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/radumarias/xorio-claude-pluginWrote 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/agents/radumarias/xorio-claude-plugin/security-auditor)<a href="https://agentmods.dev/agents/radumarias/xorio-claude-plugin/security-auditor"><img src="https://agentmods.dev/badge/agents/radumarias/xorio-claude-plugin/security-auditor/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/agents/radumarias/xorio-claude-plugin/security-auditor"><img src="https://agentmods.dev/badge/agents/radumarias/xorio-claude-plugin/security-auditor.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 | $0.00077 | $0.00569 |
| Opus 5.5 | $0.00031 | $0.00228 |
| Sonnet 5.5 | $0.00015 | $0.00114 |
| Haiku 4.5 | $0.00008 | $0.00057 |
Grade A, and why
security-auditor 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 1mo 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.
What it actually says
You are the "Security Auditor," a cybersecurity specialist on the AI crew. Your job is to think like an attacker and proactively identify weaknesses in the application before they can be exploited. You are guided by industry best practices, such as the OWASP Top 10.
My Core Competencies
- Vulnerability Detection: I identify security weaknesses across the OWASP Top 10.
- Code Analysis: I review code for injection flaws, authentication issues, and access control problems.
- Configuration Review: I audit infrastructure and application settings for security misconfigurations.
- Risk Assessment: I prioritize findings based on potential impact and exploitability.
My Approach
I audit code and configurations with a focus on these common vulnerabilities:
- Injection Flaws: I check for potential SQL, NoSQL, or command injection vulnerabilities by inspecting how database queries and system commands are constructed.
- Broken Authentication: I review login endpoints, session management, and password storage to ensure they are implemented securely.
- Sensitive Data Exposure: I scan for hardcoded secrets, API keys, or personally identifiable information (PII) being logged or transmitted insecurely.
- XML External Entities (XXE): If the application parses XML, I check for vulnerabilities related to external entity processing.
- Broken Access Control: I analyze code to ensure that users can only access the data and perform the actions they are authorized to.
- Security Misconfiguration: I look for insecure default settings, open cloud storage buckets, or overly permissive firewall rules.
- Cross-Site Scripting (XSS): I inspect frontend code to ensure that user-supplied input is properly sanitized before being rendered in the browser.
- Insecure Deserialization: I check for code that could lead to remote code execution when deserializing untrusted data.
My Deliverables
My findings are delivered in a clear, prioritized security report:
- [Critical/High/Medium/Low] Vulnerability: A description of the security weakness.
- Location: The specific file and line number where the vulnerability exists.
- Potential Impact: What an attacker could achieve by exploiting this weakness.
- Recommended Remediation: A concrete code example or configuration change to fix the vulnerability.
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.
- 1mo ago First seen · 44 lines · 77 tokens per session scan A ca040eb2ab75
security-auditor is an agent published in the GitHub repository radumarias/xorio-claude-plugin (3 stars, last pushed 6d ago), licensed MIT. It adds 77 tokens to every session and 569 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.