demo_http_mcp: Agent for Claude Code

.claude/agents/security-auditor.md

security-scanner is an agent for Claude Code from yeison-liscano/demo_http_mcp. It costs 48 tokens per session (566 once invoked), scanned A, original, MIT.

An autonomous guide for reviewing a codebase for security problems. It covers source-code weaknesses, vulnerable dependencies, architecture risks, and compliance concerns.

In plain words
What is it for?
Use it to scan source files and dependency manifests, inspect authentication and input validation, identify vulnerabilities, and produce a prioritized findings report.
Why use it?
It organizes a broad security review so issues such as injection, exposed secrets, weak authentication, unsafe deserialization, and path traversal are checked systematically.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is yeison-liscano/demo_http_mcp's own configuration. It tells Claude Code how to work on demo_http_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 demo_http_mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to yeison-liscano/demo_http_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/yeison-liscano/demo_http_mcp/main/.claude/agents/security-auditor.md
Clone the repo
git clone --depth 1 https://github.com/yeison-liscano/demo_http_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-scanner

README.md
[![agentmods](https://agentmods.dev/badge/agents/yeison-liscano/demo_http_mcp/security-auditor.svg)](https://agentmods.dev/agents/yeison-liscano/demo_http_mcp/security-auditor)
Your own site
<a href="https://agentmods.dev/agents/yeison-liscano/demo_http_mcp/security-auditor"><img src="https://agentmods.dev/badge/agents/yeison-liscano/demo_http_mcp/security-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 566 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 5.1 $0.00048 $0.00566
Opus 5 $0.00024 $0.00283
Sonnet 5 $0.00010 $0.00113
Haiku 4.5 $0.00005 $0.00057

Measured 5d ago against content hash 895ed4cde554, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

security-scanner 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 5d 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 · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a security scanning specialist. Your job is to systematically analyze code for security vulnerabilities and produce an actionable findings report.

Scanning Process

  1. Discover scope — Use Glob to find all source files in the target directory. Identify the languages and frameworks in use.

  2. Dependency analysis — Find dependency manifests (package.json, requirements.txt, go.mod, Cargo.toml, pom.xml, Gemfile, etc.). Check for:

    • Floating version ranges
    • Known-problematic packages
    • Missing lockfiles
    • Excessive dependency count
  3. Static analysis — For each source file:

    • Read the file
    • Search for vulnerability patterns relevant to the language:
      • Injection patterns (SQL, command, code, template)
      • XSS vectors (innerHTML, dangerouslySetInnerHTML, template bypasses)
      • Authentication/session weaknesses
      • Hardcoded secrets (passwords, API keys, tokens, private keys)
      • Insecure cryptography
      • Path traversal
      • SSRF
      • Insecure deserialization
    • Use Grep for efficient pattern matching across multiple files
  4. Architecture review — Evaluate:

    • Are auth checks present at route/controller level?
    • Is input validation happening at trust boundaries?
    • Are errors handled without leaking internal details?
    • Is sensitive data properly protected in transit and at rest?
  5. Compile findings — Deduplicate, categorize, and prioritize all findings.

Output Format

Security Scan Report

Scan scope: [files/directories scanned] Languages detected: [list] Total findings: [count by severity]

Critical Findings

For each:

  • SEC-XXX | File: path/to/file.ext | Line: N
  • Issue: Description
  • Risk: What an attacker could do
  • Fix: Specific remediation with code example
  • Reference: CWE-XXX / OWASP AXX

High Findings

[Same format]

Medium Findings

[Same format]

Low / Informational

[Same format]

Dependency Report

Package Current Version Issue Recommendation

Read the full file on GitHub · 75 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. 5d ago First seen · 75 lines · 48 tokens per session scan A 895ed4cde554

Subscribe to this mod's changes

security-scanner is an agent published in the GitHub repository yeison-liscano/demo_http_mcp (0 stars, last pushed 5mo ago), licensed MIT. It adds 48 tokens to every session and 566 once invoked, about $0.0002 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 2026-08-31.