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.
npx skills add axiomantic/spellbook --skill fractal-thinkinggit clone --depth 1 https://github.com/axiomantic/spellbookWrote 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.
[](https://agentmods.dev/skills/axiomantic/spellbook/fractal-thinking)<a href="https://agentmods.dev/skills/axiomantic/spellbook/fractal-thinking"><img src="https://agentmods.dev/badge/skills/axiomantic/spellbook/fractal-thinking/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.
<a href="https://agentmods.dev/skills/axiomantic/spellbook/fractal-thinking"><img src="https://agentmods.dev/badge/skills/axiomantic/spellbook/fractal-thinking.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00089 | $0.02740 |
| Opus 5.5 | $0.00036 | $0.01096 |
| Sonnet 5.5 | $0.00018 | $0.00548 |
| Haiku 4.5 | $0.00009 | $0.00274 |
Grade A, and why
fractal-thinking 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fractal Thinking
Announce: "Using fractal-thinking skill for recursive question decomposition."
Invariant Principles
- Orchestrator never explores - Dispatch subagents for all question answering; orchestrator monitors and coordinates only.
- Graph is the source of truth - All state persists in MCP tools; never hold exploration state only in context. The graph IS the work queue.
- Budget is a hard ceiling - Never exceed intensity budget for agents spawned or depth reached.
- One primitive, every scale - The same operation (decompose, recurse, synthesize, connect) runs at depth 0 and depth N.
Before each phase, assess: graph state, budget remaining, convergence signals, claimable work count. After each phase, verify: gate conditions met, graph updated, no orphaned nodes, synthesis cascade progressing.
Overview
Fractal thinking builds a persistent graph of questions and answers. Starting from a seed (question, claim, goal, or fact), it generates seed sub-questions, then dispatches workers that pull tasks from the graph and execute a single recursive primitive on each: decompose the question into sub-questions, add them to the graph as claimable work, answer the question, and when all children are done, synthesize bottom-up. The graph persists in SQLite via MCP tools, surviving context boundaries.
Workers operate independently with branch affinity (preferring nodes in branches they have already touched) and steal across branches when their branch is exhausted. Synthesis cascades upward automatically: when a node's children are all synthesized or saturated, the node itself becomes ready to synthesize. The root node's synthesis IS the final summary.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 277 lines · 89 tokens per session scan A 7f1a9003a475
fractal-thinking is a skill published in the GitHub repository axiomantic/spellbook (10 stars, last pushed 2d ago), licensed MIT. It adds 89 tokens to every session and 2,740 once invoked, about $0.0004 per session on Opus 5.5. 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.
Other skills, from other repositories
repo-hygiene
Use when the scheduled repo-hygiene workflow runs from GitHub Actions (or an operator dry-run) to scan the repository for small, certain docs/test/code hygiene issues and fix them as one batched branch.
test-failure-explorer
Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.
orchestration-team
Use when coordinating assignments, selected review boundaries, or blocked work across a rig.
find-simplifications
Use for a periodic repo-wide sweep of qwen-code for accumulated excess surface — dead components and files, orphaned locale keys, exports nothing consumes, added-then-removed scaffolding — filing candidates on a tracking issue and landing only what a maintainer has said yes to. Repo-wide and evidence-first; every…
bundle-safety
Bundle transform safety — minification variant selection, consumer-constraint verification, identifier preservation, and namespace re-export coverage for build output.
confirm-failures-are-causally-linked-to-the-task-before-reportin
When delegating a task affected by this skill, include.