fractal-loop CLAUDE.md

fractal-loop CLAUDE.md is an instructions file for coding agents from rmolines/fractal-loop. It costs 1,486 tokens per session, scanned A, original, MIT.

A set of instructions for Claude Code projects using Fractal Loop, a recursive way to break a goal into smaller conditions that can be checked. It includes shell commands for testing the state machine and viewing the project tree and active condition.

In plain words
What is it for?
Use it to inspect Fractal Loop state in a repository, view its tree and timeline, read the active condition, and test the underlying state machine.
Why use it?
It provides a repeatable way to work through a large goal by addressing the riskiest unknowns first and checking whether each part is complete, unfinished, or not achievable.

Instructions file

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.

agentmods
npx agentmods add instructions/rmolines/fractal-loop/claude-md
Clone the repo
git clone --depth 1 https://github.com/rmolines/fractal-loop

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-loop CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rmolines/fractal-loop/claude-md.svg)](https://agentmods.dev/instructions/rmolines/fractal-loop/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/rmolines/fractal-loop/claude-md"><img src="https://agentmods.dev/badge/instructions/rmolines/fractal-loop/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,486 This file is loaded in full into every session.
When invoked 1,486 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01486 $0.01486
Opus 5 $0.00743 $0.00743
Sonnet 5 $0.00297 $0.00297
Haiku 4.5 $0.00149 $0.00149

Measured 3d ago against content hash 0d499c1db5b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fractal-loop CLAUDE.md 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 3d 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.

CLAUDE.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this is

Fractal Loop — recursive project management for Claude Code. A plugin that decomposes goals into predicates and works on the riskiest unknown first. One operation, repeated at any scale.

Version: 0.9.0 | Plugin manifest: .claude-plugin/plugin.json

Commands

# Test the state machine
bash scripts/fractal-state.sh

# View tree state (auto-discovers tree in .fractal/)
bash scripts/fractal-tree.sh

# Read active predicate
bash scripts/active-predicate.sh

# Timeline: concluded nodes newest-first
bash scripts/fractal-timeline.sh

No build step. No dependencies. Pure shell scripts + markdown skills.

Architecture

The primitive

fractal(predicate):
  evaluate(predicate, existing_children)  → new_child | complete | leaf | unachievable
  if unachievable            → prune
  if leaf                    → specify → execute → human validates
  if new_child               → create child → human validates → recurse → re-evaluate parent
  if complete                → validate branch satisfaction or select next pending child

Skill chain (execution order)

  1. /fractal:init — bootstrap: extract objective, create tree
  2. /fractal:run — idempotent state machine (main entry point, call repeatedly)
  3. /fractal:patch — fast path for trivial leaf predicates
  4. Sprint agent (agents/sprint.md) — runs the full cycle /fractal:planning/fractal:delivery/fractal:review/fractal:ship as a single Sonnet subagent with no human gates
  5. /fractal:doctor — tree integrity validation
  6. /standards:generate — inspect repo and generate .claude/standards.md (called by /fractal:init when no standards.md exists)

Skills live in commands/. Subagents live in agents/ (evaluate, sprint, patch-worker).

On-disk state (.fractal/ in target repo)

The filesystem IS the state. No database, no JSON.

  • root.md — root predicate + active_node pointer (always exactly one per tree)
  • predicate.md — per node: verifiable condition, status (pending|satisfied|pruned)
  • discovery.md — per node (after evaluation): evaluator response (new_child|complete|leaf|unachievable). Ephemeral on parents — deleted when child ascends.
  • prd.md — leaf nodes only: acceptance criteria, out-of-scope, constraints
  • Execution state derived from artifact presence:
    • Only predicate.md → not started
    • discovery.md exists (new_child) → create proposed child, recurse
    • discovery.md exists (leaf, no prd) → specify, write prd
    • discovery.md + prd.md → specified (run sprint)
    • plan.md exists → planned (run delivery)
    • plan.md + results.md → executed (run review)
    • plan.md + results.md + review.md → reviewed (validate, then ship)
  • conclusion.md — per node (after satisfaction): what was achieved, key decisions, deferred items
  • learnings.md — accumulated human corrections (read on every /fractal:run entry)

Read the full file on GitHub · 117 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. 3d ago First seen · 117 lines · 1,486 tokens per session scan A 0d499c1db5b0

Subscribe to this mod's changes

fractal-loop CLAUDE.md is an instructions file published in the GitHub repository rmolines/fractal-loop (13 stars, last pushed 5mo ago), licensed MIT. It adds 1,486 tokens to every session, about $0.0074 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 2026-08-31.

Related

Other instructions, from other repositories