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.
git 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/red-team-plan)<a href="https://agentmods.dev/commands/hermeticormus/libresecops-claude-code/red-team-plan"><img src="https://agentmods.dev/badge/commands/hermeticormus/libresecops-claude-code/red-team-plan/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/hermeticormus/libresecops-claude-code/red-team-plan"><img src="https://agentmods.dev/badge/commands/hermeticormus/libresecops-claude-code/red-team-plan.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00034 | $0.01082 |
| Opus 5.5 | $0.00014 | $0.00433 |
| Sonnet 5.5 | $0.00007 | $0.00216 |
| Haiku 4.5 | $0.00003 | $0.00108 |
Grade A, and why
red-team-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 12d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/red-team-plan
Create a structured adversary simulation plan with threat scenario, scope, rules of engagement, and phased operation design.
Trigger
Use when you need to:
- Plan a red team engagement for authorized testing
- Structure an adversary simulation exercise
- Define rules of engagement and scope for an upcoming test
- Design a purple team exercise with detection validation points
- Prepare a red team proposal for stakeholder approval
PREREQUISITE: Written authorization from the system owner must be in place or in progress. This command produces a plan document, not an attack.
Input
- Required: Target organization description (industry, size, technology stack, threat landscape)
- Required: Objective of the engagement (test detection, test response, validate controls, compliance requirement)
- Optional: Specific threat actor to emulate (e.g., "APT29-like scenario" or "ransomware group TTPs")
- Optional: Known constraints (off-limits systems, testing windows, budget)
- Optional flag:
--purple-- design as a collaborative purple team exercise with built-in detection validation
Process
-
Threat Scenario Selection: Based on the organization's industry, geography, and technology stack, identify the most relevant threat scenario:
- Which threat actors target this type of organization?
- What are their known TTPs?
- What is their typical objective (data theft, ransomware, espionage, disruption)?
-
Scope Definition: Define the boundaries of the engagement:
- In-scope systems, networks, and applications
- Out-of-scope systems (production critical systems, third-party systems, etc.)
- Authorized access methods
- Prohibited actions (no data destruction, no customer data access, etc.)
-
Rules of Engagement: Establish operational boundaries:
- Testing windows (business hours, after hours, weekends)
- Notification requirements (who knows, who does not know)
- Emergency stop procedures
- Deconfliction (how to distinguish red team from real attacker)
- Evidence handling (screenshots, logs, accessed data)
- Legal review 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.
- 12d ago Changed · +5 lines · +34 tokens per session c200e126425d
- 1mo ago First seen · 115 lines · 0 tokens per session scan A e891f2591095
red-team-plan is a command published in the GitHub repository HermeticOrmus/LibreSecOps-Claude-Code (4 stars, last pushed 9d ago), licensed MIT. It adds 34 tokens to every session and 1,082 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
Other commands, from other repositories
verify
An independent recheck of a security assessment report that derives conclusions from its own evidence instead of accepting the original findings.
corporate-launcher
Build a secure, branded, organization-specific launcher around an AI coding CLI (Claude Code, Codex CLI, Gemini CLI, Cursor, or Cline) so the user can.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.