Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/TechNickAI/claude_telemetrynpx agentmods add commands/technickai/claude_telemetry/troubleshoot-setupWrote 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.
[](https://agentmods.dev/commands/technickai/claude_telemetry/troubleshoot-setup)<a href="https://agentmods.dev/commands/technickai/claude_telemetry/troubleshoot-setup"><img src="https://agentmods.dev/badge/commands/technickai/claude_telemetry/troubleshoot-setup/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.
<a href="https://agentmods.dev/commands/technickai/claude_telemetry/troubleshoot-setup"><img src="https://agentmods.dev/badge/commands/technickai/claude_telemetry/troubleshoot-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00000 | $0.00659 |
| Opus 5.5 | $0.00000 | $0.00264 |
| Sonnet 5.5 | $0.00000 | $0.00132 |
| Haiku 4.5 | $0.00000 | $0.00066 |
Grade A, and why
troubleshoot-setup 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setting Up /troubleshoot Command
Quick Start
1. Configure MCP Server
Create .mcp.json in your project root:
{
"mcpServers": {
"sentry": {
"url": "https://mcp.sentry.dev/mcp"
}
}
}
(Or use "honeybadger" with https://mcp.honeybadger.io/mcp)
2. Symlink for Cursor Compatibility
If you use both Claude Code and Cursor:
ln -s ../.mcp.json .cursor/mcp.json
This ensures both tools share the same MCP configuration.
3. Connect Error Monitoring Service
- Sentry: https://mcphubby.ai/integrations/sentry
- HoneyBadger: https://mcphubby.ai/integrations/honeybadger
Click "Connect" and authorize MCP Hubby to access your account.
4. Install the Command
From ai-coding-config repo:
ln -s ../ai-coding-config/.claude/commands/troubleshoot.md .claude/commands/troubleshoot.md
5. Run It
/troubleshoot
The AI will autonomously fix production errors!
What Happens
- AI detects which error monitoring service is connected
- Fetches all unresolved errors
- Groups errors by root cause (cluster analysis)
- Calculates priority scores (recency + frequency + impact + blast radius)
- Fixes highest priority errors in isolated git worktrees
- Operates in parallel (multiple fixes simultaneously)
- Submits PRs with full context
- Monitors deployment and verifies fixes
Advanced Usage
/troubleshoot auto 5 # Fix top 5 bugs in parallel
/troubleshoot watch # Continuous monitoring mode
/troubleshoot analyze # Pattern analysis only
/troubleshoot 3 # Fix specific bug by priority rank
Architecture
Project Root/
├── .mcp.json # MCP server config (source of truth)
├── .cursor/
│ └── mcp.json -> ../.mcp.json # Symlink for Cursor
├── .claude/
│ └── commands/
│ └── troubleshoot.md -> ... # Command symlink
└── .cursor/rules/
├── git-worktree-task.mdc # Worktree workflow
└── git-commit-message.md # Commit standards
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.
- 1mo ago First seen · 105 lines · 0 tokens per session scan A 2b79d2348c1f
troubleshoot-setup is a command published in the GitHub repository TechNickAI/claude_telemetry (31 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 659 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 2026-08-30.
Other commands, from other repositories
explain-error
Explains an error found in a log file and proposes a next step.
local
Command "local" from getsentry/toolkit, covering sentry local run, browser ui, endpoints, tail output and agent tracing.
debug-files
Command "debug-files" from getsentry/toolkit, covering notes on find and important notes.
speckit.md-doctor.drift
Re-evaluate since the last run: compute the git/.memsearch/TDD delta, re-score previously graded files in light of what changed, and report which past suggestions were resolved or are now stale/false.
poly-check
Lint and check formatting with poly — apply no fixes; summarize findings and drift.
fix-issues
Pick up one approved task, implement the fix, and close it.