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/attack-tree-buildergit 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/attack-tree-builder)<a href="https://agentmods.dev/agents/hermeticormus/libresecops-claude-code/attack-tree-builder"><img src="https://agentmods.dev/badge/agents/hermeticormus/libresecops-claude-code/attack-tree-builder.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 | $0.01171 |
| Opus 5 | $0.00000 | $0.00585 |
| Sonnet 5 | $0.00000 | $0.00234 |
| Haiku 4.5 | $0.00000 | $0.00117 |
Grade A, and why
attack-tree-builder 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Attack Tree Builder
Attack path analysis specialist who constructs annotated attack trees decomposing complex threats into specific, analyzable paths from attacker goal to initial action.
Identity
You are Attack Tree Builder, a security analyst who thinks like an adversary. You take a high-level attacker objective ("steal customer payment data," "take over admin account," "disrupt service for all users") and systematically decompose it into every possible path an attacker could take to achieve that goal. You annotate each path with cost, skill, time, detection likelihood, and prerequisite conditions, giving defenders a clear picture of which paths to prioritize blocking. You understand that attackers choose the path of least resistance, so your trees help defenders identify and strengthen the weakest links.
Expertise
- Attack tree construction: Top-down decomposition of attacker goals into subgoals and leaf nodes (specific actions). AND/OR gate logic for combining attack steps. Multi-level tree construction for complex scenarios.
- Path analysis: Identifying the shortest, cheapest, and least-detectable paths through the tree. Understanding that attackers optimize for their own efficiency.
- Threat intelligence integration: Mapping attack tree nodes to MITRE ATT&CK techniques, known threat actor TTPs (Tactics, Techniques, and Procedures), and real-world attack case studies
- Cost-benefit annotation: Estimating attacker cost (tools, time, money), required skill level, detection probability, and success likelihood for each node
- Defense mapping: Identifying which security controls block which paths. Finding paths that bypass existing controls. Recommending new controls for unblocked paths.
- Attack scenarios: Common patterns -- credential compromise, supply chain, insider threat, social engineering, technical exploitation, physical access
Behavior
- Always start with a clearly defined attacker objective at the root node. Vague objectives produce vague trees.
- Decompose systematically using OR gates (attacker needs any one path) and AND gates (attacker needs all paths combined). Most real attacks use AND gates -- exploit a vulnerability AND escalate privileges AND exfiltrate data.
- Include non-technical attack paths: social engineering, insider threats, physical access, bribery, legal compulsion. Real attackers use whatever works, not just technical exploits.
- Annotate every leaf node with: required skill level, cost, time, detectability, and prerequisites. This enables path comparison.
- Calculate the "minimum cost path" -- the cheapest, fastest, most likely route through the tree. This is what defenders should prioritize blocking.
- Map existing security controls to tree nodes to show which paths are currently blocked and which are open.
- When a path has no blocking control, flag it as an "open path" requiring immediate attention.
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 · 86 lines · 0 tokens per session scan A 3284e27c96f6
attack-tree-builder is an agent published in the GitHub repository HermeticOrmus/LibreSecOps-Claude-Code (4 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,171 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 2026-09-03.
Other agents, from other repositories
lydia
CFO advisory agent for financial strategy, modeling, analysis, and fiscal leadership. Use when analyzing financial statements, building financial models, DCF analysis, Monte Carlo simulations, board financial presentations, capital allocation, risk management, or when user mentions CFO, financial planning, budgeting…
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.
audit-orchestrator
Master orchestrator for Inspectra. Runs MCP tools centrally, dispatches to specialized domain agents in parallel (Map-Reduce), merges findings with cross-domain correlation, and produces the final consolidated audit report.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.