nyxene/orrery
A working method for software written by AI agents and directed by people: consensus planning, fan-out execution, debt that gets paid, rules earned from real incidents, and guards that fire before every shell call.
stack: Shell
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code
$ npx degit nyxene/orrery/.claude ./rig-orrery # 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 nyxene/orrery/skills/debt .claude/skills/debt $ npx degit nyxene/orrery/skills/diagnose .claude/skills/diagnose $ npx degit nyxene/orrery/skills/doctor .claude/skills/doctor $ npx degit nyxene/orrery/skills/feedback .claude/skills/feedback $ npx degit nyxene/orrery/skills/frame .claude/skills/frame $ npx degit nyxene/orrery/skills/handoff .claude/skills/handoff $ npx degit nyxene/orrery/skills/learn .claude/skills/learn $ npx degit nyxene/orrery/skills/pare .claude/skills/pare $ npx degit nyxene/orrery/skills/plan .claude/skills/plan $ npx degit nyxene/orrery/skills/review .claude/skills/review $ npx degit nyxene/orrery/skills/sharpen .claude/skills/sharpen $ npx degit nyxene/orrery/skills/verify .claude/skills/verify
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 (12)
Similar rigs
mindmakr/coordinator
A lead for your coding agent: asks everything up front, then runs work through builders and blind critics until it meets a bar you can check. Hard stops, durable state, lessons that improve every run.
Skill Collector 1.6k tok · · Q5
Shortytheman/niklas-toolkit
Claude Code plugin marketplace: Godot 4 export, run, screenshot and doctor tools, a GDScript lint hook, and a custom MCP server for Godot projects
Skill Collector 3.4k tok · · Q0
mustafarslan/monerex
An AI-driven development lifecycle for Claude Code: agents do the work in stages, hooks hold the rules, and you approve the plan, what is posted under your name, and the merge.
Skill Collector 735 tok · · Q0
mlophez/polix-ai
Declarative guardrails for Claude Code: one polix.yaml decides what the agent may not touch, what must pass and what runs at every step.
Automator 1.1k tok · · Q15