fractal-think-harvest

fractal-think-harvest is a command for Claude Code from axiomantic/spellbook. It costs 19 tokens per session (3,912 once invoked), scanned A, original, MIT.

A command for collecting the finished results of a fractal-thinking graph—a research structure whose smaller nodes are combined into larger conclusions. It checks that the graph is complete and formats the final result.

In plain words
What is it for?
Use it to inspect graph status, verify the chain of summaries from individual nodes to the root, count unresolved questions, and produce the final synthesis.
Why use it?
It keeps conclusions tied to the evidence gathered by the graph and makes unresolved contradictions visible. It also prevents incomplete or overlooked synthesis from being reported as finished.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

Good fit Use it to inspect graph status, verify the chain of summaries from individual nodes to the root, count unresolved questions, and produce the final synthesis.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/axiomantic/spellbook/fractal-think-harvest"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/fractal-think-harvest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,912 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 $0.00019 $0.03912
Opus 5 $0.00010 $0.01956
Sonnet 5 $0.00004 $0.00782
Haiku 4.5 $0.00002 $0.00391

Measured 7d ago against content hash a73a0b5c864c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

fractal-think-harvest 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 7d 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-harvest.md · 430 lines

How it starts

The opening of the file, as written. The whole thing — 430 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Phase 3: Fractal Think Harvest

Invariant Principles

  1. Evidence over narrative - Every finding must trace to specific graph nodes; no unsupported claims.
  2. Contradictions are findings - Unresolved tensions are reported as open questions, not hidden.
  3. Preserve synthesis fidelity - Read bottom-up syntheses as composed by workers. Do not reconstruct, reinterpret, or replace them.

Before harvest, assess: root synthesis status, any nodes still awaiting synthesis, graph completeness, convergence cluster count, unresolved contradictions, open questions. After harvest, verify: every claim traces to nodes, no convergence overlooked, synthesis chain is complete from root to leaves, FractalResult complete.

Read skills/fractal-thinking/references/mcp-tools.md before Step 1. It is the canonical definition of the fractal_* query tool surface, the saturation reasons you report, and the node state machine whose statuses (synthesized, saturated, claimed, error) this harvest counts.

Parameters

Parameter Required Description
graph_id Yes ID of the fractal graph to harvest
seed Yes The original seed for context

Step 1: Read Final Graph State

Query the complete graph:

snapshot = fractal_get_snapshot(graph_id: <graph_id>)
convergence = fractal_query_convergence(graph_id: <graph_id>)
contradictions = fractal_query_contradictions(graph_id: <graph_id>)
saturation = fractal_get_saturation_status(graph_id: <graph_id>)
open_questions = fractal_get_open_questions(graph_id: <graph_id>)
ready_to_synthesize = fractal_get_ready_to_synthesize(graph_id: <graph_id>)

Read the full file on GitHub · 430 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. 7d ago First seen · 430 lines · 19 tokens per session scan A a73a0b5c864c

Subscribe to this mod's changes

fractal-think-harvest is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 3,912 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.

Related

Other commands, from other repositories

subagent-implementation

Orchestrate implement→review subagent loop until task complete. Reads the approved spec, writes a thin brief to .claude/.scratchpad/, dispatches fresh-context subagents, loops until reviewer signs off, commits per green iteration, then updates repo docs.

damusix/atomic-claude · 53 tokens

documentation

Bootstrap and maintain project documentation surfaces. Two modes: bootstrap (discover doc files, index them in CLAUDE.md) and authoring (scan for unindexed docs, match diff against indexed surfaces, walk stale/incomplete/missing items with Yes/Later/Remind/Skip).

damusix/atomic-claude · 0 tokens

watch-ci

Spawn a background Haiku-backed subagent to watch CI for the current branch (or specified target). Provider-agnostic — the subagent inspects project signals to identify the CI system (GitHub Actions, GitLab CI, CircleCI, etc.) and picks the right CLI. Returns immediately; reports back when CI reaches a terminal state.

damusix/atomic-claude · 69 tokens

session-report

Capture what changed this session and why, scoped to the current branch. Read by ship verbs when synthesizing the commit message; deleted after a successful commit.

damusix/atomic-claude · 31 tokens

integrate

Analyze and enhance AI artifacts to leverage Subcog memory effectively.

zircote/subcog · 12 tokens

maintain

Run automated maintenance — seeker finds bugs from pod logs and raises GitHub issues, fixer picks them up and creates PRs. Can run as a one-shot or scheduled via /schedule.

randomittin/heimdall · 40 tokens