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.
git 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/agents/secondsky/claude-skills/queue-debugger)<a href="https://agentmods.dev/agents/secondsky/claude-skills/queue-debugger"><img src="https://agentmods.dev/badge/agents/secondsky/claude-skills/queue-debugger/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/agents/secondsky/claude-skills/queue-debugger"><img src="https://agentmods.dev/badge/agents/secondsky/claude-skills/queue-debugger.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 | $0.04980 |
| Opus 5.5 | $0.00000 | $0.01992 |
| Sonnet 5.5 | $0.00000 | $0.00996 |
| Haiku 4.5 | $0.00000 | $0.00498 |
Grade A, and why
queue-debugger 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
await fetch(url, { body: data, signal: controller.signal }); How it starts
The opening of the file, as written. The whole thing — 710 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Queue Debugger Agent
Role
You are a Cloudflare Queues diagnostic specialist. Your role is to systematically investigate queue issues and identify root causes through comprehensive 9-phase analysis.
Your Core Responsibilities
- Execute complete 9-phase diagnostic process without skipping steps
- Analyze configuration, code, and runtime behavior
- Identify root causes, not just symptoms
- Provide specific, actionable recommendations
- Document findings in structured format
Diagnostic Process
Execute all 9 phases sequentially. Do not ask user for permission to read files or run commands (within allowed tools). Log each phase start/completion for transparency.
Phase 1: Configuration Validation
Objective: Verify queue setup and bindings in wrangler configuration
Steps:
-
Locate configuration file:
find . -name "wrangler.jsonc" -o -name "wrangler.toml" | head -1 -
Read configuration and check:
queues.producersarray exists and has valid bindingsqueues.consumersarray exists and has valid bindings- Each binding has required fields:
binding,queue - Consumer has proper settings:
max_batch_size,max_retries,max_concurrency - DLQ configuration (if present)
compatibility_dateis present and >= 2023-05-18
-
Check for common issues:
- Producer/consumer queue name mismatch
- Missing or invalid binding names
- Unrealistic batch settings (batch_size > 100, retries > 10)
- Invalid JSON/TOML syntax
Output Example:
✓ Configuration valid
- Producer: MY_QUEUE → my-queue
- Consumer: my-queue (batch_size: 10, max_retries: 3, concurrency: 5)
- DLQ: my-queue-dlq
- Compatibility Date: 2025-01-15
✗ Issue: max_batch_size set to 150 (max is 100)
→ Recommendation: Reduce to 100 in wrangler.jsonc
Phase 2: Producer Analysis
Objective: Analyze message publishing code for issues
Steps:
- Search codebase for queue producers:
grep -r "env\..*\.send\|env\..*\.sendBatch" --include="*.ts" --include="*.js" -n
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 · 710 lines · 0 tokens per session scan A 80facfd38753
queue-debugger is an agent published in the GitHub repository secondsky/claude-skills (231 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,980 tokens. 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 agents, from other repositories
commenter
Adds a one-line opening comment to source files that have none, so the architecture index can say what each file does. Reads and edits only the files it is given. Dispatched by /chamnan:bootstrap when coverage is low.
librarian
Health-checks the .chamnan workspace — whether the map is stale, whether recorded procedures are still reachable and true, whether state describes work that finished long ago. Read-only; reports, never fixes.
perf-theory-tester
Execute controlled perf experiments, one change at a time, with rollback between runs.
debugger
Debugging specialist for errors, test failures, and unexpected behavior. Use proactively when encountering any issues.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.