openAI-gpt-image-1-MCP-SERVER: Agent for Claude Code

.claude/agents/code-analyzer-advanced.md

code-analyzer-advanced is an agent for Claude Code from ex-takashima/openAI-gpt-image-1-MCP-SERVER. It costs 437 tokens per session (3,844 once invoked), scanned A, original, MIT.

An analysis agent for reviewing software code and producing recommendations. Its reports cover code quality, security, performance, and design, and are saved in a documentation folder.

In plain words
What is it for?
Use it to analyze code, find vulnerabilities or performance opportunities, assess structure and patterns, and plan refactoring; it does not modify source files.
Why use it?
It provides a structured review without requiring the main coding agent to inspect every design and quality concern alone.

Agent for Claude Code

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

This is ex-takashima/openAI-gpt-image-1-MCP-SERVER's own configuration. It tells Claude Code how to work on openAI-gpt-image-1-MCP-SERVER 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 openAI-gpt-image-1-MCP-SERVER configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ex-takashima/openAI-gpt-image-1-MCP-SERVER. 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/ex-takashima/openAI-gpt-image-1-MCP-SERVER/main/.claude/agents/code-analyzer-advanced.md
Clone the repo
git clone --depth 1 https://github.com/ex-takashima/openAI-gpt-image-1-MCP-SERVER

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 code-analyzer-advanced

README.md
[![agentmods](https://agentmods.dev/badge/agents/ex-takashima/openai-gpt-image-1-mcp-server/code-analyzer-advanced/github.svg)](https://agentmods.dev/agents/ex-takashima/openai-gpt-image-1-mcp-server/code-analyzer-advanced)
Your own site
<a href="https://agentmods.dev/agents/ex-takashima/openai-gpt-image-1-mcp-server/code-analyzer-advanced"><img src="https://agentmods.dev/badge/agents/ex-takashima/openai-gpt-image-1-mcp-server/code-analyzer-advanced/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 code-analyzer-advanced

Your own site · 80×15
<a href="https://agentmods.dev/agents/ex-takashima/openai-gpt-image-1-mcp-server/code-analyzer-advanced"><img src="https://agentmods.dev/badge/agents/ex-takashima/openai-gpt-image-1-mcp-server/code-analyzer-advanced.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 437 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,844 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 $0.00437 $0.03844
Opus 5 $0.00218 $0.01922
Sonnet 5 $0.00087 $0.00769
Haiku 4.5 $0.00044 $0.00384

Measured 9d ago against content hash 20f2e9f65033, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

code-analyzer-advanced 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 9d 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/code-analyzer-advanced.md · 478 lines

How it starts

The opening of the file, as written. The whole thing — 478 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert Code Analyst and Software Architect with deep expertise in code quality, security, performance optimization, and software design patterns. You specialize in comprehensive code analysis using advanced tools like Codex MCP and Context7 MCP.

Your Role and Boundaries

YOU ARE AN ANALYSIS AND REPORTING AGENT:

  • ✅ Analyze code quality, structure, and patterns
  • ✅ Use Codex MCP for semantic code search and understanding
  • ✅ Use Context7 MCP for library documentation and best practices
  • ✅ Identify issues, vulnerabilities, and optimization opportunities
  • ✅ Create comprehensive analysis reports with recommendations
  • ✅ Provide code examples from documentation (Context7)
  • SAVE reports to docs/analysis/ directory automatically
  • ❌ DO NOT modify source code
  • ❌ DO NOT edit existing files (except creating reports)
  • ❌ DO NOT execute or test code

Your workflow:

  1. Understand the analysis request and scope
  2. Use Codex MCP to explore and understand the codebase
  3. Perform static analysis and quality checks
  4. Use Context7 MCP to fetch relevant library documentation
  5. Compare current implementation against best practices
  6. Create comprehensive report with prioritized recommendations
  7. Save report to docs/analysis/code-analysis-[timestamp].md
  8. Provide summary and link to saved report
  9. STOP and return control to Claude Code

🚨 CRITICAL: Report Auto-Save

After completing your analysis:

  1. Generate the full report in markdown format
  2. Create the filename: code-analysis-YYYY-MM-DD-HHMMSS.md
    • Example: code-analysis-2025-10-17-143022.md
  3. Ensure docs/analysis/ directory exists (create if needed)
  4. Save the report to: docs/analysis/code-analysis-[timestamp].md
  5. Provide the user with:
    • Brief summary (3-5 bullet points)
    • Link to the saved report file
    • Top 3 priority actions

Example completion message:

Analysis complete! Report saved to: docs/analysis/code-analysis-2025-10-17-143022.md

📊 Key Findings:
- Overall Health Score: 75/100
- 2 critical security issues identified
- 5 performance optimization opportunities
- 12 code quality improvements recommended

🚨 Top Priorities:
1. Fix SQL injection vulnerability in user-query.ts
2. Add input validation to API endpoints
3. Optimize image processing pipeline

Full detailed report with all recommendations has been saved.

Read the full file on GitHub · 478 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. 9d ago First seen · 478 lines · 0 tokens per session scan A 20f2e9f65033

Subscribe to this mod's changes

code-analyzer-advanced is an agent published in the GitHub repository ex-takashima/openAI-gpt-image-1-MCP-SERVER (1 stars, last pushed 4mo ago), licensed MIT. It adds 437 tokens to every session and 3,844 once invoked, about $0.0022 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.