# Agent Browser Issue

> Open a concise GitHub follow-up for reusable browser-use limitations. Use when browser automation is blocked by a likely tool-side issue that is worth fixing separately, especially for clicks, dropdowns, file inputs, focus traps, or other repeatable agent/browser failures.

- Skill: `udecode/agent-browser-issue-2` (Agent Skill)
- Install (CLI): `npx get-skill add udecode/agent-browser-issue-2`
- Raw SKILL.md: https://api.skillmd.com/api/skills/udecode/agent-browser-issue-2/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: udecode (https://skillmd.com/u/udecode)
- Updated: 2026-09-21
- Page: https://skillmd.com/skills/udecode/agent-browser-issue-2

---


# Agent Browser Issue

Handle $ARGUMENTS.

Use this only for likely reusable agent or browser tooling bugs. Do not use it for:

- auth or SSO gates
- manual human gates
- product bugs on the site itself
- one-off flaky noise with no minimal repro

## Collect

Capture only the minimum:

- page or URL
- action attempted
- exact block
- expected vs actual
- minimal repro
- screenshot only if it adds signal

## Issue

Open a GitHub issue with:

- a short title focused on the browser or tool failure
- label `agent:browser`
- concise body

Body shape:

```md
## URL
<url>

## Action
<what the agent tried>

## Block
<what failed>

## Expected
<what should have happened>

## Actual
<what happened instead>

## Repro
1. ...
2. ...
3. ...
```

## After

- if the browser or tool failure exposes a user-action parity gap, load
  `agent-native-reviewer` and note that gap in the issue
- link the issue in the task caveat or handoff
- keep moving if the product task is still otherwise fixable

