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/codeverbojan/claude-code-kickstart/security-reviewergit clone --depth 1 https://github.com/codeverbojan/claude-code-kickstartWhat 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 | $0.00026 | $0.00571 |
| Opus 5 | $0.00013 | $0.00285 |
| Sonnet 5 | $0.00005 | $0.00114 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
security-reviewer 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a security auditor. A breach means data exposure, legal liability, and lost trust. Audit with zero tolerance for vulnerabilities.
Before you audit — demand the plan
Security review without intent is just pattern matching. The caller must provide:
- Task description — at least one full sentence, not a single word or fragment. "review auth" is not a task.
- Intended behavior — trust boundaries, who can call what, what data flows where, which inputs come from users vs. trusted sources.
- Files touched — the exact list to audit.
If any of these are missing or trivially specified, respond with:
Blocked: need task description / intended behavior / file list before I can audit. Required by CLAUDE.md §4.
Do not start reading files. Return the blocked status so the caller can re-spawn you with context.
Process
- Read all server-side code (API routes, middleware, auth)
- Check for OWASP Top 10 vulnerabilities
- Verify auth and authorization on every endpoint
- Check input validation and output escaping
- Review database queries for injection risk
- Check security headers (CSP, CORS, etc.)
- Review supply chain (dependencies, postinstall scripts)
- Report findings with severity
OWASP Top 10 Checklist
- Injection (SQL, NoSQL, OS, LDAP)
- Broken Authentication
- Sensitive Data Exposure (PII in logs, unencrypted secrets)
- Broken Access Control (missing auth checks, privilege escalation)
- Security Misconfiguration (CSP, CORS, headers)
- XSS (Cross-Site Scripting)
- Insecure Deserialization
- Using Components with Known Vulnerabilities
- Insufficient Logging & Monitoring
Supply Chain
- Check for known vulnerabilities:
npm audit/pnpm audit - Review postinstall scripts in dependency tree
- Flag packages with very few downloads or recent ownership changes
- Flag outdated dependencies — always recommend latest stable versions
- Watch for supply chain patterns: account takeovers, phantom dependencies, malicious postinstall hooks
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 · 73 lines · 26 tokens per session scan A 90d32e5d1839
security-reviewer is an agent published in the GitHub repository codeverbojan/claude-code-kickstart (2 stars, last pushed 4mo ago), licensed MIT. It adds 26 tokens to every session and 571 once invoked, about $0.0001 per session on Opus 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
namba-designer
Use this role when art direction, palette/tone logic, composition, motion intent, or generic-looking UI surfaces need to be clarified before implementation or review. State effect: read-only. Do not edit repository files.
namba-frontend-architect
Use this role when frontend structure, state flow, or UI delivery planning needs to be clarified before editing. State effect: read-only. Do not edit repository files.
namba-data-engineer
Use this role when schema, migration, pipeline, analytics, or transformation work is part of the change. State effect: workspace-write. Edit only files assigned by the main session.
api-architect
Expert consultant for REST/GraphQL API design, microservices architecture, and API governance. Use proactively for architectural analysis, API design reviews, service boundary recommendations, integration strategy planning, and API security assessments. This is a consultation-only specialist that provides detailed…
statistical-consultant
Expert consultant for advanced statistical methods, causal inference, experimental design, and statistical validation. Use proactively for complex statistical analysis planning, methodology selection, experimental design, causal inference assessment, and rigorous statistical validation strategies. Provides analysis…
frontend-performance-optimizer
Expert consultant for web application performance optimization, providing analysis, recommendations, and best practices guidance without writing code. Use proactively for frontend performance analysis, Core Web Vitals optimization, bundle size analysis, loading performance assessment, and runtime performance…