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.
git 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/commands/axiomantic/spellbook/fractal-think-seed)<a href="https://agentmods.dev/commands/axiomantic/spellbook/fractal-think-seed"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/fractal-think-seed/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/commands/axiomantic/spellbook/fractal-think-seed"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/fractal-think-seed.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00015 | $0.01654 |
| Opus 5 | $0.00008 | $0.00827 |
| Sonnet 5 | $0.00003 | $0.00331 |
| Haiku 4.5 | $0.00002 | $0.00165 |
Grade A, and why
fractal-think-seed 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.
How it starts
The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fractal Think Seed
Invariant Principles
- Seed determines root - Every graph starts from exactly one seed node.
- No upfront clustering - Questions are added as flat children of root. Branch structure emerges from recursive decomposition, not surface-level domain grouping.
- Budget set once - Intensity determines max_agents and max_depth at creation; never change mid-exploration.
Before generating questions, assess: seed type (question/claim/goal/fact), intensity budget, resume vs new. After writing nodes, verify: all questions recorded as open nodes, count matches intensity target, no duplicates.
Read skills/fractal-thinking/references/mcp-tools.md before Step 1. 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 used here.
Parameters
| Parameter | Required | Description |
|---|---|---|
seed |
Yes | The question, claim, goal, or fact to explore |
intensity |
Yes | "pulse", "explore", or "deep" |
checkpoint |
Yes | Checkpoint mode for the exploration |
graph_id |
No | If provided, resume this graph instead of creating new |
Step 1: Create or Resume Graph
Creating a New Graph
Valid values: intensity = pulse | explore | deep; checkpoint_mode = autonomous | convergence | interactive | depth:N
fractal_create_graph(
seed: <seed>,
intensity: <intensity>,
checkpoint_mode: <checkpoint>
)
Returns:
{
"graph_id": "uuid",
"root_node_id": "uuid",
"intensity": "explore",
"checkpoint_mode": "autonomous",
"budget": { "max_agents": 8, "max_depth": 4 },
"status": "active"
}
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.
- 7d ago First seen · 191 lines · 15 tokens per session scan A 5ed9c325c1bd
fractal-think-seed is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed today), licensed MIT. It adds 15 tokens to every session and 1,654 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.
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.
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).
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.
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.
integrate
Analyze and enhance AI artifacts to leverage Subcog memory effectively.
add-command
Add a new slash command to the current plugin.