ensemblr-hq/ensemblr
Desktop orchestrator for Pi and Claude Code. Every stream of work gets its own git worktree, and an agent can drive the app itself — spawn sub-agents, delegate, integrate.
ARCHETYPE
YOLO Cowboy
Permissions? Never heard of 'em. Ships at the speed of `--dangerously-skip-permissions`.
Copy this rig
# review before running: this installs third-party code $ claude mcp add shadcn -- bunx shadcn@latest mcp $ claude mcp add fallow -- fallow-mcp $ npx degit ensemblr-hq/ensemblr/.claude ./rig-ensemblr # inspect, then merge into .claude/
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ claude mcp add shadcn -- bunx shadcn@latest mcp $ claude mcp add fallow -- fallow-mcp
$ npx degit ensemblr-hq/ensemblr/.agents/skills/fallow .claude/skills/fallow $ npx degit ensemblr-hq/ensemblr/.agents/skills/playwright-cli .claude/skills/playwright-cli $ npx degit ensemblr-hq/ensemblr/.agents/skills/react-doctor .claude/skills/react-doctor $ npx degit ensemblr-hq/ensemblr/.agents/skills/shadcn .claude/skills/shadcn $ npx degit ensemblr-hq/ensemblr/apps/desktop/resources/agent-skills-architecture/skills/architecture-diagram .claude/skills/architecture-diagram $ npx degit ensemblr-hq/ensemblr/apps/desktop/resources/agent-skills/skills/ensemblr .claude/skills/ensemblr
Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)"
]
},
"hooks": {
"PreToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": ".claude/hooks/enforce-bun.sh"
}
]
}
]
}
} MCP servers (2)
| server | source | est. tokens |
|---|---|---|
| shadcn/ui · "shadcn" | npm | 2.0k |
| fallow-mcp · "fallow" | binary | 2.5k |
Skills (6)
Hooks (1)
| event | matcher | runs |
|---|---|---|
| PreToolUse | Bash | .claude/hooks/enforce-bun.sh |
Plugins (1)
fallow@fallow-skills
Permissions
deny (3)
Read(./.env)
Read(./.env.*)
Read(**/.env)
ask (0)
—
allow (8)
Bash
Read
Edit
Write
WebFetch
Agent
mcp__claude_ai_Linear
mcp__plugin_context-mode_context-mode
Similar rigs
HatriGt/agent-sandbox
A cloud sandbox for coding agents, on your own server. Start a run from the dashboard, from any agentic IDE (Cursor, Claude Code, Codex, VS Code), or from a script — it runs in an isolated KVM microVM and streams back live.
Pragmatist 391 tok · · Q0
SalvadorCardona/ponos
Write the ticket, it comes back done. A self-hosted harness around Claude Code that runs your tasks — code, writing, external actions — each on its own git worktree. Works with Notion, GitHub, Telegram and Slack, or none of them.
Pragmatist 4.4k tok · · Q15
knutkirkhorn/dotfiles
My personal dotfiles
Pragmatist 6.2k tok · · Q0
flolefebvre/claude-convo-analyzer
A local-only web app that analyzes your Claude Code conversation logs for per-conversation token usage and cost.
Pragmatist 2.5k tok · · Q0