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.
npx agentmods add commands/secondsky/claude-skills/queue-troubleshootgit clone --depth 1 https://github.com/secondsky/claude-skillsWrote 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/secondsky/claude-skills/queue-troubleshoot)<a href="https://agentmods.dev/commands/secondsky/claude-skills/queue-troubleshoot"><img src="https://agentmods.dev/badge/commands/secondsky/claude-skills/queue-troubleshoot.svg" alt="Measured on agentmods" 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 | $0.00018 | $0.02373 |
| Opus 5 | $0.00009 | $0.01187 |
| Sonnet 5 | $0.00004 | $0.00475 |
| Haiku 4.5 | $0.00002 | $0.00237 |
Grade A, and why
cloudflare-queues:troubleshoot scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
await fetch(url, { signal: controller.signal }); How it starts
The opening of the file, as written. The whole thing — 408 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Queue Troubleshoot Command
Troubleshoot Cloudflare Queue issues with systematic checks.
Usage: /queue-troubleshoot my-queue-name
Step 1: Validate Input
If queue name provided as argument ($1), use it. If not provided, ask user:
- "Which queue name do you want to troubleshoot?"
- Store as:
queueName
Step 2: Quick Status Check
Run diagnostics in parallel:
# Check if queue exists
wrangler queues list
# Get queue details
wrangler queues info $queueName
Analyze output for:
- ✅ Queue exists and is listed
- ⚠️ High backlog (>100 messages)
- ⚠️ No active consumer
- ❌ Queue not found (doesn't exist)
Output Example:
Queue Status: my-queue
├── Exists: ✅ Yes
├── Backlog: ⚠️ 250 messages (high)
├── Consumers: ⚠️ 0 active (no consumer configured)
└── Last Activity: 5 minutes ago
Step 3: Configuration Check
Read wrangler.jsonc/wrangler.toml and verify:
Producer Check:
- Search for
queues.producersarray - Check if any binding references
$queueName - Verify binding name is valid JavaScript identifier
Consumer Check:
- Search for
queues.consumersarray - Check if any consumer references
$queueName - Verify settings are reasonable:
max_batch_size: 1-100max_retries: 1-10 (3 is typical)max_concurrency: 1-20 (1-5 is typical)
- Check if
dead_letter_queueconfigured
Output Example:
Configuration Check:
Producer:
✅ Binding: MY_QUEUE → my-queue
Consumer:
❌ NOT CONFIGURED
→ Recommendation: Add consumer configuration:
```jsonc
{
"queues": {
"consumers": [{
"queue": "my-queue",
"max_batch_size": 10,
"max_retries": 3
}]
}
}
```
DLQ:
⚠️ Not configured (recommended for production)
Step 4: Common Issues Check
For each common issue, check and provide fix:
Issue 1: Messages Not Being Consumed
Symptom: Backlog growing, no consumer errors Check:
- Is consumer configured in wrangler.jsonc?
- Is Worker deployed with queue handler?
- Is queue() export present in Worker?
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 · 408 lines · 18 tokens per session scan A 8cbbb5eb9b30
cloudflare-queues:troubleshoot is a command published in the GitHub repository secondsky/claude-skills (214 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 2,373 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other commands, from other repositories
correlate
Find related failures through pattern matching.
diff
Compare two command outputs with intelligent diff.
open
Open/retrieve an offloaded output by ID or shortcut.
search
Search through offloaded outputs with hard caps.
stats
Show FewWord session statistics with rich output and token savings.
timeline
Visual timeline of command outputs in current session.