debugging-skill

A procedure for checking a web interface after code changes by starting a fresh browser session and repeating the complete user flow.

In plain words
What is it for?
Use it to verify the standalone test app first, then inspect the interface, follow the user journey, and monitor browser errors.
Why use it?
It catches stale browser state, runtime errors, warnings, and broken interactions before more work continues.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/bitovi/convey/debugging
Any agent
npx skills add bitovi/convey --skill debugging
Clone the repo
git clone --depth 1 https://github.com/bitovi/convey

Made for: Claude Code, Codex.

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 707 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00033 $0.00707
Opus 5 $0.00016 $0.00353
Sonnet 5 $0.00007 $0.00141
Haiku 4.5 $0.00003 $0.00071

Measured 2d ago against content hash 99fe7d2f52bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

debugging-skill 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 2d 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.

.github/skills/debugging/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debugging Skill: Error-Free UI Verification

Purpose

Ensure that after any code change, the app is fully reloaded, the user flow is tested from the beginning, and no runtime errors or warnings are present before continuing with feature work or test automation.

Workflow

  1. Restart Browser Session

    • After any file change or hot-reload, always start a new browser session (do not reuse previous state).
    • This ensures no stale state or session issues.
  2. Start with the Test App (http://localhost:5173)

    • Always verify behavior on the standalone test app first, before testing in Storybook or other environments.
    • The test app runs directly in the page (no iframes), making it easier to inspect shadow DOM elements, debug overlay state, and interact with the bottom toolbar.
    • Only move to Storybook (SB8/SB10) or other environments after confirming the feature works in the test app.
  3. Walk Through Full User Flow

    • Navigate to the target page.
    • Interact with the UI as a real user would.
  4. Monitor for Errors and Warnings

    • Capture all browser console logs, errors, and exceptions during navigation and interaction.
    • Do not proceed if any runtime errors or warnings are present.
    • Only continue with feature work or test automation when the UI is confirmed error-free.

Clicking the Toggle Button (Playwright MCP)

The Convey toggle button (aria-label="Open Convey inspector") lives inside a shadow DOM (#tw-visual-editor-host). Playwright MCP's click_element and snapshot tools cannot reach shadow DOM elements directly.

Always use page.evaluate() to click it:

await page.waitForFunction(() => {
  const host = document.querySelector('#tw-visual-editor-host') as HTMLElement;
  return !!(host?.shadowRoot?.querySelector('.toggle-btn'));
}, { timeout: 5000 });

await page.evaluate(() => {
  const host = document.querySelector('#tw-visual-editor-host') as HTMLElement;
  const btn = host.shadowRoot!.querySelector('.toggle-btn') as HTMLButtonElement;
  btn.click();
});

Read the full file on GitHub · 75 lines

Changes

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.

  1. 2d ago First seen · 75 lines · 33 tokens per session scan A 99fe7d2f52bb

Subscribe to this mod's changes

debugging-skill is a skill published in the GitHub repository bitovi/convey (46 stars, last pushed 16d ago), licensed MIT. It adds 33 tokens to every session and 707 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 2026-08-30.