agentmods.dev

scion AGENTS.md

A set of project instructions for Scion, a platform that runs multiple AI coding agents in containers. It explains the project’s terminology, structure, technologies, and specialised instructions for different folders.

In plain words
What is it for?
Use it when working on Scion’s code, especially its web frontend or documentation site. It helps an agent understand what to inspect and which project terms and conventions to follow.
Why use it?
It gives a coding agent the context it needs before changing the code. This reduces confusion caused by renamed concepts, project-specific rules, or different parts of the repository having different guidance.

Instructions file for CodexOpenCode

1.7k 2d ago A scan 4,259 tokens original Apache-2.0
View the source file GoogleCloudPlatform/scion
Install

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.

agentmods
npx agentmods add instructions/googlecloudplatform/scion/agents-md
Clone the repo
git clone --depth 1 https://github.com/GoogleCloudPlatform/scion

Made for: Codex, OpenCode.

Per session 4,259 This file is loaded in full into every session.
When invoked 4,259 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.04259 $0.04259
Opus 5 $0.02129 $0.02129
Sonnet 5 $0.00852 $0.00852
Haiku 4.5 $0.00426 $0.00426

Measured yesterday against content hash 760c724d7860, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

scion AGENTS.md 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 yesterday.

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.

AGENTS.md · 197 lines

How it starts

The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scion Project Context

Overview

Note: This project is currently in a pre-release/alpha stage.

Important Terminology Change: The concept previously called "grove" has been renamed to "project" throughout the product. You will encounter "grove" in existing code, database schemas, API endpoints, issues, and documentation — treat "grove" and "project" as synonymous. New code should prefer "project" where feasible, but the rename is ongoing and many internal references still use "grove".

scion is a container-based orchestration platform designed to manage concurrent LLM-based code agents. It supports both a standalone local CLI mode and a distributed "Hosted" architecture where state is centralized in a Hub and agents execute on disparate Runtime Brokers (local Docker, remote servers, or Kubernetes clusters).

Agent Instruction Files

Subdirectories contain domain-specific agent instructions for their respective areas of the codebase.

Path Domain
web/AGENTS.md Web frontend (Lit components, Shoelace, Vite build)
docs-site/AGENTS.md Documentation site

Before You Start

  • If you are working on web content, review web/AGENTS.md before making changes.
  • If you are working on the documentation site, review docs-site/AGENTS.md before making changes.
  • Check the project root claude.md for build commands, architecture notes, and coding conventions.

System Goals

  • Parallelism: Run multiple agents concurrently as independent processes.
  • Isolation: Ensure strict separation of identities, credentials, and configuration.
  • Context Management: Provide each agent with a dedicated git worktree to prevent conflicts.
  • Specialization: Support role-based agent configuration via templates.
  • Interactivity: Support "detached" background operation with the ability to "attach" for human-in-the-loop interaction.

Core Technologies

  • Backend Language: Go (Golang)
  • CLI Framework: Cobra
  • Frontend Stack: TypeScript, React, Vite, Koa (Node.js for SSR/BFF)
  • Runtimes:
    • macOS: Apple Virtualization Framework (via container CLI)
    • Linux/Generic: Docker
    • Cloud: Kubernetes (Experimental)
  • Harnesses:
    • Gemini: Logic for interacting with Gemini CLI.
    • Claude: Logic for interacting with Claude Code.
    • Generic: A base harness for other LLM interfaces.
  • Workspace Management: Git Worktrees for concurrent, isolated code modification.

Read the full file on GitHub · 197 lines

Changes

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.

  1. yesterday First seen · 197 lines · 4,259 tokens per session scan A 760c724d7860

Subscribe to this mod's changes

scion AGENTS.md is an instructions file published in the GitHub repository GoogleCloudPlatform/scion (1,683 stars, last pushed 2d ago), licensed Apache-2.0. It adds 4,259 tokens to every session, about $0.0213 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.

FrontendWriting and docs
Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

buildNext

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,040 tokens

langchain AGENTS.md

Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens