hunt-hypothesis

hunt-hypothesis is a command for coding agents from HermeticOrmus/LibreSecOps-Claude-Code. It costs 0 tokens per session (902 once invoked), scanned A, original, MIT.

A command that creates a structured threat-hunting hypothesis for investigating possible attacker behavior. Threat hunting is the proactive search for signs of attacks in an organisation’s systems.

In plain words
What is it for?
Use it to plan hunts for tactics such as credential theft, lateral movement, persistence, or data exfiltration, optionally including SIEM queries or a step-by-step playbook.
Why use it?
It turns a broad concern, threat-intelligence report, detection gap, or ATT&CK technique into a testable investigation with suggested data sources and analysis steps.

Command

Install

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.

agentmods
npx agentmods add commands/hermeticormus/libresecops-claude-code/hunt-hypothesis
Clone the repo
git clone --depth 1 https://github.com/HermeticOrmus/LibreSecOps-Claude-Code

Wrote 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.

agentmods badge for hunt-hypothesis

README.md
[![agentmods](https://agentmods.dev/badge/commands/hermeticormus/libresecops-claude-code/hunt-hypothesis.svg)](https://agentmods.dev/commands/hermeticormus/libresecops-claude-code/hunt-hypothesis)
Your own site
<a href="https://agentmods.dev/commands/hermeticormus/libresecops-claude-code/hunt-hypothesis"><img src="https://agentmods.dev/badge/commands/hermeticormus/libresecops-claude-code/hunt-hypothesis.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 902 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00902
Opus 5 $0.00000 $0.00451
Sonnet 5 $0.00000 $0.00180
Haiku 4.5 $0.00000 $0.00090

Measured 4d ago against content hash f042df9f0e5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hunt-hypothesis 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 4d 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.

plugins/blue-team-detection/commands/hunt-hypothesis.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/hunt-hypothesis

Generate a structured threat hunting hypothesis with data sources, analysis approach, and expected indicators.

Trigger

Use when you need to:

  • Start a threat hunt and need a structured hypothesis
  • Investigate a specific ATT&CK technique proactively
  • Follow up on threat intelligence with a targeted hunt
  • Explore a detection gap identified during a red team exercise
  • Conduct a periodic hunt against common adversary behaviors

Input

  • Required: One of the following:
    • ATT&CK tactic or technique (e.g., credential-access, T1003.001)
    • Threat intelligence indicator or report to investigate
    • Detection gap description (e.g., "we have no detection for DNS tunneling")
    • Broad category (e.g., "lateral-movement", "persistence", "exfiltration")
  • Optional: Available data sources (SIEM platform, log types collected, EDR product)
  • Optional flag: --queries -- include ready-to-run SIEM queries
  • Optional flag: --playbook -- generate a full hunt playbook with step-by-step instructions

Process

  1. Hypothesis Formulation: Construct a testable hypothesis:

    • Based on the input, what specific adversary behavior are we looking for?
    • What would evidence of this behavior look like in our telemetry?
    • What is the null hypothesis (expected benign baseline)?
  2. Scope Definition: Define the hunt boundaries:

    • Time window (last 7 days, 30 days, 90 days)
    • Systems in scope (all endpoints, servers only, specific segments)
    • Data sources to query
  3. Data Source Mapping: Identify the specific data sources needed:

    • Which log types contain the relevant telemetry?
    • What fields are we analyzing?
    • Are there data gaps that limit the hunt?
  4. Analysis Approach: Design the analytical methodology:

    • Statistical: Frequency analysis, baseline deviation, rare value identification
    • Pattern matching: Known indicators, behavioral signatures
    • Temporal: Time-series analysis, beaconing detection, periodicity analysis
    • Relational: Process tree analysis, network graph analysis, user-entity mapping

Read the full file on GitHub · 114 lines

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.

  1. 4d ago First seen · 114 lines · 0 tokens per session scan A f042df9f0e5d

Subscribe to this mod's changes

hunt-hypothesis is a command 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 902 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 2026-08-31.