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 agentmods add skills/googlecloudplatform/scion/team-creationnpx skills add GoogleCloudPlatform/scion --skill team-creationgit clone --depth 1 https://github.com/GoogleCloudPlatform/scionWhat 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 | $0.00093 | $0.02987 |
| Opus 5 | $0.00046 | $0.01494 |
| Sonnet 5 | $0.00019 | $0.00597 |
| Haiku 4.5 | $0.00009 | $0.00299 |
Grade A, and why
team-creation 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 2d 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 — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scion Team Creation & Extension Skill
You create and extend scion agent templates — the blueprints that define specialized agent roles. Given a description of a team (roles, responsibilities, workflow), you produce template directories that can be used to start agents with scion start <name> --type <template>.
When extending an existing team, review the current templates to understand the established patterns, naming, and workflow before making changes.
Template Directory Structure
Each template lives in .scion/templates/<template-name>/ and contains:
.scion/templates/<template-name>/
├── scion-agent.yaml # REQUIRED: template metadata and config
├── agents.md # REQUIRED: agent behavioral instructions
├── system-prompt.md # REQUIRED: role persona and expertise framing
└── skills/ # OPTIONAL: harness skills (agentskills.io standard)
└── <skill-name>/
└── SKILL.md
Custom templates automatically inherit from the built-in default template, which provides shell configs, git setup, and base scion infrastructure. You do NOT need to create a home/ directory or duplicate any infrastructure files.
Template Naming
- Directory names use kebab-case:
panel-judge,code-reviewer,team-lead - Names should be descriptive of the role, not the project
Required File Formats
scion-agent.yaml
Every template MUST have this file. Minimal valid config:
schema_version: "1"
description: "Short description of this agent role"
agent_instructions: agents.md
system_prompt: system-prompt.md
Optional fields you may include when the role requires them:
max_turns: 50 # Maximum conversation turns
max_duration: "30m" # Maximum wall-clock time (e.g. "1h", "30m")
env:
ROLE: "reviewer"
services:
- name: chromium
command: ["chromium", "--headless", "--no-sandbox", "--remote-debugging-port=9222"]
restart: always
ready_check:
type: tcp
target: "localhost:9222"
timeout: "10s"
skills:
- uri: "skill://scion/global/idea-refine@latest"
- uri: "skill://scion/core/scion@^1.0"
optional: true
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.
- 2d ago First seen · 287 lines · 93 tokens per session scan A 464dd86d855c
team-creation is a skill published in the GitHub repository GoogleCloudPlatform/scion (1,685 stars, last pushed today), licensed Apache-2.0. It adds 93 tokens to every session and 2,987 once invoked, about $0.0005 per session on Opus 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
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…