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/do-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/do-debug)<a href="https://agentmods.dev/commands/secondsky/claude-skills/do-debug"><img src="https://agentmods.dev/badge/commands/secondsky/claude-skills/do-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 | $0.00033 | $0.04775 |
| Opus 5 | $0.00016 | $0.02388 |
| Sonnet 5 | $0.00007 | $0.00955 |
| Haiku 4.5 | $0.00003 | $0.00477 |
Grade A, and why
cloudflare-durable-objects:debug 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 today.
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.
curl https://your-worker.workers.dev?id=test How it starts
The opening of the file, as written. The whole thing — 834 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Durable Objects Debug Command
Interactive command to diagnose and fix common Durable Objects issues. Provides step-by-step troubleshooting for configuration errors, runtime failures, and performance problems.
Overview
This command helps debug DO issues by:
- Detecting common error patterns from error messages
- Running diagnostic checks on configuration and code
- Providing specific fixes for identified issues
- Testing solutions before deployment
- Monitoring DO behavior with wrangler tail
Step 1: Gather Error Context
Use AskUserQuestion tool to understand the problem:
Question 1: Error Category
Question: "What type of issue are you experiencing with Durable Objects?" Header: "Issue Type" Options:
- Deployment Error - wrangler deploy fails with DO-related error
- Description: "Migration errors, binding issues, class export problems"
- Runtime Error - DO throws error during execution
- Description: "Constructor failures, storage errors, WebSocket issues"
- Performance Issue - DO is slow or timing out
- Description: "Slow queries, hibernation problems, memory issues"
- Data Loss - DO state not persisting correctly
- Description: "Data disappearing, inconsistent state, sync issues"
- WebSocket Problem - WebSocket connections failing or not hibernating
- Description: "Connection drops, hibernation failures, message loss"
- Alarm Not Firing - Scheduled alarms not executing
- Description: "Alarms not triggering, retry loops, timing issues"
- Other/Unknown - Not sure or different issue
- Description: "General debugging assistance needed"
Question 2: Error Message (If Applicable)
If user selected error-based category (Deployment, Runtime):
Prompt: "Please paste the full error message:"
Enter error message (or 'none' if no specific error):
_____________________________________________
_____________________________________________
_____________________________________________
Parse error message for known patterns:
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.
- today First seen · 834 lines · 33 tokens per session scan A 1cd5e0d2bbcf
cloudflare-durable-objects:debug is a command published in the GitHub repository secondsky/claude-skills (214 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 4,775 once invoked, about $0.0002 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.