agent-atlas-studio: Instructions file for Claude Code

CLAUDE.md

agent-atlas-studio CLAUDE.md is an instructions file for Claude Code from Fox-River-AI/agent-atlas-studio. It costs 1,889 tokens per session, scanned A, original, Apache-2.0.

A repository instruction file for agent-atlas-studio, a visual modeler for designing AI-agent systems as connected graphs and exporting their definitions as YAML files. It documents the project’s purpose, commands, architecture, and connection rules.

In plain words
What is it for?
Use it when developing or maintaining agent-atlas-studio, including its web build, Tauri desktop app, graph model, validation, and YAML export.
Why use it?
It gives coding agents the project-specific context and conventions needed to make safe, consistent changes.

Instructions file for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is Fox-River-AI/agent-atlas-studio's own configuration. It tells Claude Code how to work on agent-atlas-studio itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agent-atlas-studio configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Fox-River-AI/agent-atlas-studio. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Fox-River-AI/agent-atlas-studio/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Fox-River-AI/agent-atlas-studio

Made for: Claude Code.

Wrote 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.

agentmods badge for agent-atlas-studio CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/fox-river-ai/agent-atlas-studio/claude-md/github.svg)](https://agentmods.dev/instructions/fox-river-ai/agent-atlas-studio/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/fox-river-ai/agent-atlas-studio/claude-md"><img src="https://agentmods.dev/badge/instructions/fox-river-ai/agent-atlas-studio/claude-md/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.

agentmods 80×15 button for agent-atlas-studio CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/fox-river-ai/agent-atlas-studio/claude-md"><img src="https://agentmods.dev/badge/instructions/fox-river-ai/agent-atlas-studio/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,889 This file is loaded in full into every session.
When invoked 1,889 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01889 $0.01889
Opus 5 $0.00945 $0.00945
Sonnet 5 $0.00378 $0.00378
Haiku 4.5 $0.00189 $0.00189

Measured 9d ago against content hash 408a91122c21, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

agent-atlas-studio CLAUDE.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 9d 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.

CLAUDE.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this is

agent-atlas-studio is an Erwin-style visual modeler for agentic AI systems. You lay out a whole platform — orchestrator, tasks, agents, MCP tools, jobs, routers, and systems (datastores) — as one unified, collapsible graph, validate each object live against the agent-atlas JSON schema, and export a versioned registry of YAML manifests.

It runs identically as a static web build (GitHub Pages) and a local-first Tauri 2 desktop app. No backend, no auth, no cloud dependency.

Commands

npm install                 # requires submodule: git submodule update --init
npm run dev                 # web dev server → http://localhost:5173
npm run build               # static build → dist/
npm run preview             # serve the production build
npm run lint                # eslint .
npm run tauri dev           # desktop app (runs `npm run dev` first, loads localhost:5173)
npm run tauri build         # package the desktop app (runs `npm run build` first)

There is no test runner configured. npm run lint (ESLint flat config in eslint.config.js) is the only automated check.

The GitHub Pages build sets BASE_PATH=/agent-atlas-studio/ so assets resolve on the project-pages subpath; dev and the Tauri build use base: '/' (see vite.config.js).

The submodule is the source of truth — do not duplicate the schema

vendor/agent-atlas is a git submodule (Fox-River-AI/agent-atlas) holding the canonical manifest schema and deterministic validators. The point of vendoring it is that there is exactly one copy of the spec, so the UI can never drift from it.

  • src/atlas/schema.js imports schemas and compiles Ajv validators. The tool schema is imported straight from the submodule (vendor/agent-atlas/registry/schema/tool.schema.json). The agent, job, system, router, and orchestrator schemas live in src/atlas/schemas/*.json — these are prototyped in-studio for fast iteration and meant to be upstreamed to agent-atlas once proven. When changing object shapes, edit the studio schema, but treat the submodule tool schema as canonical.
  • Schemas declare JSON Schema draft 2020-12, so schema.js imports ajv/dist/2020 (the default Ajv export only knows draft-07 and will throw at compile()).
  • The registry export (src/atlas/model.js) is built to satisfy agent-atlas's own governance/ci/validate_registry.py, so the same checks that gate the OSS repo gate what this UI produces.

Read the full file on GitHub · 81 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. 9d ago First seen · 81 lines · 1,889 tokens per session scan A 408a91122c21

Subscribe to this mod's changes

agent-atlas-studio CLAUDE.md is an instructions file published in the GitHub repository Fox-River-AI/agent-atlas-studio (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,889 tokens to every session, about $0.0094 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 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

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

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 · 5,153 tokens

vscode buildNext.instructions.md

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

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

langchain AGENTS.md

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 · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens