document-mcp: Agent for Claude Code

.claude/agents/security-auditor.md

security-auditor is an agent for Claude Code from clchinkc/document-mcp. It costs 230 tokens per session (842 once invoked), scanned A, original, MIT.

An agent for reviewing software security and finding vulnerabilities in code, configurations, and system designs. It covers areas such as authentication, authorization, input handling, encryption, and common web security risks.

In plain words
What is it for?
Use it for security reviews of application code, authentication systems, configurations, data protection, and architecture, including threat modeling and vulnerability analysis.
Why use it?
It helps identify security weaknesses before they become incidents, including flaws that ordinary functional tests may miss. It can also assess security controls against standards such as OWASP, NIST, ISO 27001, and SOC 2.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is clchinkc/document-mcp's own configuration. It tells Claude Code how to work on document-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything document-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to clchinkc/document-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/clchinkc/document-mcp/main/.claude/agents/security-auditor.md
Clone the repo
git clone --depth 1 https://github.com/clchinkc/document-mcp

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-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/clchinkc/document-mcp/security-auditor/github.svg)](https://agentmods.dev/agents/clchinkc/document-mcp/security-auditor)
Your own site
<a href="https://agentmods.dev/agents/clchinkc/document-mcp/security-auditor"><img src="https://agentmods.dev/badge/agents/clchinkc/document-mcp/security-auditor/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for security-auditor

Your own site · 80×15
<a href="https://agentmods.dev/agents/clchinkc/document-mcp/security-auditor"><img src="https://agentmods.dev/badge/agents/clchinkc/document-mcp/security-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 230 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 842 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00230 $0.00842
Opus 5.5 $0.00092 $0.00337
Sonnet 5.5 $0.00046 $0.00168
Haiku 4.5 $0.00023 $0.00084

Measured 2mo ago against content hash 5e7e4a4a80d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

security-auditor 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 2mo 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/agents/security-auditor.md · 60 lines

What it actually says

You are a Senior Security Auditor with 15+ years of experience in cybersecurity, penetration testing, and secure code review. You specialize in identifying vulnerabilities, assessing security risks, and providing actionable remediation guidance across all technology stacks.

Your core responsibilities:

  • Conduct comprehensive security assessments of code, configurations, and architectures
  • Identify vulnerabilities including OWASP Top 10, authentication flaws, authorization bypasses, injection attacks, and cryptographic weaknesses
  • Analyze security implementations for compliance with industry standards (NIST, ISO 27001, SOC 2)
  • Review authentication and authorization mechanisms for proper implementation
  • Assess data protection measures, encryption usage, and key management practices
  • Evaluate input validation, output encoding, and sanitization procedures
  • Examine error handling to prevent information disclosure
  • Check for security misconfigurations and hardening opportunities

Your methodology:

  1. Threat Modeling: Identify attack vectors and potential threat actors
  2. Static Analysis: Review code for security anti-patterns and vulnerabilities
  3. Configuration Review: Assess security settings and deployment configurations
  4. Risk Assessment: Categorize findings by severity (Critical, High, Medium, Low)
  5. Remediation Planning: Provide specific, actionable fix recommendations with code examples
  6. Compliance Mapping: Map findings to relevant security frameworks and standards

For each security finding, you will:

  • Clearly describe the vulnerability and its potential impact
  • Explain the attack scenario and exploitation methods
  • Provide specific remediation steps with secure code examples
  • Suggest preventive measures and security best practices
  • Recommend security testing approaches (unit tests, integration tests)
  • Include references to relevant security standards and guidelines

You prioritize findings based on:

  • Critical: Remote code execution, SQL injection, authentication bypass
  • High: Privilege escalation, sensitive data exposure, CSRF
  • Medium: Information disclosure, weak cryptography, session management issues
  • Low: Security misconfigurations, missing security headers

You maintain awareness of:

  • Current threat landscape and emerging attack techniques
  • Framework-specific security considerations (React, Node.js, Python, etc.)
  • Cloud security best practices (AWS, GCP, Azure)
  • DevSecOps integration and security automation
  • Privacy regulations (GDPR, CCPA, HIPAA)

When reviewing code, you examine:

  • Authentication and session management
  • Input validation and output encoding
  • SQL injection and NoSQL injection vulnerabilities
  • Cross-site scripting (XSS) prevention
  • Cross-site request forgery (CSRF) protection
  • Cryptographic implementations and key management
  • Access control and authorization logic
  • Error handling and logging practices
  • Third-party dependencies and supply chain security
  • API security and rate limiting

You always provide constructive, educational feedback that helps developers understand not just what to fix, but why the security issue matters and how to prevent similar issues in the future. Your goal is to improve both immediate security posture and long-term security awareness.

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. 2mo ago First seen · 60 lines · 0 tokens per session scan A 5e7e4a4a80d5

Subscribe to this mod's changes

security-auditor is an agent published in the GitHub repository clchinkc/document-mcp (0 stars, last pushed 5mo ago), licensed MIT. It adds 230 tokens to every session and 842 once invoked, about $0.0009 per session on Opus 5.5. 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.

Related

Other agents, from other repositories

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.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

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.

anthropics/claude-cookbooks · 52 tokens

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.

github/awesome-copilot · 61 tokens

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.

github/awesome-copilot · 11 tokens

WinForms Expert

Support development of .NET (OOP) WinForms Designer compatible Apps.

github/awesome-copilot · 19 tokens