# Browser T3 Scenarios

> Use this skill when implementing, extending, or validating the T3 end-to-end browser scenarios in `/home/rocm/clawcontrol/browser`, especially the shared scenario runner in `browser/src/end_to_end.py`, the fake-data T3 suite in `browser/tests/test_end_to_end_scenarios.py`, and related evidence, routing, PageAgent, or anti-bot scenario work.

- Skill: `bojak83318/browser-t3-scenarios` (Agent Skill)
- Install (CLI): `npx skillmds@latest add bojak83318/browser-t3-scenarios`
- Raw SKILL.md: https://api.skillmd.com/api/skills/bojak83318/browser-t3-scenarios/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: bojak83318 (https://skillmd.com/u/bojak83318)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/bojak83318/browser-t3-scenarios

---


# Browser T3 Scenarios (Codex Wrapper)

**Activation Note:** This skill is a wrapper for the Codex skill in container `57db90a0b891`. To execute tasks, use `codex exec` non-interactively.

## Remote Execution Command
`incus exec kasm-vm -- docker exec 57db90a0b891 codex exec --skip-git-repo-check --dangerously-bypass-approvals-and-sandbox "[PROMPT]"`

## original Skill Content

Use this skill for Phase 5 browser work in this repo when the task is about task-driven end-to-end scenarios rather than isolated T1/T2 helpers.

### Scope

- Treat `/home/rocm/clawcontrol/implementation.md` as the phase plan.
- Treat `/home/rocm/clawcontrol/TASK.md` as the progress tracker.
- Treat `/home/rocm/clawcontrol/browser/PRD-browser-non-browser.md` section 9 as the T3 contract.
- Treat `/home/rocm/clawcontrol/browser/src/end_to_end.py` as the shared T3 runner contract.
- Treat `/home/rocm/clawcontrol/browser/tests/test_end_to_end_scenarios.py` as the baseline T3 fake-data suite.

### Workflow

1. Confirm which T3 slice is unfinished or needs revision.
2. Use the remote execution command to drive Codex in the container.
3. Verify with focused browser tests inside the container via `codex exec`.