madeinorbit/podium
Podium is an ADE with built-in cross-harness subagents and agent communication. It runs on desktop, mobile and VPS.
field: Developer tools
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
GUARDRAILS
3/5
Blocks destructive commands · Pre-tool screening hook · No YOLO mode · details
Quality 38/100 Guardrails v2
Copy this rig
# review before running: this installs third-party code
$ npx degit madeinorbit/podium/.claude ./rig-podium # 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.
$ npx degit madeinorbit/podium/.claude/skills/impeccable .claude/skills/impeccable Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.
{
"permissions": {
"deny": [
"Bash(tsc:*)",
"Bash(tsgo:*)",
"Bash(vitest:*)",
"Bash(playwright:*)",
"Bash(turbo:*)",
"Bash(bunx tsc:*)",
"Bash(bunx tsgo:*)",
"Bash(bunx vitest:*)",
"Bash(bunx playwright:*)",
"Bash(bunx turbo:*)",
"Bash(bun x tsc:*)",
"Bash(bun x tsgo:*)",
"Bash(bun x vitest:*)",
"Bash(npx tsc:*)",
"Bash(npx tsgo:*)",
"Bash(npx vitest:*)",
"Bash(npx playwright:*)",
"Bash(bun test:*)",
"Bash(bun --bun vitest:*)",
"Bash(bun --bun node_modules/vitest:*)",
"Bash(node_modules/.bin/tsc:*)",
"Bash(node_modules/.bin/tsgo:*)",
"Bash(node_modules/.bin/vitest:*)",
"Bash(./node_modules/.bin/tsc:*)",
"Bash(./node_modules/.bin/tsgo:*)",
"Bash(./node_modules/.bin/vitest:*)"
]
},
"hooks": {
"PreToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "bun \"$CLAUDE_PROJECT_DIR/scripts/agent-command-guard.ts\""
}
]
}
]
}
} Skills (1)
Hooks (1)
| event | matcher | runs |
|---|---|---|
| PreToolUse | Bash | bun "$CLAUDE_PROJECT_DIR/scripts/agent-command-guard.ts" |
Permissions
deny (26)
Bash(tsc:*)
Bash(tsgo:*)
Bash(vitest:*)
Bash(playwright:*)
Bash(turbo:*)
Bash(bunx tsc:*)
Bash(bunx tsgo:*)
Bash(bunx vitest:*)
Bash(bunx playwright:*)
Bash(bunx turbo:*)
Bash(bun x tsc:*)
Bash(bun x tsgo:*)
Bash(bun x vitest:*)
Bash(npx tsc:*)
Bash(npx tsgo:*)
Bash(npx vitest:*)
Bash(npx playwright:*)
Bash(bun test:*)
Bash(bun --bun vitest:*)
Bash(bun --bun node_modules/vitest:*)
Bash(node_modules/.bin/tsc:*)
Bash(node_modules/.bin/tsgo:*)
Bash(node_modules/.bin/vitest:*)
Bash(./node_modules/.bin/tsc:*)
Bash(./node_modules/.bin/tsgo:*)
Bash(./node_modules/.bin/vitest:*)
ask (0)
—
allow (0)
—
Similar rigs
Anmol-Srv/sigil
Persistent memory for AI coding agents. Local-first. MCP-native. Auto-captured from Claude Code, shared with Cursor, Codex, and any MCP client. Your agents don't remember what you decided yesterday. Sigil does. Every prompt, every session,
Minimalist 223 tok · · Q0
Brandon1138/cyberdeck
Provider-neutral local control plane for durable AI coding-agent sessions
Pragmatist 5.6k tok · · Q0
dnsatgit/aigod
Your AI agent workflow is mid. This fixes that. A structured prompt engineering framework for Claude Code. It lives in your git repo as a set of markdown files, JSON configs, and eval templates that give Claude Code consistent behavior, dom
Pragmatist 3.5k tok · · Q3
jmcelreavey/devhub
A desktop workspace for your dev day: Jira, GitHub PRs, notes and AI coding agents (Claude, Cursor, Codex via Paseo) in one place. Mac, Windows, Linux.
Minimalist 2.4k tok · · Q3