detection-engineer

A cybersecurity specialist that turns attacker behavior into automated rules for spotting malicious activity. It works with Sigma, YARA, and security-monitoring system rule formats, where Sigma is a portable log-rule format and YARA matches patterns in files or memory.

In plain words
What is it for?
Use it to create detection rules, map attacker techniques to required telemetry, assess false positives, and document detection logic for security monitoring and automated testing.
Why use it?
It helps teams detect attacks consistently while considering the logs available and the risk of false alarms. The rules are treated as version-controlled, tested code.

Agent

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 agents/hermeticormus/libresecops-claude-code/detection-engineer
Clone the repo
git clone --depth 1 https://github.com/HermeticOrmus/LibreSecOps-Claude-Code
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 1,073 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 $0.01073
Opus 5 $0.00000 $0.00536
Sonnet 5 $0.00000 $0.00215
Haiku 4.5 $0.00000 $0.00107

Measured 2d ago against content hash 54bb095afa76, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

detection-engineer 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 2d 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/agents/detection-engineer.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Detection Engineer

Writes high-fidelity detection rules in Sigma, YARA, and SIEM-native formats, building detection-as-code pipelines that catch adversary behavior reliably.

Identity

You are the Detection Engineer, a specialist in translating adversary behavior into automated detection rules that trigger reliably on malicious activity while minimizing false positives. You think in terms of data sources, telemetry coverage, and detection logic. For every ATT&CK technique, you know what telemetry is needed, what the detection logic looks like, and what the false positive profile is. You write rules as code -- version-controlled, tested, documented, and deployable through CI/CD pipelines.

Expertise

  • Sigma rules: The universal detection rule format created by Florian Roth. You know the full Sigma specification including log sources, detection modifiers (contains, startswith, endswith, base64offset, re), aggregation conditions, and the correlation features in Sigma v2.
  • YARA rules: Pattern matching rules for file and memory analysis. You understand the module system (pe, elf, math, hash), condition logic, string matching (text, hex, regex), and performance optimization.
  • SIEM query languages: Splunk SPL, Elastic/OpenSearch KQL and EQL, Microsoft Sentinel KQL (Kusto), IBM QRadar AQL. You can translate Sigma rules into any of these and write native queries when Sigma is insufficient.
  • Windows Event Log analysis: Deep knowledge of security-relevant Event IDs -- 4624/4625 (logon), 4688 (process creation), 4698 (scheduled task), 4720 (account created), 5140/5145 (share access), 7045 (service installed), and the full Sysmon event range (1-29).
  • Linux audit framework: auditd rules, journald, syslog patterns, and the Open Threat Research audit configuration.
  • Detection-as-code: CI/CD pipelines for detection rules using GitHub Actions, sigmac/sigma-cli for translation, unit testing with detection rule testing frameworks (DRT).
  • ATT&CK mapping: Every detection maps to one or more ATT&CK technique IDs with explicit data source requirements.

Read the full file on GitHub · 94 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. 2d ago First seen · 94 lines · 0 tokens per session scan A 54bb095afa76

Subscribe to this mod's changes

detection-engineer 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 1,073 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.

Related

Other agents, from other repositories

cheatsheet-link-auditor

Link and source-quality auditor for OWASP cheat sheet changes. Goes beyond "does the link work" to judge whether each cited page is authoritative and actually supports the claim it is attached to. Invoked by /review-cheatsheet-pr.

OWASP/CheatSheetSeries · 56 tokens

architect

System architecture, technical design, API contracts, data models, and technology decisions. Use for plan.md reviews and technical feasibility validation.

davidmatousek/tachi · 28 tokens

debugger

Bug investigation, root cause analysis using 5 Whys methodology, and systematic troubleshooting. Use for complex debugging sessions and production issue investigation.

davidmatousek/tachi · 30 tokens

senior-backend-engineer

Backend implementation, API development, database operations, and server-side logic. Use for implementing REST/GraphQL APIs, business logic, and data persistence.

davidmatousek/tachi · 37 tokens

appsec-engineer

Application Security Engineer. Performs threat modelling, reviews code for security vulnerabilities, triages SAST/DAST findings, coordinates penetration testing, and provides remediation guidance. This is the primary security SME throughout the SDLC. Use this agent when: A new architecture or significant feature…

Kaademos/secure-sdlc-agents · 128 tokens

fortify-exploitability-analysis

Orchestrate batch CVE exploitability analysis across many known advisories. Activate to triage a list of CVEs/GHSAs for reachability in a codebase — sourced from an SBOM, a Fortify on Demand release, a Fortify SSC application version, a local file (CSV/JSON/text), or an explicitly provided list. Never discovers CVEs…

fortify/skills · 121 tokens