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 skills add delta-and-beta/electron-dev-bridge --skill electron-debugginggit clone --depth 1 https://github.com/delta-and-beta/electron-dev-bridgeWrote 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/skills/delta-and-beta/electron-dev-bridge/electron-debugging)<a href="https://agentmods.dev/skills/delta-and-beta/electron-dev-bridge/electron-debugging"><img src="https://agentmods.dev/badge/skills/delta-and-beta/electron-dev-bridge/electron-debugging/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/skills/delta-and-beta/electron-dev-bridge/electron-debugging"><img src="https://agentmods.dev/badge/skills/delta-and-beta/electron-dev-bridge/electron-debugging.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 | $0.00066 | $0.01250 |
| Opus 5.5 | $0.00026 | $0.00500 |
| Sonnet 5.5 | $0.00013 | $0.00250 |
| Haiku 4.5 | $0.00007 | $0.00125 |
Grade A, and why
electron-debugging 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Electron App Debugging with electron-dev-bridge
Systematic debugging using 41 MCP bridge tools.
Quick Diagnostic (3 calls)
# 1. What's on the page?
electron_get_page_summary
# 2. Any errors?
electron_get_errors
# 3. Any failed network requests?
electron_get_network_requests errorsOnly=true
If errors found, generate a full report: electron_error_report
Diagnostic Flowchart
Problem reported
|
+-- Can you connect?
| NO --> See "Connection Issues"
| YES
|
+-- Run electron_get_page_summary. Is UI visible?
| NO --> See "Blank Screen"
| YES
|
+-- Run electron_get_errors. Any exceptions?
| YES --> See "Error Analysis"
| NO
|
+-- Is the expected element present?
| NO --> See "Element Not Found"
| YES
|
+-- Does interaction work?
NO --> See "Interaction Failures"
YES --> Issue may be data-related. Check network + IPC.
Connection Issues
# Check port
electron_list_targets
# If no targets: app not running or wrong port
# Launch with auto-port (handles conflicts)
electron_launch appPath="/path/to/{YOUR_APP}"
# Or connect to specific port
electron_connect port=9230
| Error | Fix |
|---|---|
| Connection refused | Start app with --remote-debugging-port |
| Port in use | electron_launch auto-picks a free port |
| Wrong window | electron_list_targets then electron_switch_target |
| Connection lost | Auto-reconnects after 1s. If still down, electron_connect |
Blank Screen
electron_get_url
# Is the URL correct?
electron_wait_for_selector selector="{YOUR_APP_ROOT}" timeout=15000
# Did it appear?
electron_get_main_process_logs level="stderr"
# Any main process errors?
electron_get_console_logs level="error"
# Any renderer errors?
Error Analysis
# Grouped errors with stack traces
electron_get_errors
# Filter by source
electron_get_errors source="exception"
electron_get_errors source="network"
electron_get_errors source="console.error"
# Full error report (HTML dashboard)
electron_error_report
# Opens in browser — shows grouped errors, stack traces, timeline,
# failed requests, console errors, main process logs
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 · 203 lines · 66 tokens per session scan A 00f9a31759b0
electron-debugging is a skill published in the GitHub repository delta-and-beta/electron-dev-bridge (1 stars, last pushed 6mo ago), licensed MIT. It adds 66 tokens to every session and 1,250 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
node-inspect-debugger
Debug Node.js via --inspect + Chrome DevTools Protocol CLI.
inspector-mcp
Debug a live Node.js process via CDP — connect to --inspect, set TypeScript breakpoints, step through code, and inspect variables at runtime. Use when the user mentions debugging, --inspect port, breakpoints, wants to trace a bug, inspect what a variable holds, or understand why code behaves unexpectedly at runtime.
troubleshoot
Investigate unexpected chat agent behavior by analyzing direct debug logs in JSONL files. Use when users ask why something happened, why a request was slow, why tools or subagents were used or skipped, or why instructions/skills/agents did not load.
pinchtab-dev
Develop and contribute to the PinchTab project. Use when working on PinchTab source code, adding features, fixing bugs, running tests, or preparing PRs. Triggers on "work on pinchtab", "pinchtab development", "contribute to pinchtab", "fix pinchtab bug", "add pinchtab feature".
winapp-sandbox
Run, debug, and UI-automate a Windows app in a persistent Windows Sandbox rather than the user's desktop. Use for disposable app testing, guest diagnostics, file transfer, and app or whole-desktop evidence. Builds remain on the host; connection and reconnect can briefly take focus.
winui-devtools
Inspect a running WinUI 3 app's XAML with winapp devtools: resolved property values (margin, size, style), what a binding yields or why it's empty, the XAML line behind an element, live edits, and UI review comments left in the app. To click, type, read text or screenshot, use winapp-ui-automation.