cc-troubleshoot

cc-troubleshoot is a command for Claude Code from TheLobbi/claude. It costs 0 tokens per session (446 once invoked), scanned A, original, MIT.

A command for diagnosing Claude Code setup and runtime problems. It checks areas such as authentication, configuration, MCP servers, hooks, plugins, permissions, installation, and performance.

In plain words
What is it for?
Use it for a full health check or to investigate one issue type, such as login, MCP connection, hooks, permissions, plugins, installation, or slow performance.
Why use it?
It turns a broad setup problem or a specific failure into a structured diagnostic check, helping identify what is misconfigured or unavailable.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

Part of the claude-orchestration plugin — 6 skills, 133 commands, 9 agents, 8 hooks, 6 plugins shipped together

Good fit Use it for a full health check or to investigate one issue type, such as login, MCP connection, hooks, permissions, plugins, installation, or slow performance.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/thelobbi/claude/cc-troubleshoot
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.

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

Made for: Claude Code.

Or install claude-orchestration, the plugin that ships this one along with the rest of its 6 skills, 133 commands, 9 agents, 8 hooks, 6 plugins.

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 cc-troubleshoot

README.md
[![agentmods](https://agentmods.dev/badge/commands/thelobbi/claude/cc-troubleshoot/github.svg)](https://agentmods.dev/commands/thelobbi/claude/cc-troubleshoot)
Your own site
<a href="https://agentmods.dev/commands/thelobbi/claude/cc-troubleshoot"><img src="https://agentmods.dev/badge/commands/thelobbi/claude/cc-troubleshoot/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 cc-troubleshoot

Your own site · 80×15
<a href="https://agentmods.dev/commands/thelobbi/claude/cc-troubleshoot"><img src="https://agentmods.dev/badge/commands/thelobbi/claude/cc-troubleshoot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
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 446 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00446
Opus 5 $0.00000 $0.00223
Sonnet 5 $0.00000 $0.00089
Haiku 4.5 $0.00000 $0.00045

Measured 9d ago against content hash 7bedd36bae95, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

cc-troubleshoot 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 9d 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.

.claude/commands/cc-troubleshoot.md · 65 lines

What it actually says

/cc-troubleshoot — Claude Code Issue Diagnostics

Diagnose and fix Claude Code setup and runtime issues.

Usage

/cc-troubleshoot [issue-type]

Issue Types

/cc-troubleshoot                  # Run full diagnostics
/cc-troubleshoot auth             # Authentication issues
/cc-troubleshoot mcp              # MCP server issues
/cc-troubleshoot hooks            # Hook issues
/cc-troubleshoot config           # Configuration issues
/cc-troubleshoot permissions      # Permission issues
/cc-troubleshoot performance      # Performance issues
/cc-troubleshoot install          # Installation issues
/cc-troubleshoot plugins          # Plugin issues

Implementation

When invoked, activate the claude-code-debugger agent to run systematic diagnostics:

Full Diagnostics (no issue-type)

  1. Environment check (Node, npm, Claude Code version)
  2. Authentication check (API key, provider)
  3. Configuration validation (settings.json, .mcp.json, CLAUDE.md)
  4. MCP server status
  5. Hook validation
  6. Plugin validation
  7. Check lessons-learned for known issues
  8. Report all findings with severity

Targeted Diagnostics (with issue-type)

Focus only on the specified area with deeper analysis.

Output Format

=== Claude Code Diagnostics ===

[PASS] Node.js v20.11.0
[PASS] Claude Code v1.2.3
[PASS] API Key configured (54 chars)
[PASS] settings.json valid
[WARN] 3 unresolved issues in lessons-learned.md
[FAIL] MCP server "postgres" not responding
[FAIL] Hook script .claude/hooks/guard.sh not executable

=== Recommended Fixes ===
1. Fix MCP server: Check DATABASE_URL env var
2. Fix hook: chmod +x .claude/hooks/guard.sh

Auto-Fix

When possible, offer to automatically fix issues:

  • Make scripts executable
  • Fix JSON syntax errors
  • Set missing env vars (prompt for values)
  • Install missing dependencies
  • Clear corrupted cache
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. 9d ago First seen · 65 lines · 0 tokens per session scan A 7bedd36bae95

Subscribe to this mod's changes

cc-troubleshoot is a command published in the GitHub repository TheLobbi/claude (21 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 446 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.