agent-debugging

agent-debugging is a skill for Claude Code from majiayu000/claude-skill-registry. It costs 58 tokens per session (6,667 once invoked), scanned B, a copy of agent-debugging, MIT.

A troubleshooting process for ElevenLabs conversational AI agents and Twilio phone calls. It uses symptoms, reproduction, isolation, diagnosis, and verification to investigate configuration, audio, latency, and conversation problems.

In plain words
What is it for?
Use it to inspect failed calls, interpret error logs, diagnose agent configuration and audio problems, and produce diagnostic reports.
Why use it?
It gives a repeatable way to find the cause of failed calls, missing responses, audio issues, or broken context instead of guessing.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths.

Good fit Use it to inspect failed calls, interpret error logs, diagnose agent configuration and audio problems, and produce diagnostic reports.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/majiayu000/claude-skill-registry/agent-debugging
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add majiayu000/claude-skill-registry --skill agent-debugging
Clone the repo
git clone --depth 1 https://github.com/majiayu000/claude-skill-registry

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 agent-debugging

README.md
[![agentmods](https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/agent-debugging/github.svg)](https://agentmods.dev/skills/majiayu000/claude-skill-registry/agent-debugging)
Your own site
<a href="https://agentmods.dev/skills/majiayu000/claude-skill-registry/agent-debugging"><img src="https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/agent-debugging/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 agent-debugging

Your own site · 80×15
<a href="https://agentmods.dev/skills/majiayu000/claude-skill-registry/agent-debugging"><img src="https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/agent-debugging.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,667 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod 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 $0.00058 $0.06667
Opus 5 $0.00029 $0.03334
Sonnet 5 $0.00012 $0.01333
Haiku 4.5 $0.00006 $0.00667

Measured 8d ago against content hash 039f1e6805cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

agent-debugging scanned grade B with 2 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 8d 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

const response = await fetch('https://your-domain.com/twiml/test', { method: 'POST',

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -X POST https://your-domain.com/twiml/test-123
Origin

This is a copy

100% identical to agent-debugging — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/agent/agent-debugging/SKILL.md · 1,061 lines

How it starts

The opening of the file, as written. The whole thing — 1,061 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Debugging Skill

Systematic debugging and troubleshooting framework for ElevenLabs Conversational AI + Twilio integration on the Next Level Real Estate platform. This skill provides diagnostic procedures, root cause analysis techniques, and resolution strategies.

When to Use This Skill

Invoke this skill when you need to:

  • ✅ Debug agent configuration issues
  • ✅ Analyze failed or poor-quality calls
  • ✅ Troubleshoot audio/latency problems
  • ✅ Investigate conversation breakdowns
  • ✅ Review and interpret error logs
  • ✅ Diagnose context injection failures
  • ✅ Identify performance bottlenecks
  • ✅ Generate diagnostic reports

Debugging Methodology

The 5-Step Debug Process

1. OBSERVE   → Gather symptoms and error data
2. REPRODUCE → Confirm issue is consistent
3. ISOLATE   → Narrow down to specific component
4. DIAGNOSE  → Identify root cause
5. FIX       → Implement and verify solution

Common Issues & Solutions

Issue Category 1: Agent Configuration

Problem: Agent Not Starting/Responding

Symptoms:

  • Agent status shows "inactive" or "error"
  • Conversation fails to start
  • No greeting heard on call
  • Error: "Agent not found" or "Invalid agent ID"

Diagnostic Steps:

# 1. Check agent exists and is active
Use mcp__elevenlabs__elevenlabs_get_agent with:
{
  "agentId": "your_agent_id"
}

# Expected output:
# - status: "active"
# - voiceId: valid voice ID
# - modelId: valid model
# - systemPrompt: non-empty

# 2. Verify voice is valid
Use mcp__elevenlabs__elevenlabs_get_voice with:
{
  "voiceId": "voice_from_agent_config"
}

# 3. Check agent configuration file
Read .claude/agents/elevenlabs-agent-manager.md

# Look for:
# - Syntax errors in frontmatter
# - Invalid tool names
# - Malformed YAML

Common Root Causes:

Root Cause Symptoms Solution
Invalid voice ID Agent fails to start Use list_voices to find valid ID
Voice not available for TTS "Voice not supported" error Select voice with availableForTts: true
Empty system prompt Generic/confused responses Add detailed system prompt
Wrong model ID "Model not found" error Use: eleven_flash_v2_5, eleven_turbo_v2_5, or eleven_multilingual_v2
Agent not deployed "Agent not found" Re-create agent or verify agent ID

Read the full file on GitHub · 1,061 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 1,061 lines · 58 tokens per session scan B 039f1e6805cd

Subscribe to this mod's changes

agent-debugging is a skill published in the GitHub repository majiayu000/claude-skill-registry (604 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 6,667 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). It is 100% identical to agent-debugging, differing in 0 lines, and is treated as a copy.