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 commands/hermeticormus/libresecops-claude-code/forensic-plangit 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/commands/hermeticormus/libresecops-claude-code/forensic-plan)<a href="https://agentmods.dev/commands/hermeticormus/libresecops-claude-code/forensic-plan"><img src="https://agentmods.dev/badge/commands/hermeticormus/libresecops-claude-code/forensic-plan.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 | $0.01155 |
| Opus 5 | $0.00000 | $0.00577 |
| Sonnet 5 | $0.00000 | $0.00231 |
| Haiku 4.5 | $0.00000 | $0.00115 |
Grade A, and why
forensic-plan 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.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/forensic-plan
Create a forensic investigation plan tailored to the incident type, defining evidence sources, collection priorities, and analysis approach.
Trigger
Use at the start of any forensic investigation to establish a structured plan before collecting evidence. Appropriate for:
- Active incident response requiring forensic analysis
- Post-incident investigation
- Insider threat investigation (with HR and legal authorization)
- Data breach assessment
- Malware impact analysis
- Compliance-driven forensic review
Input
- Required: Incident type or description (e.g., "ransomware on file server", "suspected data exfiltration", "compromised web server", "insider threat investigation")
- Required: Authorization status (who authorized the investigation)
- Optional: Known affected systems
- Optional: Incident timeline (when was it detected, suspected start time)
- Optional flag:
--live-- the system is still running (affects collection order) - Optional flag:
--legal-- investigation may lead to legal proceedings (stricter evidence handling)
Process
-
Scope Definition: Based on the incident type, define:
- What questions does this investigation need to answer?
- What systems are in scope?
- What time period is relevant?
- What legal or regulatory requirements apply?
-
Evidence Source Identification: Map all potential evidence sources:
- Volatile (collect first): RAM, running processes, network connections, logged-in users, clipboard contents, mounted file systems
- Semi-volatile: Temporary files, swap/page file, system logs on disk
- Non-volatile: Disk images, backup tapes, removable media, cloud storage
- External: SIEM logs, network flow data, authentication logs (Active Directory, IdP), cloud audit logs, email gateway logs
-
Collection Priority: Order evidence collection by:
- Volatility (most volatile first)
- Relevance to the investigation questions
- Risk of loss (evidence that may be overwritten or destroyed)
- Legal requirements (some jurisdictions require specific collection orders)
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.
- 4d ago First seen · 115 lines · 0 tokens per session scan A 29e509b04b78
forensic-plan 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 1,155 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 commands, from other repositories
tachi.architecture
Generate an architecture description for tachi threat modeling input.
aod.blueprint
Unified project setup & story generation — auto-detects new vs existing projects.
sicario.assess
Assess the repository against SicarioSpec guardrails.
baseline
Manage violation baselines for gradual adoption.
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.