agentrigs
+ submit rig
~ / rigs / sno-ai / sno-station

sno-ai/sno-station

Sno Station — your Claude Code and Codex working as one squad on your own machine. Shared encrypted memory, agent-to-agent messaging (Reach), squad skills for handoff and cross-vendor review, and a nightly loop that rewrites the agents' own

↗ GitHub ★ 476 Apache-2.0 updated today project Codex
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
~941 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

$ git clone --depth 1 https://github.com/sno-ai/sno-station

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 sno-ai/sno-station/apps/mem-claude/skills/sno-mem-claude .claude/skills/sno-mem-claude
$ npx degit sno-ai/sno-station/apps/mem-codex/skills/sno-mem-codex .claude/skills/sno-mem-codex
$ npx degit sno-ai/sno-station/packages/memory/skills/extract-atomic-memory .claude/skills/extract-atomic-memory
$ npx degit sno-ai/sno-station/packages/memory/skills/judge-group-closure .claude/skills/judge-group-closure
$ npx degit sno-ai/sno-station/packages/memory/skills/judge-rem-memory-updates .claude/skills/judge-rem-memory-updates
$ npx degit sno-ai/sno-station/packages/memory/skills/judge-retired-position .claude/skills/judge-retired-position
$ npx degit sno-ai/sno-station/packages/memory/skills/judge-task-lifecycle .claude/skills/judge-task-lifecycle
$ npx degit sno-ai/sno-station/packages/memory/skills/key-state-attribute .claude/skills/key-state-attribute
$ npx degit sno-ai/sno-station/packages/memory/skills/resolve-entity-identity .claude/skills/resolve-entity-identity
$ npx degit sno-ai/sno-station/packages/memory/skills/resolve-relative-time .claude/skills/resolve-relative-time

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(.env)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(~/.aws/**)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(sudo:*)",
      "Bash(git reset --hard*)",
      "Bash(git reset --hard:*)",
      "Read(.env.*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(rm:*)",
      "Bash(git rebase *)",
      "Bash(wget *)",
      "Bash(npm publish:*)",
      "Bash(git commit *)",
      "Bash(gh pr merge *)"
    ]
  }
}

Skills (10)

sno-mem-claudesno-mem-codexextract-atomic-memoryjudge-group-closurejudge-rem-memory-updatesjudge-retired-positionjudge-task-lifecyclekey-state-attributeresolve-entity-identityresolve-relative-time

Similar rigs

obra/superpowers
An agentic skills framework & software development methodology that works.
★ 294k project CodexGemini CLI 15 skills 12d ago
Skill Collector 3.0k tok ·
anthropics/skills
Public repository for Agent Skills
★ 180k collection Claude Code 19 skills 4d ago
Skill Collector 1.3k tok ·
anthropics/claude-code
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
★ 149k project Claude Code 10 skills 6d ago
Skill Collector 1.4k tok ·
JuliusBrussee/caveman
🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
★ 110k project Claude CodeCodexGemini CLI 22 skills 3 agents 1d ago
Skill Collector 16.5k tok ·
copied ✓