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-conversationgit 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-conversation)<a href="https://agentmods.dev/skills/googlecloudplatform/scion/scion-conversation"><img src="https://agentmods.dev/badge/skills/googlecloudplatform/scion/scion-conversation/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-conversation"><img src="https://agentmods.dev/badge/skills/googlecloudplatform/scion/scion-conversation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00040 | $0.00927 |
| Opus 5.5 | $0.00016 | $0.00371 |
| Sonnet 5.5 | $0.00008 | $0.00185 |
| Haiku 4.5 | $0.00004 | $0.00093 |
Grade A, and why
scion-conversation 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 12d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scion Conversation
Overview
Use scion conversation to inspect and manage conversation metadata,
participants, and message history. Conversation commands require Hub mode.
This command does not send messages. Use scion message to write to a
conversation; see the scion-messaging skill for sending and reply-routing
guidance.
When to Use
- See which conversations you participate in.
- Create a group conversation for multi-agent coordination.
- Read message history or catch up on recent activity.
- List or add participants, or leave a conversation.
- Retrieve a specific message by ID.
When NOT to use: Do not use scion conversation to send messages. Use
scion message for writing into conversations. Avoid creating a conversation
for a one-off direct message; send it with scion message @<agent-name> instead.
Conversation References
Conversation subcommands accept three reference formats:
conv:<uuid>: Direct conversation ID. This is the most common form and always works for a conversation you can access.@<agent-name>: The direct-message conversation with an agent.#<thread-name>: A named thread conversation.
Bare UUIDs are not accepted. Always include the conv: prefix when addressing
a conversation by ID.
Functional Capabilities
Reading: list, get, messages, catch-up, and get-message let you
discover accessible conversations, inspect their metadata, and read all,
recent, or individual messages. Prefer structured output when another command
or agent will consume the result.
Administration: create, join, leave, participants, and
set-default create coordination spaces and manage their membership and
default agent. A conversation name is the positional argument to create, not
a --title flag. join is not idempotent: adding an existing participant
returns HTTP 409, so check participants first when membership is uncertain.
Run scion conversation --help for the full command reference and
scion conversation <subcommand> --help for authoritative usage, arguments,
and flags for an individual subcommand.
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.
- 12d ago Changed · +1 lines ec2e2775e9d2
- 27d ago First seen · 112 lines · 40 tokens per session scan A 0fbc2ed9d326
scion-conversation is a skill published in the GitHub repository GoogleCloudPlatform/scion (1,900 stars, last pushed yesterday), licensed Apache-2.0. It adds 40 tokens to every session and 927 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 2026-09-19.
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…
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.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…