detection-rule

detection-rule is a command for coding agents from HermeticOrmus/LibreSecOps-Claude-Code. It costs 0 tokens per session (794 once invoked), scanned A, original, MIT.

A command for creating an automated security detection rule for attacker behavior. It can describe the rule in Sigma, a tool-independent detection format, and translate it for selected security monitoring systems.

In plain words
What is it for?
It helps create rules from an ATT&CK technique, threat description, log sample, penetration-test finding, or CVE exploitation pattern, with optional SIEM, YARA, and validation output.
Why use it?
A manual investigation does not automatically alert you the next time the same behavior occurs. This turns a known threat pattern or hunting result into a repeatable detection.

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/detection-rule
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 detection-rule

README.md
[![agentmods](https://agentmods.dev/badge/commands/hermeticormus/libresecops-claude-code/detection-rule.svg)](https://agentmods.dev/commands/hermeticormus/libresecops-claude-code/detection-rule)
Your own site
<a href="https://agentmods.dev/commands/hermeticormus/libresecops-claude-code/detection-rule"><img src="https://agentmods.dev/badge/commands/hermeticormus/libresecops-claude-code/detection-rule.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 794 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 $0.00794
Opus 5 $0.00000 $0.00397
Sonnet 5 $0.00000 $0.00159
Haiku 4.5 $0.00000 $0.00079

Measured 3d ago against content hash 8ddc839a43e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

detection-rule 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.

plugins/blue-team-detection/commands/detection-rule.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/detection-rule

Create a detection rule for a specific ATT&CK technique or threat behavior, in Sigma format with SIEM-specific translations.

Trigger

Use when you need to:

  • Build a detection rule for a specific ATT&CK technique
  • Detect a specific adversary behavior observed in threat intelligence
  • Create a rule for a finding from a red team exercise or penetration test
  • Add detection for a specific CVE exploitation pattern
  • Convert a hunting query into an automated detection

Input

  • Required: One of the following:
    • ATT&CK technique ID (e.g., T1059.001, T1003.001)
    • Description of the behavior to detect (e.g., "detect PowerShell download cradle execution")
    • Log sample showing the malicious activity
  • Optional flag: --siem [splunk|elastic|sentinel|qradar] -- include SIEM-specific translation
  • Optional flag: --yara -- generate a YARA rule instead of (or in addition to) Sigma
  • Optional flag: --test -- include Atomic Red Team test command for validation

Process

  1. Technique Analysis: Understand the ATT&CK technique -- what the adversary does, what telemetry it generates, and what the detection surface looks like.

  2. Data Source Identification: Determine the required data sources:

    • Windows Event IDs (Security, Sysmon, PowerShell, etc.)
    • Linux log sources (auditd, syslog, journald)
    • Network data (DNS, HTTP, NetFlow)
    • Cloud audit logs (CloudTrail, Cloud Audit Logs, Azure Activity Log)
  3. Detection Logic Design: Build the detection logic:

    • Selection criteria: What fields and values identify the malicious behavior?
    • Filter conditions: What legitimate activity looks similar and should be excluded?
    • Aggregation: Does the detection need counting, grouping, or time windows?
    • Correlation: Does the detection need multiple events correlated together?
  4. False Positive Assessment: Identify known benign activities that will trigger the rule:

    • Administrative tools that produce similar telemetry
    • Legitimate automation that matches the pattern
    • System processes that mimic adversary behavior

Read the full file on GitHub · 102 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. 3d ago First seen · 102 lines · 0 tokens per session scan A 8ddc839a43e9

Subscribe to this mod's changes

detection-rule 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 794 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.