A command for diagnosing Claude Code setup and configuration problems. Claude Code is a command-line coding assistant that can use project files, tools, servers, and hooks.

For running a full check, applying available fixes, or generating a report about a Claude Code installation.

It checks common installation, authentication, project configuration, MCP server, and hook problems in one debugging scan.

cc-debug — Command by TheLobbi

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.

agentmods

npx agentmods add commands/thelobbi/claude/cc-debug

Clone the repo

git clone --depth 1 https://github.com/TheLobbi/claude

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 590 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00590
Opus 5	$0.00000	$0.00295
Sonnet 5	$0.00000	$0.00118
Haiku 4.5	$0.00000	$0.00059

Measured yesterday against content hash e3b67b960695, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cc-debug 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 yesterday.

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/commands/cc-debug.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/cc-debug — Claude Code Setup Debugger

Comprehensive debugger for Claude Code configuration and setup issues.

Usage

/cc-debug                         # Full debug scan
/cc-debug --fix                   # Scan and auto-fix issues
/cc-debug --report                # Generate debug report

What It Checks

1. Installation Health

Claude Code CLI version and installation
Node.js version (requires 18+)
npm/pnpm/yarn availability
Global vs local installation
PATH configuration

2. Authentication

API key presence and format
Provider configuration (Direct, Bedrock, Vertex)
Token validity (basic connectivity test)
Proxy settings affecting auth

3. Project Configuration

CLAUDE.md presence and readability
settings.json syntax and schema validation
settings.local.json syntax
.mcp.json syntax and server configs
Rules files syntax and path patterns
.gitignore entries for sensitive files

4. MCP Servers

Each server: command exists, env vars set, starts successfully
Tool listing from each server
Timeout and connectivity issues
Duplicate server names

5. Hooks

Each hook: script exists, is executable, produces valid JSON
Matcher patterns are valid
No circular dependencies
Timeout configuration

6. Plugins

Plugin manifest validation
Resource file existence
Registry consistency
Version compatibility

7. Permissions

Allow/deny list syntax
Pattern matching validation
Conflicting rules detection
Enterprise settings conflicts

8. Known Issues

Check lessons-learned.md for NEEDS_FIX entries
Check for known error patterns
Compare against common fixes database

Implementation

When invoked:

Activate the claude-code-debugger agent
Run all diagnostic checks systematically
Categorize findings: PASS, WARN, FAIL
For each FAIL: provide specific fix command/steps
If --fix flag: automatically apply safe fixes
If --report flag: save full report to .claude/debug-report.md

Read the full file on GitHub · 97 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.

yesterday First seen · 97 lines · 0 tokens per session scan A e3b67b960695

Subscribe to this mod's changes

cc-debug is a command published in the GitHub repository TheLobbi/claude (21 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 590 tokens. 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.

Debugging

cc-debug