Wf UI — Design skill for Claude Code
Open the Harness browser control panel for task capsules, workflow graphs, agent peers, settings, and terminal observability.
How to install Wf UI
Installs to ~/.claude/commands/zingspark-create-harness-vibe-coding-wf-ui.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/zingspark/create-harness-vibe-coding/HEAD/.claude/commands/wf-ui.md -o ~/.claude/commands/zingspark-create-harness-vibe-coding-wf-ui.md Restart Claude Code, or start a new session, for it to be picked up.
What Wf UI does
Open the Harness browser control panel for task capsules, workflow graphs, agent peers, settings, and terminal observability.
Alternatives in Design
- Kode Agent — Kode Agent — Design for post-human workflows 5k ★
- Ovis — Ovis (formerly herdr web UI): free, open-source browser and phone client for herdr 1.4k ★
- Taiyi Forge — TaiyiForge engine control — init, next, harness, continue (OMX-style) 881 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Claude Widget Kit
Claude Widget Kit: a mods pack for Claude Code. Live usage rings, effort meter, task ETA and an agents panel,
Settings
Work with the Settings panel and UI preferences
Add Admin Panel
Create basic admin dashboard with protected routes. Implement admin route protection with role-based access co
Agent Mode Change
Agent-mode floating window for DeepSeek Harness (dsh): a draggable Web-UI panel that switches a session's syst
File Browser Agent
A Windows desktop app (Electron) that works like a file browser, with a chat panel in the style of Claude Code
Litellm Agent Runtime
Coding-agent runtime that runs inside per-session VMs provisioned by LiteLLM proxy. Generic by design — custom
Related Agents
macOS System Operator
Mac housekeeping and CLI operations — installing tools (brew/npm/curl installers), logins that open a browser,
Browser Scout Sonnet
Default browser tier. Read-only work in the user's real Chrome — open a ticket, a chat channel, a dashboard or
Mp Adversarial Reviewer
Adversarial second-opinion review of a completed masterplan task. The harness runs this agent on the routing p