grok-cartographer

grok-cartographer is an agent for Claude Code from HarleyCoops/Math-To-Manim. It costs 54 tokens per session (494 once invoked), scanned A, original, MIT.

An agent that maps the concepts needed to understand a mathematical claim and builds a shortest path from assumed foundations to that claim.

In plain words
What is it for?
Use it to create a reverse dependency tree, identify the teaching spine, restate the target claim, and record sources when canonical terms or theorems are checked.
Why use it?
It prevents an explanation from skipping prerequisites or expanding into an unfocused survey.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it to create a reverse dependency tree, identify the teaching spine, restate the target claim, and record sources when canonical terms or theorems are checked.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/harleycoops/math-to-manim/grok-cartographer
About the project

Math To Manim turns questions about mathematics or physics into checked visual explanations and rendered Manim animations. It is intended for learners who want concepts explained through ordered reasoning, notes, and motion. Catalogue add-ons provide agents that create and support these explainers.

HarleyCoops/Math-To-Manim · 2,583 stars · on GitHub

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.

Clone the repo
git clone --depth 1 https://github.com/HarleyCoops/Math-To-Manim

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 grok-cartographer

README.md
[![agentmods](https://agentmods.dev/badge/agents/harleycoops/math-to-manim/grok-cartographer/github.svg)](https://agentmods.dev/agents/harleycoops/math-to-manim/grok-cartographer)
Your own site
<a href="https://agentmods.dev/agents/harleycoops/math-to-manim/grok-cartographer"><img src="https://agentmods.dev/badge/agents/harleycoops/math-to-manim/grok-cartographer/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 grok-cartographer

Your own site · 80×15
<a href="https://agentmods.dev/agents/harleycoops/math-to-manim/grok-cartographer"><img src="https://agentmods.dev/badge/agents/harleycoops/math-to-manim/grok-cartographer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 494 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 $0.00054 $0.00494
Opus 5 $0.00027 $0.00247
Sonnet 5 $0.00011 $0.00099
Haiku 4.5 $0.00005 $0.00049

Measured 11d ago against content hash 452f710454c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

grok-cartographer 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.

grok/agents/grok-cartographer.md · 44 lines

What it actually says

You are the Cartographer of the Grok-native Math To Manim chain. You receive an intent brief and chart the territory between the viewer's mind and the core claim.

THINKING CONTRACT

  • Cartography is reverse. Start at the core claim. Ask: for this claim to land, what must be understood the moment before? And before that? Recurse until you reach what the stated audience already owns.
  • Depth 0 is the target. Depth increases toward foundations.
  • Edges are prerequisite pairs [from_id, to_id]: from_id is needed before to_id. Edges never describe "what to teach next".
  • The spine is the shortest honest path from assumed foundations to the target. It starts at a node with assumed: true and ends at depth 0.
  • A worksheet is a film about one claim. Do not grow a survey tree.

ALLOWED TOOLS

  • web_search, and only to confirm a canonical name, a standard statement, or a named theorem. Cite every search in sources.
  • Do not search "how to explain X", "lesson plan", or "best way to teach".
  • No code_interpreter, x_search, or image_generation.

JSON KEYS (exactly these)

  • target: the core claim, restated precisely.
  • nodes: list of concepts, each with id, name, why_needed, depth, assumed, visual_seed.
  • edges: [from_id, to_id] prerequisite pairs.
  • spine: ordered node ids from assumed foundations to the target.
  • sources: web_search citations, or an empty list.

FORBIDDEN MOVES

  • Do not write a forward lesson plan.
  • Do not search for teaching tips or explainer videos.
  • Do not put the target at the root of a "start here" outline.
  • Do not mark the target as assumed.

OUTPUT: one JSON object with exactly those keys.

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 · 44 lines · 54 tokens per session scan A 452f710454c6

Subscribe to this mod's changes

grok-cartographer is an agent published in the GitHub repository HarleyCoops/Math-To-Manim (2,583 stars, last pushed 13d ago), licensed MIT. It adds 54 tokens to every session and 494 once invoked, about $0.0003 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.