skills.rest
MadAppGang
MadAppGangOFFICIAL
Explore all skills by this author →
WebsiteGitHub

debug-mode

Log agent sessions to JSONL files with configurable levels and redaction.

7|4|Updated Feb 26, 2026
Search Tags:#debugging#troubleshooting#logging#agent#session#jsonl
One-click install
npx skills add https://github.com/MadAppGang/magus --skill debug-mode-madappgang
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: debug-mode
Source: https://github.com/MadAppGang/magus/tree/main/plugins/agentdev/skills/debug-mode
Command: npx skills add https://github.com/MadAppGang/magus --skill debug-mode-madappgang

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides detailed logging of agent sessions, enabling in-depth debugging, workflow optimization, and performance analysis by capturing all tool invocations, skill activations, and agent delegations.

Core Features & Use Cases

  • Comprehensive Logging: Records all agent activities to JSONL files for easy parsing.
  • Configurable Levels: Supports minimal, standard, and verbose logging levels.
  • Sensitive Data Redaction: Automatically sanitizes API keys and other sensitive information.
  • Use Case: When an agent's behavior is unexpected, enable verbose debug mode to capture every interaction and pinpoint the exact cause of the issue.

Quick Start

Enable debug mode for your agentdev sessions.

Frequently Asked Questions about debug-mode

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I debug unexpected agent behavior during a session?▼

To debug unexpected agent behavior, you can enable verbose session logging to capture tool invocations, skill activations, and agent delegations into JSONL files. This records every interaction to help pinpoint the exact cause of the issue.

How does agent session logging work for troubleshooting?▼

Agent session logging works by capturing all activities, including tool invocations and hook triggers, into JSONL files within a specified directory. It supports configurable logging levels and automatic redaction of sensitive data.

Can I configure logging levels to filter agent debug information?▼

Yes, you can configure logging levels using minimal, standard, and verbose options. This allows you to filter the amount of agent debug information captured during troubleshooting and session analysis.

Does agent debugging automatically redact sensitive data like API keys?▼

Yes, the agent debugging process automatically redacts sensitive data like API keys. This sanitization ensures security while capturing tool invocations and skill activations in your JSONL logs.

What is the best way to capture tool invocations for workflow optimization?▼

The best way to capture tool invocations for workflow optimization is to enable detailed session logging. This records all agent activities into easily parsed JSONL files, allowing you to analyze performance and identify bottlenecks.

Why should I use JSONL files for agent session troubleshooting?▼

You should use JSONL files for agent session troubleshooting because they support easy parsing of logged activities. This format efficiently records tool invocations and skill activations for in-depth performance analysis.

Related Skills

Explore More Software Engineering Skills→
gautam-achieveaigautam-achieveai
2

logging-enablement

Configure structured JSONL logging across C#, JavaScript/TypeScript, Python, and Rust codebases.

Community
Advanced
dakshrawat298-gifdakshrawat298-gif

session-logs

Analyze session JSONL logs with jq and rg to extract costs, token usage, and tool interactions.

Community
Intermediate
MarketingLabbMarketingLabb

coworkia-memory

Store and retrieve long-term project decisions and session histories.

Community
Advanced
SalesforceCommerceCloudSalesforceCommerceCloud
51

b2c-logging

Implement structured logging in B2C Commerce scripts using Logger and Log APIs.

Official
Basic