crafts69guy/orchestra
Orchestrator + subagents workflow plugin for Claude Code and Codex: parallel implementers in git worktrees (worktrunk).
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code $ npx degit crafts69guy/orchestra/agents ./rig-orchestra/agents $ npx degit crafts69guy/orchestra/skills ./rig-orchestra/skills $ npx degit crafts69guy/orchestra/hooks ./rig-orchestra/hooks
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 crafts69guy/orchestra/skills/dispatch .claude/skills/dispatch $ npx degit crafts69guy/orchestra/skills/plan .claude/skills/plan $ npx degit crafts69guy/orchestra/skills/reflect .claude/skills/reflect
$ curl -fsSL --create-dirs -o .claude/agents/implementer.md https://raw.githubusercontent.<redacted>.md $ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/crafts69guy/orchestra/main/agents/reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/scoper.md https://raw.githubusercontent.com/crafts69guy/orchestra/main/agents/scoper.md $ curl -fsSL --create-dirs -o .claude/agents/shipper.md https://raw.githubusercontent.com/crafts69guy/orchestra/main/agents/shipper.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (3)
Subagents (4)
| implementer model: sonnet | orc workflow: writes, modifies or refactors code and adds or fixes tests for a well-defined plan. For changes spanning 2+ files or needing more than one edit-and-test cycle. |
| reviewer model: opus | orc workflow: independent, read-only code review. For explicit requests or risky changes (security, concurrency, migrations, public APIs). Never modifies files. |
| scoper model: haiku | orc workflow: read-only scoping of a non-trivial task in unfamiliar code. Gathers facts and returns a brief. |
| shipper model: haiku | orc workflow: commits, pushes and opens PRs after review is done. Handles only git and GitHub. |
Similar rigs
Saba-Var/claude-ward
A read-only tripwire that watches Claude Code's local config and reports suspicious changes.
Pragmatist 1.8k tok · · Q21
yopazerbot/brieltje
Smetlede and Briel (Lede, Belgium) in 3D: a walkable village in the browser, alone or with up to 16 friends. Explore, Paintball, Action, and endless waves of Zombies. Three.js and Blender, made with Claude Code and OpenAI Codex..
Pragmatist 4.7k tok · · Q8
chrille0313/agentic-monorepo-template
Stack-agnostic monorepo template where agents are the workflow: PM → implementer → fresh-context reviewer loops via Claude Code subagents, skills, and GitHub Actions
Pragmatist 1.5k tok · · Q15
SavenkoSy/sin-flow
Ticket-to-PR flow for a live codebase, as a Claude Code plugin: setup, sync, ingest, plan, exec, review and learning stages.
Orchestrator 1.4k tok · · Q3