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/vuln-reportgit 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/vuln-report)<a href="https://agentmods.dev/commands/hermeticormus/libresecops-claude-code/vuln-report"><img src="https://agentmods.dev/badge/commands/hermeticormus/libresecops-claude-code/vuln-report.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
vuln-report 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 5d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/vuln-report
Write a professional vulnerability report for bug bounty platform submission with clear reproduction steps, accurate severity assessment, and impact analysis.
Trigger
Use when you have confirmed a vulnerability and need to write a clear, professional report for submission. Also useful for:
- Reviewing and improving a draft report before submission
- Escalating a finding by demonstrating higher impact
- Writing a retest report after a fix has been deployed
- Documenting a vulnerability chain combining multiple findings
Input
- Vulnerability type: What class of vulnerability (XSS, IDOR, SSRF, SQLi, etc.)
- Affected asset: Exact URL, endpoint, or application component
- Description: What you found and how it works
- Reproduction steps: How you triggered the vulnerability
- Evidence: HTTP requests/responses, screenshots, PoC code
- Impact assessment: What an attacker could achieve
- Program context: Which bug bounty program, any relevant program-specific information
- Severity estimate: Your initial assessment of severity
Process
-
Title crafting -- Write a specific, descriptive title that communicates the vulnerability type, location, and impact in one line. Examples:
- Good: "Stored XSS via SVG upload in profile avatar allows session hijacking on app.example.com"
- Bad: "XSS found"
- Good: "IDOR in /api/v2/users/{id}/documents allows any authenticated user to download other users' documents"
- Bad: "Authorization bypass"
-
Summary writing -- 2-3 sentences covering: what the vulnerability is, where it exists, and the maximum impact. This is what the triage analyst reads first.
-
Reproduction steps -- Write exact, numbered steps that work on the first attempt:
- Start with prerequisites (account type, browser, extensions needed)
- Every step must be specific: exact URLs, exact input values, exact clicks
- Include the expected vs actual result
- Provide raw HTTP requests for precision
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.
- 5d ago First seen · 139 lines · 0 tokens per session scan A 3fd3892df251
vuln-report 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.run
Run the full AOD lifecycle orchestrator — chains all 6 stages (Discover → Define → Plan → Build → Deliver → Document) with session-resilient state and governance gates at every boundary.
aod.blueprint
Unified project setup & story generation — auto-detects new vs existing projects.
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.