security-check

security-check is a command for Claude Code from TheDecipherist/claude-code-mastery-project-starter-kit. It costs 17 tokens per session (715 once invoked), scanned A, original, MIT.

A command that scans a software project for exposed secrets, unsafe patterns, sensitive tracked files, and missing entries in the .gitignore file.

In plain words
What is it for?
Use it for a project security review covering code, credential URLs, environment files, SSH keys, dependency folders, logs, and ignore rules.
Why use it?
It helps catch passwords, API keys, private credentials, and generated or local files before they are committed to Git, a system for tracking code changes.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/thedecipherist/claude-code-mastery-project-starter-kit/security-check
Clone the repo
git clone --depth 1 https://github.com/TheDecipherist/claude-code-mastery-project-starter-kit

Made for: Claude Code.

Wrote 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.

agentmods badge for security-check

README.md
[![agentmods](https://agentmods.dev/badge/commands/thedecipherist/claude-code-mastery-project-starter-kit/security-check.svg)](https://agentmods.dev/commands/thedecipherist/claude-code-mastery-project-starter-kit/security-check)
Your own site
<a href="https://agentmods.dev/commands/thedecipherist/claude-code-mastery-project-starter-kit/security-check"><img src="https://agentmods.dev/badge/commands/thedecipherist/claude-code-mastery-project-starter-kit/security-check.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 715 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00017 $0.00715
Opus 5 $0.00009 $0.00358
Sonnet 5 $0.00003 $0.00143
Haiku 4.5 $0.00002 $0.00072

Measured 4d ago against content hash 05079c7eb511, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-check 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 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.

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.

.claude/commands/security-check.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Check

Scan this project for security vulnerabilities.

Checks to Perform

1. Secrets in Code

# Search for common secret patterns in tracked files
git grep -n -E '(api[_-]?key|secret[_-]?key|password|token)\s*[:=]\s*["\x27][A-Za-z0-9+/=_-]{8,}' -- ':!*.lock' ':!node_modules' 2>/dev/null || echo "No secrets found in code"

# Search for AWS keys
git grep -n 'AKIA[0-9A-Z]\{16\}' 2>/dev/null || echo "No AWS keys found"

# Search for hardcoded URLs with credentials
git grep -n -E '(https?://[^:]+:[^@]+@)' 2>/dev/null || echo "No credential URLs found"

2. .gitignore Coverage

Verify these entries exist in .gitignore:

  • .env
  • .env.*
  • .env.local
  • node_modules/
  • dist/
  • CLAUDE.local.md
  • *.log

3. Sensitive Files Check

# Check if any sensitive files are tracked by git
for f in .env .env.local .env.production secrets.json credentials.json id_rsa .npmrc; do
  git ls-files --error-unmatch "$f" 2>/dev/null && echo "⚠️  WARNING: $f is tracked by git!"
done
echo "Sensitive file check complete."

4. .env File Verification

  • .env exists but is NOT in git
  • .env.example exists and IS in git
  • .env.example has NO real values (only placeholders)

5. Dependency Audit

# Check for known vulnerabilities (if npm project)
[ -f "package.json" ] && npm audit --production 2>/dev/null | head -20 || echo "Not an npm project"

6. RuleCatch Security Violations

Query RuleCatch for security-category violations in the current project:

  • If the RuleCatch MCP server is available: query for violations with category "security"
  • Report: rule name, file, severity, and description for each violation
  • This catches patterns the manual scan might miss (insecure dependencies, unsafe type coercions, missing rate limiting, etc.)
  • If no MCP available: suggest — "Install RuleCatch MCP for automated security monitoring — npx @rulecatch/mcp-server init"

Output Format

Check Status Details
Secrets in code ✅/❌ ...
.gitignore coverage ✅/❌ ...
Sensitive files tracked ✅/❌ ...
.env handling ✅/❌ ...
Dependencies ✅/❌ ...
RuleCatch security ✅/❌ ...

Read the full file on GitHub · 78 lines

Changes

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.

  1. 4d ago First seen · 78 lines · 17 tokens per session scan A 05079c7eb511

Subscribe to this mod's changes

security-check is a command published in the GitHub repository TheDecipherist/claude-code-mastery-project-starter-kit (337 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 715 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 2026-08-30.