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/dachivadachkoria/claude-code-starter-kit/security-checkgit clone --depth 1 https://github.com/dachivadachkoria/claude-code-starter-kitWrote 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/dachivadachkoria/claude-code-starter-kit/security-check)<a href="https://agentmods.dev/commands/dachivadachkoria/claude-code-starter-kit/security-check"><img src="https://agentmods.dev/badge/commands/dachivadachkoria/claude-code-starter-kit/security-check.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 | $0.00011 | $0.01021 |
| Opus 5 | $0.00005 | $0.00511 |
| Sonnet 5 | $0.00002 | $0.00204 |
| Haiku 4.5 | $0.00001 | $0.00102 |
Grade A, and why
security-check 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 4d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- Command injection (os.system, exec, eval) How it starts
The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Vulnerability Scanner
Perform security audit on: $ARGUMENTS (default: entire project)
Scan Categories
1. Dependency Vulnerabilities
Python:
pip-audit --desc 2>/dev/null || pip install pip-audit && pip-audit --desc
safety check 2>/dev/null || true
JavaScript:
npm audit --json
npx audit-ci --moderate
Go:
govulncheck ./...
2. Code Security Issues
Scan for these patterns:
🔴 Critical
- Hardcoded secrets/API keys
- SQL injection vulnerabilities
- Command injection (os.system, exec, eval)
- Path traversal (../ in file operations)
- Insecure deserialization
- XXE vulnerabilities
🟠 High
- Missing input validation
- Insecure cryptography (MD5, SHA1 for passwords)
- Sensitive data in logs
- Missing authentication checks
- CORS misconfiguration
- Open redirects
🟡 Medium
- Missing rate limiting
- Verbose error messages
- Missing security headers
- Insecure random number generation
- Session fixation risks
🟢 Low
- Debug mode enabled
- Unnecessary dependencies
- Outdated but non-vulnerable packages
3. Secret Detection
Scan for exposed secrets:
# Check for common secret patterns
grep -rn "password\s*=" --include="*.py" --include="*.js" --include="*.go" .
grep -rn "api_key\s*=" --include="*.py" --include="*.js" --include="*.go" .
grep -rn "secret\s*=" --include="*.py" --include="*.js" --include="*.go" .
Patterns to detect:
- AWS access keys:
AKIA[0-9A-Z]{16} - GitHub tokens:
ghp_[a-zA-Z0-9]{36} - Generic API keys:
[aA][pP][iI]_?[kK][eE][yY].*['\"][a-zA-Z0-9]{20,}['\"] - Private keys:
-----BEGIN (RSA|EC|OPENSSH) PRIVATE KEY----- - JWT tokens:
eyJ[a-zA-Z0-9_-]*\.eyJ[a-zA-Z0-9_-]*\.[a-zA-Z0-9_-]*
4. Configuration Security
Check:
.envfiles not in.gitignore- Debug/development settings in production configs
- Default credentials
- Overly permissive CORS
- Missing HTTPS enforcement
Output Report
🛡️ Security Scan Report
══════════════════════════════════════════════════════════
🔴 CRITICAL (2)
───────────────
1. SQL Injection - src/db/queries.py:45
Issue: User input directly in SQL query
Fix: Use parameterized queries
2. Hardcoded Secret - src/config.py:12
Issue: API key exposed in source code
Fix: Move to environment variable
🟠 HIGH (3)
───────────────
1. Missing Auth Check - src/api/admin.py:23
Issue: Admin endpoint lacks authentication
Fix: Add @require_auth decorator
[... more items ...]
📦 Dependency Issues (5)
───────────────
- requests 2.25.0 → 2.31.0 (CVE-2023-32681)
- lodash 4.17.20 → 4.17.21 (Prototype pollution)
📊 Summary
───────────────
Critical: 2 | High: 3 | Medium: 5 | Low: 8
Dependencies: 5 vulnerable
🔧 Auto-fixable: 6 issues
Run /security-fix to apply safe fixes
══════════════════════════════════════════════════════════
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.
- 4d ago First seen · 150 lines · 11 tokens per session scan A cb7ddf453e22
security-check is a command published in the GitHub repository dachivadachkoria/claude-code-starter-kit (4 stars, last pushed 5mo ago), licensed MIT. It adds 11 tokens to every session and 1,021 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
sdlc-cycle
이슈/기획서 기준 SDLC 한 사이클(이슈→개발→테스트→검증→PR/MR)을 사람 개입 없이 자동 실행.
knowledge-graph
AGENTS.md 생태계(rules·memory·agents·skills·commands·workflows)의 연결 구조를 1장의 대시보드로 뽑는다. 온보딩·문서 정합성 점검용.
fix-issue
이슈 #$ARGUMENTS 를 처리한다(이슈 우선 워크플로).
README
반복 작업을 /이름 으로 호출. 파일명 = 커맨드 이름(fix-issue.md → /fix-issue). frontmatter name/argument-hint, 본문에 프롬프트. $ARGUMENTS 로 인자 수신.
sonar
SonarQube 정적분석 실행 및 결과 조회. 코드 품질·보안 핫스팟·커버리지 확인 시 사용.
tailtest-hunt
Run an adversarial pass on $ARGUMENTS -- explicitly try to break the source code.