think

think is a skill for Claude Code, Codex from rijuvashisht/Magneto. It costs 0 tokens per session (2,445 once invoked), scanned A, original, MIT.

A guided planning skill that asks questions about a requested change after examining the codebase. It saves the resulting design in a project sprint folder.

In plain words
What is it for?
It helps clarify feature goals, identify related code, expose design choices, and prepare a written design for the next planning step.
Why use it?
It reduces wrong assumptions and unnecessary work by connecting the discussion to existing code, decisions, and recurring patterns.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for gstack. Also seen: names the AskUserQuestion tool; built for gstack.

Good fit It helps clarify feature goals, identify related code, expose design choices, and prepare a written design for the next planning step.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rijuvashisht/magneto/think
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.

Any agent
npx skills add rijuvashisht/Magneto --skill think
Clone the repo
git clone --depth 1 https://github.com/rijuvashisht/Magneto

Made for: Claude Code, Codex.

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 think

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/rijuvashisht/magneto/think"><img src="https://agentmods.dev/badge/skills/rijuvashisht/magneto/think.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,445 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 $0.00000 $0.02445
Opus 5 $0.00000 $0.01222
Sonnet 5 $0.00000 $0.00489
Haiku 4.5 $0.00000 $0.00245

Measured 9d ago against content hash 71cd6e822296, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

think 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.

src/templates/magneto-skills/skills/think/SKILL.md · 290 lines

How it starts

The opening of the file, as written. The whole thing — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/think — Graph-Grounded Forcing Questions

Role: YC Office Hours × Your-Actual-Repo Inputs: user task description (conversational) Outputs: .magneto/sprints/<id>/design.md Next skill: /plan Audit actions: think.started, think.questions_asked, think.design_drafted


Why This Skill Exists

Most AI assistants skip straight to code. The result is wrong assumptions, overengineering, and features nobody asked for. /think forces you through a structured interrogation before any code is written.

Unlike generic "office hours" prompts, /think is grounded in YOUR codebase. Before asking "what's the real pain?", it reads your knowledge graph and asks: "You already have 3 auth implementations in communities 12, 18, and 47 — which are you extending, or are you replacing them all?"

That's the difference between gstack's /office-hours and Magneto's /think.


The Protocol

Step 1: Load codebase context (required before asking any question)

Run these commands and read the output:

magneto graph communities    # list top 20 communities with god nodes
magneto graph god-nodes      # most-connected files/symbols
magneto memory show --tags patterns,decisions   # past decisions

From that context, identify:

  • Existing implementations related to the user's request (grep the graph for keywords from the task)
  • God nodes they'll likely touch
  • Communities the change will affect
  • Past learnings from .magneto/memory/ that apply

If the graph is not built, say:

"I don't have a knowledge graph for this project yet. Run magneto analyze && magneto graph build first — it takes 1-5 minutes on a normal repo and makes every subsequent skill 10x more useful. Want me to proceed without the graph (less accurate) or wait?"

Step 2: Start the sprint

magneto sprint new "<short-title>" --owner "<user>"

Write .magneto/sprints/<id>/design.md as you go (don't wait until the end).

Emit audit: magneto audit add think.started --payload '{"sprintId":"..."}'.

Read the full file on GitHub · 290 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 · 290 lines · 0 tokens per session scan A 71cd6e822296

Subscribe to this mod's changes

think is a skill published in the GitHub repository rijuvashisht/Magneto (6 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,445 tokens. 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.