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/paulduvall/ai-development-patterns/security-reviewgit clone --depth 1 https://github.com/PaulDuvall/ai-development-patternsWhat 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 | $0.00009 | $0.01089 |
| Opus 5 | $0.00005 | $0.00544 |
| Sonnet 5 | $0.00002 | $0.00218 |
| Haiku 4.5 | $0.00001 | $0.00109 |
Grade A, and why
security-review 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Review
You are helping a developer identify security vulnerabilities in code changes. Perform multi-layer security analysis covering secrets, dependencies, authentication, input validation, and configuration security. Provide actionable remediation with specific code examples.
Usage
/security-review # Review recent changes
/security-review --full # Full codebase scan
/security-review --secrets # Focus on secret detection
/security-review --deps # Focus on dependencies
/security-review --config # Focus on configuration
Implementation
1. Secret Detection
Scan for hardcoded sensitive data:
API Keys and Tokens
- AWS keys (AKIA*, ASIA*)
- GitHub tokens (ghp_, gho_)
- Stripe keys (sk_live_, pk_live_)
- Generic patterns (api_key=, apiKey:, API_TOKEN)
Credentials
- Hardcoded passwords (password=, pwd=)
- Database connection strings with passwords
- Private keys (BEGIN PRIVATE KEY, BEGIN RSA PRIVATE KEY)
- Certificate files (.pem, .key, .p12)
Environment Variables
- Check for proper usage:
process.env.API_KEY,os.getenv('DB_PASSWORD') - Verify credentials are not committed
- Identify credential files (.env, secrets.json, config/credentials.yml)
2. Vulnerability Analysis
Dependency Vulnerabilities
- Check dependencies against CVE databases
- Identify outdated packages with known vulnerabilities
- Assess severity (CRITICAL/HIGH/MEDIUM/LOW)
- Suggest specific version upgrades
Authentication & Authorization
- Verify authentication on all protected endpoints
- Check for authorization bypass vulnerabilities
- Review session management (token expiration, refresh logic)
- Identify missing authentication checks
Input Validation
- Check for SQL injection vulnerabilities
- Identify XSS (Cross-Site Scripting) risks
- Verify input sanitization for user data
- Check file upload validation (file type, size, content)
3. Configuration Security
Network Security
- Verify HTTPS enforcement (no HTTP fallback)
- Check TLS version (TLS 1.2+ required)
- Validate certificate configuration
- Review redirect policies
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 · 168 lines · 9 tokens per session scan A 008adc8bc088
security-review is a command published in the GitHub repository PaulDuvall/ai-development-patterns (645 stars, last pushed 3d ago), licensed MIT. It adds 9 tokens to every session and 1,089 once invoked, about $0.0000 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 2026-08-30.
Other commands, from other repositories
paul:help
Show available PAUL commands and usage guide.
paul:handoff
Generate comprehensive session handoff document.
paul:research-phase
Research unknowns for a phase using subagents.
paul:plan-fix
Plan fixes for UAT issues from verify.
paul:progress
Smart status with routing - suggests ONE next action.
config
Manage PAUL project configuration and integrations. Create or update .paul/config.md at any point in the project lifecycle.