#269269th of 572 in Skills, plugins and prompts
sno-station
Coordinates Claude Code, Codex and Cursor as a team with handoff and review
- Stars
- 1k
- License
- Apache-2.0
- Last commit
- Nov 2026
- Last release
- Nov 2026
- Language
- TypeScript
0 on 16 Sept 20261,028 on 18 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Sno Station sits on top of coding agents you already run (Claude Code, Codex, Cursor, Hermes Agent, OpenClaw) and adds messaging between them, paired build and review sessions in tmux, scheduled tasks, and shared memory. It installs skills such as rotate-agent and peer-review, and a nightly Self Learning pass proposes skill edits that you accept with `sno rem-reflect accept`. It runs on your own machine and needs no API key.
Who it is for: Developers running several coding agents who want handoff and cross-review
Strengths
- Hands a task to another vendor's agent at 2% quota, continuing from the exact commit
- Reviews run in a fresh session by a different agent, with capped review rounds
- Nightly lesson proposals change nothing until a person runs the accept command
- Raw evidence from a real overnight handover is published in the repo
Weaknesses
- Timed tasks start Claude Code and Codex only; full-reboot recovery is untested
- Hermes and OpenClaw lack mail pickup at turn end; Cursor lacks approval notices
- Cross-machine messaging needs both machines on the same LAN or Tailscale
- Unlinked computers get one tenth of the free sno.ai allowance
What it needs
- Needs tmux, Tailscale (optional, cross-machine), sno.ai account (free, for full allowance)
- Models: Claude Code, Codex, Cursor, Hermes Agent, OpenClaw
What changed
From the release notes. No flag means the note does not say so, not that the upgrade is safe.
Also in Skills, plugins and prompts
See all 572| Rank | Project | Score |
|---|---|---|
| 1 | claude-memPersistent cross-session memory plugin for Claude Code and other coding agents | 97 out of 100 |
| 2 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 97 out of 100 |
| 3 | gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles | 96 out of 100 |
| #4 | rufloAgent harness adding swarms, memory and hooks to Claude Code and Codex | 96 out of 100 |
| #5 | eccAgents, skills, hooks and memory bundle for Claude Code and other harnesses | 95 out of 100 |