AI Agent Skill: bmad-Run Inspector for Loop Forensics

AI Agent Skill: bmad-Run Inspector for Loop Forensics

The bmad-Run Inspector for Loop Forensics is an AI agent skill designed to inspect and explain artifacts generated by bmad-loop runs, located within the `.bmad-loop/runs/` directory. This tool facilitates live health checks to determine if loops are functioning correctly and post-run forensics to analyze the execution and gather insights on issues encountered.

What this skill does

• Inspects bmad-loop run artifacts specifically located under `.bmad-loop/runs/`.
• Provides live health checks such as verifying if the loop is active, assessing if there is a fault, and inspecting the agent's current operation.
• Conducts post-run forensic analysis to understand failures, identify runtime issues, and trace token utilization.
• Responds to monitoring and summarizing requests made in various languages, including Vietnamese.
• Operates exclusively with bmad-loop run artifacts, not with application runtime logs or those provided by CI providers.

Who it is for

This tool is ideal for developers and technical teams utilizing AI coding agents such as Claude Code, Cursor, and Codex. It is beneficial for those who need precise and reliable insights into bmad-loop run processes.

Use cases

• Live monitoring of ongoing bmad-loop runs to ensure smooth operation.
• Forensic analysis after a run to discover why a particular execution failed and to generate reports for team discussion.
• Assisting in debugging loops by providing detailed explanations of what occurred during each step of execution.

Technical details

• Verified compatibility with bmad-loop version 0.11.1.
• The skill includes scripts written in Python 3.9+, while bmad-loop requires Python 3.11 or newer, commonly run in isolated environments.
• Understands that the `.log` file within the run artifacts is a terminal redraw capture, not a sequential transcript.
• Special considerations for `opencode-http` which instead writes out an actual transcript.

Source & Licence

This package is built on open-source work published by tronghieu (tronghieu/agent-skills) and distributed under MIT. The original licence text and copyright notice are included in your download.

Personal and commercial use, modification and redistribution are permitted, provided the original copyright and licence notice are retained.

Your purchase covers curation, licence verification, packaging, documentation and instant delivery. It does not grant exclusive rights to the underlying open-source code, which remains available under its original licence.

Delivery & Support

• Delivery: instant — a secure download link is emailed to you as soon as payment is confirmed.
• Format: ZIP archive containing the skill files, documentation and the original licence.
• Support: support@mcpcart.com — we aim to reply within 2 business days.
• Updates: updates are included only where stated on this page.

Refunds

This is a digital product delivered immediately after purchase. By completing your order you request immediate delivery and acknowledge that, once the download has been accessed, the statutory right to cancel no longer applies to the extent permitted by law. Refund requests are handled in accordance with our published Refund Policy.

Claude, Codex, Gemini and Cursor are trademarks of their respective owners. MCP Cart is an independent marketplace and is not affiliated with, endorsed by, or sponsored by any of them. Compatibility references describe interoperability only.