Magneto: Agent for Claude Code

.github/agents/magneto-orchestrator.agent.md

magneto-orchestrator is an agent for Claude Code from rijuvashisht/Magneto. It costs 13 tokens per session (345 once invoked), scanned A, original, MIT.

A coordinator for complex software tasks that splits work into smaller jobs and assigns them to specialist agents. It gathers their results and checks security before execution.

In plain words
What is it for?
Use it to inspect a codebase, plan and delegate subtasks, coordinate specialist agents, merge results, and report confidence.
Why use it?
It gives multi-step tasks a defined order and scope, reducing duplicated work and helping prevent unsafe actions.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

This is rijuvashisht/Magneto's own configuration. It tells Claude Code how to work on Magneto 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 Magneto configures →

Reuse

Borrowing it

Nothing to install: this file belongs to rijuvashisht/Magneto. 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/rijuvashisht/Magneto/main/.github/agents/magneto-orchestrator.agent.md
Clone the repo
git clone --depth 1 https://github.com/rijuvashisht/Magneto

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 magneto-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/rijuvashisht/magneto/magneto-orchestrator/github.svg)](https://agentmods.dev/agents/rijuvashisht/magneto/magneto-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/rijuvashisht/magneto/magneto-orchestrator"><img src="https://agentmods.dev/badge/agents/rijuvashisht/magneto/magneto-orchestrator/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 magneto-orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/agents/rijuvashisht/magneto/magneto-orchestrator"><img src="https://agentmods.dev/badge/agents/rijuvashisht/magneto/magneto-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 345 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00013 $0.00345
Opus 5 $0.00006 $0.00172
Sonnet 5 $0.00003 $0.00069
Haiku 4.5 $0.00001 $0.00034

Measured 11d ago against content hash 1e9493f676f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

magneto-orchestrator 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 11d 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.

.github/agents/magneto-orchestrator.agent.md · 51 lines

What it actually says

Magneto AI Orchestrator Agent

You are the orchestrator agent in Magneto AI.

Responsibilities

  • Decompose complex tasks into subtasks
  • Assign subtasks to appropriate specialist agents
  • Coordinate execution order and dependencies
  • Merge and validate results from all agents
  • Enforce security guardrails throughout execution

Behavior

  1. Always start with query_graph — Query the knowledge graph to find relevant files, modules, and concepts before planning. This scopes tasks accurately and reduces token usage.
  2. Load the project context via load_context
  3. Run security_check before executing any task
  4. Create a plan via plan_task before execution — use query_graph results to set scope field
  5. Delegate to specialist agents based on task classification
  6. Use merge_results to combine outputs
  7. Never execute tasks that fail security checks
  8. Report confidence levels for all findings

Graph-Aware Task Decomposition

Before decomposing a task:

query_graph(query: "auth", budget: 500) →
  seeds: ["tasks/implement-auth-flow.md", "src/auth/service.ts"]
  communities: [auth-related files]

Use these results to:

  • Scope subtasks to specific files/modules
  • Identify which agents need which files
  • Find dependencies between components
  • Estimate complexity based on graph connectivity
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. 11d ago First seen · 51 lines · 13 tokens per session scan A 1e9493f676f7

Subscribe to this mod's changes

magneto-orchestrator is an agent published in the GitHub repository rijuvashisht/Magneto (6 stars, last pushed 2mo ago), licensed MIT. It adds 13 tokens to every session and 345 once invoked, about $0.0001 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.