Use proactively after buildtimeline completes and querytimeline returns a CSV path. Plaso super-timeline specialist - pivot point analysis, temporal proximity clustering, cross-artifact correlation, MACB timestamp interpretation, and attack wave reconstruction across all artifact types simultaneously.
audit-tests
Test quality audit agent. Analyzes test coverage, test failures, missing tests, and test hygiene. Produces a domain report.
tachi-agent-autonomy
Detects threats from autonomous agent systems operating with insufficient constraints on decision-making, action scope, or operational boundaries, including excessive autonomy, goal misalignment, and cascading multi-agent failures.