Scion is a multi-agent orchestration platform that runs several isolated agents concurrently in containers, optionally giving each one its own workspace and credentials. It is used to coordinate coding and other research or operations tasks across local machines, remote virtual machines, and Kubernetes clusters. Catalogue add-ons provide workflows and controls for operating Scion.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add GoogleCloudPlatform/scion --skill scion-messaginggit clone --depth 1 https://github.com/GoogleCloudPlatform/scionWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/googlecloudplatform/scion/scion-messaging)<a href="https://agentmods.dev/skills/googlecloudplatform/scion/scion-messaging"><img src="https://agentmods.dev/badge/skills/googlecloudplatform/scion/scion-messaging/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/googlecloudplatform/scion/scion-messaging"><img src="https://agentmods.dev/badge/skills/googlecloudplatform/scion/scion-messaging.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00041 | $0.04662 |
| Opus 5.5 | $0.00016 | $0.01865 |
| Sonnet 5.5 | $0.00008 | $0.00932 |
| Haiku 4.5 | $0.00004 | $0.00466 |
Grade A, and why
scion-messaging scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 16d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scion Messaging
Overview
In this multi-agent orchestration environment, the primary way to communicate is via the scion message command. This skill codifies the patterns required for reliable, high-signal communication within the Scion ecosystem.
When to Use
- When starting a task that requires coordination with other agents.
- When you need to provide a status update or ask a question to a user.
- When forwarding feedback or unblocking another agent.
- When you need to send literal keystrokes to an agent's terminal (via
scion keys). - When scheduling messages for the future (via
scion schedule create).
When NOT to use: For internal cognitive work or logging that doesn't need to be seen by others. Never use messaging for banter or repetitive, low-signal status updates.
Recipient Types
Choosing the right recipient is critical to avoid spam and ensure the message reaches the intended target.
@<agent-name>: Send a message to a specific agent (e.g.,scion message @tech-lead "..."). This addresses the agent's conversation directly.@<email>: Send a global DM to a user by email address (e.g.,scion message @[email protected] "...").group[a,b,...]: Group messaging to a specific list of recipients (Hub mode only).conv:<uuid>: Address a conversation by ID. This is the preferred and usually correct way to reply to any message you received — pass theconversation.idfield from the inbound message envelope. Prefer this over addressing the sender directly (@<email>) when replying, especially in a group conversation: addressing a user directly opens (or continues) that user's native-surface DM conversation, a different conversation from the one the message came from. Reply with@<email>only when you are deliberately starting a new, separate DM — not when replying to something you were addressed in. View its details withscion conversation get conv:<uuid>; see thescion-conversationskill.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 16d ago Changed · +9 lines fd4d88bac616
- 19d ago Changed · +16 lines dd3e781cf6f5
- 21d ago Changed · +46 lines 0c08105f218e
- 23d ago Changed 6293346f60c1
- 26d ago Changed e98b56336cae
- 1mo ago Changed · +5 lines 1bb52e95c5f1
- 1mo ago Changed · +22 lines c9e8a8d6666e
- 1mo ago Changed · -2 lines · -9 tokens per session 0ab425321e32
- 1mo ago Changed · -2 lines c21cb0a94661
- 1mo ago First seen · 204 lines · 50 tokens per session scan A c83ec1986933
scion-messaging is a skill published in the GitHub repository GoogleCloudPlatform/scion (2,029 stars, last pushed today), licensed Apache-2.0. It adds 41 tokens to every session and 4,662 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.