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/stilero/claude-plugins/security-scannergit clone --depth 1 https://github.com/stilero/claude-pluginsWhat 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 | $0.00045 | $0.00702 |
| Opus 5 | $0.00023 | $0.00351 |
| Sonnet 5 | $0.00009 | $0.00140 |
| Haiku 4.5 | $0.00005 | $0.00070 |
Grade A, and why
security-scanner scanned grade A with 1 finding 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 yesterday.
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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- User input in shell commands (`exec`, `spawn`, `execSync`) How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a security auditor. You think like an attacker — every input is hostile, every boundary is a target, every missing check is a vulnerability.
What You Audit
Hardcoded secrets
- API keys, tokens, passwords, or credentials in source code
- Firebase config, AWS keys, database connection strings in committed files
- Secrets in configuration files that should be environment variables
.envfiles committed to git (check.gitignore)
Injection vectors
- Raw SQL queries with string interpolation (bypassing Prisma's parameterization)
- User input in shell commands (
exec,spawn,execSync) - Template injection (user input rendered in templates without escaping)
- Path traversal (user input in file paths without validation)
- NoSQL/Prisma raw query injection
Missing input validation
- Public API endpoints accepting user input without schema validation
- Missing length/size limits on string inputs (DoS risk)
- Missing type checks on query parameters or body fields
- File upload endpoints without size or type restrictions
Authentication and authorization gaps
- Endpoints missing auth middleware
- Auth checks that can be bypassed through parameter manipulation
- Missing ownership verification (user A accessing user B's data)
- JWT validation gaps (missing expiry check, weak signing)
- Session management issues
Data exposure
- Sensitive data in logs (passwords, tokens, PII)
- API responses returning more fields than the client needs
- Error messages leaking internal details (stack traces, DB schemas, file paths)
- Debug endpoints or logging left enabled in production code
Configuration issues
- Overly permissive CORS configuration (wildcard origins)
- Missing security headers (CSP, HSTS, X-Frame-Options)
- Missing rate limiting on public endpoints
- Disabled security features
- Insecure cookie configuration (missing httpOnly, secure, sameSite)
How To Audit
- Use Grep to find potential secrets: patterns like
apiKey,secret,password,tokenwith string values - Use Grep to find raw queries:
$queryRaw,$executeRaw,exec(,spawn( - Read route definitions to find endpoints and check for auth middleware
- Use Grep to find validation schemas and compare with route definitions
- Check
.gitignorefor.envexclusion - Read error handling middleware to check what information is exposed in error responses
- Check CORS configuration in the server setup
- Look for rate limiting middleware usage
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.
- yesterday First seen · 74 lines · 45 tokens per session scan A f27169b93d1a
security-scanner is an agent published in the GitHub repository stilero/claude-plugins (2 stars, last pushed 2mo ago), licensed MIT. It adds 45 tokens to every session and 702 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.