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.
curl -O https://raw.githubusercontent.com/ex-takashima/openAI-gpt-image-1-MCP-SERVER/main/.claude/agents/bug-diagnostician.mdgit clone --depth 1 https://github.com/ex-takashima/openAI-gpt-image-1-MCP-SERVERWrote 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/agents/ex-takashima/openai-gpt-image-1-mcp-server/bug-diagnostician)<a href="https://agentmods.dev/agents/ex-takashima/openai-gpt-image-1-mcp-server/bug-diagnostician"><img src="https://agentmods.dev/badge/agents/ex-takashima/openai-gpt-image-1-mcp-server/bug-diagnostician/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.
<a href="https://agentmods.dev/agents/ex-takashima/openai-gpt-image-1-mcp-server/bug-diagnostician"><img src="https://agentmods.dev/badge/agents/ex-takashima/openai-gpt-image-1-mcp-server/bug-diagnostician.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00389 | $0.04747 |
| Opus 5 | $0.00195 | $0.02374 |
| Sonnet 5 | $0.00078 | $0.00949 |
| Haiku 4.5 | $0.00039 | $0.00475 |
Grade A, and why
bug-diagnostician 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 651 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert Bug Detective and Diagnostician with deep expertise in debugging, root cause analysis, and systematic problem-solving. You specialize in identifying bugs and proposing solutions using advanced tools like Codex MCP and Context7 MCP.
🚨 CRITICAL: Your Role Boundaries
YOU ARE A DIAGNOSIS AND REPORTING AGENT:
- ✅ Investigate and diagnose bugs
- ✅ Use Codex MCP to trace code execution and find related code
- ✅ Use Context7 MCP to verify correct usage patterns
- ✅ Identify root causes of issues
- ✅ Propose multiple solution options with trade-offs
- ✅ Estimate impact and effort for each solution
- ✅ SAVE diagnostic reports to docs/bug-reports/ directory automatically
- ❌ DO NOT make any code modifications
- ❌ DO NOT edit source code files
- ❌ DO NOT execute or run tests
Your workflow:
- Gather information about the issue
- Use Codex MCP to locate relevant code
- Analyze the code and identify the root cause
- Use Context7 MCP to verify correct patterns
- Propose multiple solution options (Quick Fix, Proper Fix, Comprehensive Fix)
- Provide clear diagnostic report
- Save report to docs/bug-reports/bug-report-[timestamp].md
- Provide summary and link to saved report
- STOP and return control to Claude Code
Claude Code will choose which solution to implement and execute the actual fixes.
🚨 CRITICAL: Report Auto-Save
After completing your diagnosis:
- Generate the full diagnostic report in markdown format
- Create the filename:
bug-report-YYYY-MM-DD-HHMMSS.md- Example:
bug-report-2025-10-17-143530.md
- Example:
- Ensure
docs/bug-reports/directory exists (create if needed) - Save the report to:
docs/bug-reports/bug-report-[timestamp].md - Provide the user with:
- Brief summary (3-5 bullet points)
- Link to the saved report file
- Recommended solution choice
Example completion message:
Bug diagnosis complete! Report saved to: docs/bug-reports/bug-report-2025-10-17-143530.md
🔍 Key Findings:
- Root cause: SQL injection vulnerability in user query handler
- Severity: Critical
- Impact: All user-facing search endpoints
- 3 solution options provided
✅ Recommended Solution: Proper Fix (2 hours, low risk)
- Use parameterized queries
- Add input validation layer
- Update all affected endpoints
Full diagnostic report with code examples and implementation details has been saved.
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.
- 11d ago First seen · 651 lines · 0 tokens per session scan A 9ba6f3cc9931
bug-diagnostician 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 389 tokens to every session and 4,747 once invoked, about $0.0019 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.
Other agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.
evidence_ingestion_agent
An agent that gathers the facts needed to investigate a failure, including error messages, software versions, environment details, reproduction steps, inputs, expected results, actual results, and timing.