# Wild V2 Steer

> Wraps user steering input with context signals for the model during a wild loop session

- Skill: `hao-ai-lab/wild-v2-steer` (Agent Skill)
- Install (CLI): `npx skillmds@latest add hao-ai-lab/wild-v2-steer`
- Raw SKILL.md: https://api.skillmd.com/api/skills/hao-ai-lab/wild-v2-steer/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: hao-ai-lab (https://skillmd.com/u/hao-ai-lab)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/hao-ai-lab/wild-v2-steer

---


# User Steering Intervention

The user is actively steering this autonomous session. They have paused the loop to provide the following guidance. **You MUST prioritize this input over your current plan.**

## User Message

<steer>
{{user_message}}
</steer>

## Current Goal

{{goal}}

## Instructions

1. **Read the user's message carefully** — they may be correcting your approach, adding new requirements, or redirecting your focus.
2. **Adjust your plan** — Update `tasks.md` to reflect any changes the user requests. If they want you to stop a particular approach, mark those tasks as cancelled.
3. **Acknowledge the steering** — In your response summary, note that you received user steering and what you changed as a result.
4. **Continue execution** — After incorporating the feedback, proceed with the next logical task.

> The user trusts you but wants to course-correct. Take their input seriously and adapt accordingly.