From pipecrew
Live browser UI for PipeCrew agent pipeline runs. Shows characters as queued/working/done with pyramid tiers, fed via SSE. Auto-started by /deliver skill.
How this skill is triggered — by the user, by Claude, or both
Slash command
/pipecrew:site-viewThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Live visualizer for a `/deliver` run — the crew's work site. One character per pipeline role animates from queued → working → done as the orchestrator progresses; the pyramid's tiers rise as work completes. A yellow banner surfaces whenever the orchestrator is paused for user input.
Live visualizer for a /deliver run — the crew's work site. One character per pipeline role animates from queued → working → done as the orchestrator progresses; the pyramid's tiers rise as work completes. A yellow banner surfaces whenever the orchestrator is paused for user input.
Auto-started by /deliver at Pre-flight. Run manually with /site-view or node server.js ….
/site-view [--workspace=<slug>] [--run-id=<id>] [--port=5173]
Flags:
--workspace=<slug> — workspace name. Auto-detected when only one exists under {workspace_root}/.--run-id=<id> — specific feature run to watch. Defaults to most-recent run under runs/deliver/.--port=<n> — initial port. Auto-increments up to 10 on EADDRINUSE.When the user invokes /site-view:
~/.claude/plugins/marketplaces/local/pipecrew/).run_in_background: true:
node {plugin_dir}/skills/site-view/server.js --workspace={slug} [--run-id={id}] [--port={n}]
All details — data sources, character roster, gate contract, multi-run handling, state shape, troubleshooting — are in {plugin_dir}/docs/site-view.md. Consult that doc for anything beyond the basic launch flow.
npx claudepluginhub pipecrew-ai/pipecrew --plugin pipecrewLaunches a machine-wide dashboard showing all active Claude Code sessions with token usage, sub-agents, and needs-approval badges. Complements per-run /site-view.
Opens local web dashboard to browse workflow runs, inspect step timelines, view artifacts, and diff executions side-by-side.
Open the web UI to visually inspect, edit, and run the benchmark pipeline. Use when the user wants a visual interface for their pipeline.