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/workers-debuggit 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/workers-debug)<a href="https://agentmods.dev/commands/secondsky/claude-skills/workers-debug"><img src="https://agentmods.dev/badge/commands/secondsky/claude-skills/workers-debug.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 | $0.00031 | $0.02383 |
| Opus 5 | $0.00015 | $0.01192 |
| Sonnet 5 | $0.00006 | $0.00477 |
| Haiku 4.5 | $0.00003 | $0.00238 |
Grade A, and why
cloudflare-workers: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.
How it starts
The opening of the file, as written. The whole thing — 377 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workers Debug Command
Interactive debugging assistant for diagnosing and fixing Cloudflare Workers issues.
Execution Workflow
Phase 1: Error Category Identification
Use AskUserQuestion to understand the problem type:
Question: "What type of issue are you experiencing?"
- Options:
- Deployment Error (wrangler deploy fails)
- Runtime Error (worker crashes or returns 500)
- Performance Issue (slow responses, timeouts)
- Build Error (bundling or compilation fails)
- Binding Error (D1, KV, R2, DO not working)
- Authentication Error (wrangler login issues)
Phase 2: Specific Error Details
Based on category, ask follow-up questions:
If Deployment Error:
- "What error message did you receive?"
- "Does
wrangler whoamiwork?" - "Are you deploying to a zone-scoped worker or workers.dev?"
If Runtime Error:
- "What's the exact error message or status code?"
- "Does this happen on all requests or specific routes?"
- "Are you using any bindings (D1, KV, R2, DO)?"
If Performance Issue:
- "What's the expected vs. actual response time?"
- "When did the slowness start?"
- "Is this affecting all routes or specific endpoints?"
If Build Error:
- "What's the build error message?"
- "What bundler are you using (Vite, Webpack, esbuild)?"
- "Did you recently add dependencies?"
If Binding Error:
- "Which binding is failing (D1, KV, R2, DO, Queue)?"
- "What's the error message?"
- "Is the binding configured in wrangler.jsonc?"
If Authentication Error:
- "What command are you running?"
- "Have you run
wrangler loginrecently?" - "Are you using API tokens or OAuth?"
Phase 3: Investigation - Read Relevant Files
Based on error category, read files to diagnose:
For ALL categories:
- Read
wrangler.jsoncorwrangler.toml - Check
package.jsonfor dependencies - Look for recent git changes:
git log -5 --oneline
For Deployment Errors:
4. Check wrangler whoami output
5. Check routes configuration
6. Look for compatibility flags
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 · 377 lines · 31 tokens per session scan A b78db88936cd
cloudflare-workers:debug is a command published in the GitHub repository secondsky/claude-skills (214 stars, last pushed 2d ago), licensed MIT. It adds 31 tokens to every session and 2,383 once invoked, about $0.0002 per session on Opus 5. 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 2026-09-03.
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.