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/detection-engineergit clone --depth 1 https://github.com/HermeticOrmus/LibreSecOps-Claude-CodeWhat 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 | $0.01073 |
| Opus 5 | $0.00000 | $0.00536 |
| Sonnet 5 | $0.00000 | $0.00215 |
| Haiku 4.5 | $0.00000 | $0.00107 |
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.
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.
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.
- 2d ago First seen · 94 lines · 0 tokens per session scan A 54bb095afa76
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.
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.
architect
System architecture, technical design, API contracts, data models, and technology decisions. Use for plan.md reviews and technical feasibility validation.
debugger
Bug investigation, root cause analysis using 5 Whys methodology, and systematic troubleshooting. Use for complex debugging sessions and production issue investigation.
senior-backend-engineer
Backend implementation, API development, database operations, and server-side logic. Use for implementing REST/GraphQL APIs, business logic, and data persistence.
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…
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…