fractal-think-work

fractal-think-work is a command for Claude Code from axiomantic/spellbook. It costs 22 tokens per session (4,265 once invoked), scanned A, original, MIT.

A work-phase command for fractal thinking, where workers claim open questions from a shared graph and investigate them recursively. The graph acts as the work queue.

In plain words
What is it for?
Use it after seeding an exploration to dispatch workers, process open questions, and complete the synthesis of findings.
Why use it?
It coordinates parallel investigation without a separate task list and checks that claimed work and resulting summaries are accounted for.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md). Also seen: mentions subagents; mentions Claude Code.

Good fit Use it after seeding an exploration to dispatch workers, process open questions, and complete the synthesis of findings.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/axiomantic/spellbook/fractal-think-work
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/axiomantic/spellbook

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 fractal-think-work

README.md
[![agentmods](https://agentmods.dev/badge/commands/axiomantic/spellbook/fractal-think-work/github.svg)](https://agentmods.dev/commands/axiomantic/spellbook/fractal-think-work)
Your own site
<a href="https://agentmods.dev/commands/axiomantic/spellbook/fractal-think-work"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/fractal-think-work/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 fractal-think-work

Your own site · 80×15
<a href="https://agentmods.dev/commands/axiomantic/spellbook/fractal-think-work"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/fractal-think-work.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,265 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 $0.00022 $0.04265
Opus 5 $0.00011 $0.02132
Sonnet 5 $0.00004 $0.00853
Haiku 4.5 $0.00002 $0.00426

Measured 5d ago against content hash e654ef00e6ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

fractal-think-work 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 5d 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.

commands/fractal-think-work.md · 464 lines

How it starts

The opening of the file, as written. The whole thing — 464 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Phase 2: Fractal Think Work

Invariant Principles

  1. The graph IS the work queue - All state is in MCP tools. No separate task queue, no round counter, no cluster registry. Workers pull work dynamically via fractal_claim_work.
  2. All graph mutations happen inside workers - The dispatcher only reads state; it never writes nodes or synthesis.
  3. Return, don't re-dispatch - When workers exit with open work, return state to the orchestrator (SKILL.md). It decides whether to re-dispatch.

Before dispatching, assess: open question count, budget limits, graph active status. After workers finish, verify: no orphaned claimed nodes, synthesis cascade complete, all work accounted for.

Read skills/fractal-thinking/references/mcp-tools.md before Step 1, and pass that path to every worker. It is the canonical definition of the fractal_* tool surface, the valid intensity and checkpoint_mode values, the saturation reasons, and the node state machine that governs every status transition workers make.

Parameters

Parameter Required Description
exploration_state Yes JSON from Phase 1 (seed command) with graph_id, budget, intensity, checkpoint

The exploration_state has this shape:

{
  "graph_id": "<graph_id>",
  "root_node_id": "<root_node_id>",
  "intensity": "<intensity>",
  "checkpoint": "<checkpoint>",
  "budget": { "max_agents": 8, "max_depth": 4 },
  "seed_count": 6
}

Read the full file on GitHub · 464 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. 5d ago First seen · 464 lines · 22 tokens per session scan A e654ef00e6ad

Subscribe to this mod's changes

fractal-think-work is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 4,265 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 2026-09-03.