AgentArmorHQ
Sign in

sno-station-skills

Skill · GitHub · ★ 883 · graded 2026-10-26Source linked

Sno Station Skills: 31 tested skills that turn Claude Code and Codex into one working team. Cross-vendor peer review, automatic handoff when an agent hits its quota, a one-page morning brief, work orders with proof, and a nightly loop that learns from your own sessions. Open source, installed with one sno setup.

No outside reports on file

Use Sno Station Skills only with non-sensitive projects; the learning loop and agent coordination add complexity that could expose mistakes or private work details.

Based on public adoption and transparency signals as of Oct 26, 2026. Our opinion, not a code audit or security guarantee.

Was this verdict for Sno Station Skills helpful?

What it can access

  • Local filesNo local folder access notedLOW
  • Command executionNo shell command runner notedLOW
  • Network reachConnects to outside service APINOTED
  • CredentialsNo API token requiredLOW
  • Package sourceGitHub (sno-ai/sno-station-skills)PUBLIC

Inferred from this listing’s public package details and description. Check the project’s source before installing.

Install

No npm or PyPI package is listed. Install from source: github.com/sno-ai/sno-station-skills ↗

All setup options ↓

Check this skillWatch it in my stackCompareREADME badgeView project

Everything known

We found nothing about this project in the sources we read (last checked 2026-10-30). That does not mean it has no problems.

0 incidents · 0 advisories · 0 news articles · 0 community threads · checked 2026-10-30

Popularity grade: C (from public signals such as stars and downloads, not a code review). Graded 2026-10-26.

Sources we read: OSV, GitHub Advisory Database, CISA Known Exploited Vulnerabilities, 44 security news feeds and our incident library. Last checked 2026-10-30.

Check a specific version →

About Sno Station Skills

Sno Station Skills is a collection of 31 pre-built tasks designed to help Claude (an AI assistant) and Codex (a code model) work together as a team. It includes features like automatic handoff when one agent reaches its work limit, daily briefings, work order tracking with proof, and a system that learns from your past sessions.

Who it’s for

Teams using Claude and Codex who want them to coordinate on projects without manual switching. Best for organizations that need work tracking, proof of completion, and agents that improve over time based on real workflows.

Alternatives

  • LangChain Agent Orchestration: Framework for coordinating multiple AI agents with customizable workflows.
  • AutoGen (Microsoft): Multi-agent framework that lets different models collaborate on tasks.
  • Crew AI: Simpler multi-agent coordination for small teams.
  • n8n or Zapier: General workflow automation that can chain AI models without custom code.

Setup

Check these steps against the project’s own instructions before running anything.

Follow the project's README at https://github.com/sno-ai/sno-station-skills (opens external site) for installation steps. The project mentions sno setup as the installation method, but exact commands should come from their documentation.

Why this grade

CC — Moderate risk signals

Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.

Popularity and upkeep

32/100
GitHub stars
883
Listing last refreshed
2026-10-30

These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.

Risks to watch for

  • Agent coordination overhead: Multiple AI agents working together can multiply mistakes or cause unpredictable behavior if one agent misunderstands the other's output.
  • Learning loop risks: A nightly system that learns from your sessions could reinforce errors or biases if the training data includes mistakes.
  • Access to work orders and proofs: The skill can create, read, and modify records of your work—attackers or misconfigurations could expose sensitive project data.
  • Automatic handoff logic: If the quota-switching system has bugs, an agent might hand off work mid-task, leaving incomplete results or corrupted state.
  • Third-party model dependence: Relies on Claude and Codex; if either service changes or has downtime, the whole workflow breaks.

How to lower the risk

Least-privilege permissions

  • Restrict agent access to only the files and APIs needed for each specific task.
  • Do not give agents credentials for production systems.

Network isolation

  • Run agents in a sandboxed environment if handling business-critical work.
  • Disable internet access unless agents specifically need external APIs.

Monitoring

  • Log all handoffs between agents and review them regularly for errors.
  • Audit the nightly learning loop to ensure it is not picking up sensitive data.

Red flags to watch for

  • Agents repeating the same mistakes after the nightly update suggests the learning loop is broken.
  • Sudden slowdowns or failed handoffs may indicate a quota or coordination bug.
  • Missing or corrupted work order records could mean data loss or tampering.

Questions

How do I install Sno Station Skills?

Sno Station Skills does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/sno-ai/sno-station-skills.

Are there security reports about Sno Station Skills?

No reports found for this package in our research (last checked 2026-10-30). Sno Station Skills currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include agent coordination overhead, learning loop risks, access to work orders and proofs.

Is Sno Station Skills actively maintained?

Sno Station Skills has 883 GitHub stars. Our directory data was last refreshed on 2026-10-30. Check recent commit activity, release tags, and open issues at github.com/sno-ai/sno-station-skills before pinning it in production.

What are alternatives to Sno Station Skills?

Notable alternatives to Sno Station Skills include LangChain Agent Orchestration (Framework for coordinating multiple AI agents with customizable workflows), AutoGen (Microsoft) (Multi-agent framework that lets different models collaborate on tasks), Crew AI (Simpler multi-agent coordination for small teams), n8n or Zapier (General workflow automation that can chain AI models without custom code). You can also compare Sno Station Skills side by side with other skills in the Related tools section on this page.

README badge and team notes

Maintain or use Sno Station Skills? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.

AgentArmorHQ Risk Grade C for Sno Station Skills

GitHub README Markdown:

markdown
[![AgentArmorHQ Risk Grade for Sno Station Skills](https://agentarmorhq.com/api/badge/sno-ai-sno-station-skills)](https://agentarmorhq.com/skills/sno-ai-sno-station-skills)

HTML embed:

html
<a href="https://agentarmorhq.com/skills/sno-ai-sno-station-skills"><img src="https://agentarmorhq.com/api/badge/sno-ai-sno-station-skills" alt="AgentArmorHQ Risk Grade for Sno Station Skills" height="20" /></a>

Terminal check:

terminal
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "sno-ai-sno-station-skills"

Share with your security lead

Need sign-off to use sno-station-skills? Copy this note for Slack, a ticket or a pull request.

### AgentArmorHQ Security Review Memo: sno-station-skills
- **Listing URL:** https://agentarmorhq.com/skills/sno-ai-sno-station-skills
- **Type:** AI agent skill
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 883 GitHub stars

#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** No shell command runner noted
- **Network reach:** Connects to outside service API
- **Credentials:** No API token required
- **Package source:** GitHub (sno-ai/sno-station-skills)

#### Recommended Hardened Setup
- **Source Repo:** https://github.com/sno-ai/sno-station-skills
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.

_Based on public adoption and transparency signals as of Oct 26, 2026. Our opinion, not a code audit or security guarantee._

Key facts

Type
AI agent skill
Publisher
sno-ai
Source code
github.com/sno-ai/sno-station-skills
Est. context load
~107 tokens idle · ~500 tokens when active (on-demand skill)
Popularity
883 GitHub stars
Last updated
2026-10-30
Last graded
2026-10-26

Community

Discussions for Sno Station Skills

Ask questions or share configuration tips. Governed by our Community Rules & Terms.

No posts match this filter yet.

Be the first to ask a question or share a working tip.

Was this listing for Sno Station Skills helpful?

Check before you install, in Claude

Your assistant answers Block, Review or No known issues for any package before it installs it.

Get this check inside Claude