parallel-fanout

parallel-fanout is a skill for Codex from plurigrid/asi. It costs 31 tokens per session (2,321 once invoked), scanned A, original, MIT.

A coordinator that splits each interaction into multiple parallel skill runs using a deterministic seed derived from the interaction. It assigns separate generator, coordinator, and validator roles.

In plain words
What is it for?
It is for dispatching parallel skill invocations across generation, coordination, and validation tasks.
Why use it?
It is intended to reduce waiting when several kinds of work can be attempted at the same time and then coordinated.

Skill for Codex

Written for Codex: installed under .codex/.

Good fit It is for dispatching parallel skill invocations across generation, coordination, and validation tasks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/plurigrid/asi/parallel-fanout
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.

Any agent
npx skills add plurigrid/asi --skill parallel-fanout
Clone the repo
git clone --depth 1 https://github.com/plurigrid/asi

Made for: Codex.

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 parallel-fanout

README.md
[![agentmods](https://agentmods.dev/badge/skills/plurigrid/asi/parallel-fanout/github.svg)](https://agentmods.dev/skills/plurigrid/asi/parallel-fanout)
Your own site
<a href="https://agentmods.dev/skills/plurigrid/asi/parallel-fanout"><img src="https://agentmods.dev/badge/skills/plurigrid/asi/parallel-fanout/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 parallel-fanout

Your own site · 80×15
<a href="https://agentmods.dev/skills/plurigrid/asi/parallel-fanout"><img src="https://agentmods.dev/badge/skills/plurigrid/asi/parallel-fanout.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,321 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00031 $0.02321
Opus 5 $0.00015 $0.01161
Sonnet 5 $0.00006 $0.00464
Haiku 4.5 $0.00003 $0.00232

Measured 6d ago against content hash 5f73020368b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

parallel-fanout 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 6d 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.

ies/music-topos/.codex/skills/parallel-fanout/SKILL.md · 291 lines

How it starts

The opening of the file, as written. The whole thing — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.

parallel-fanout - Interaction-Entropy-Seeded Parallel Skill Dispatch

Overview

A metaskill that transforms every user interaction into a maximally parallel skill invocation, using the interaction's entropy as the seed for deterministic SplitMixTernary forking.

┌─────────────────────────────────────────────────────────────────┐
│                    USER INTERACTION                              │
│  "implement feature X with Y constraints"                        │
└──────────────────────────┬──────────────────────────────────────┘
                           │
                    ┌──────▼──────┐
                    │   ENTROPY   │
                    │  EXTRACTION │
                    │ (Shannon H) │
                    └──────┬──────┘
                           │ seed = hash(interaction) & MASK64
                    ┌──────▼──────┐
                    │ SplitMix64  │
                    │   .fork(3)  │
                    └──────┬──────┘
                           │
           ┌───────────────┼───────────────┐
           │               │               │
    ┌──────▼──────┐ ┌──────▼──────┐ ┌──────▼──────┐
    │  GENERATOR  │ │ COORDINATOR │ │  VALIDATOR  │
    │   (+1 RED)  │ │  (0 GREEN)  │ │  (-1 BLUE)  │
    │ child[0]    │ │  child[1]   │ │  child[2]   │
    └──────┬──────┘ └──────┬──────┘ └──────┬──────┘
           │               │               │
           └───────────────┼───────────────┘
                           │
                    ┌──────▼──────┐
                    │   MERGE     │
                    │  GF(3) = 0  │
                    └─────────────┘

Interaction Entropy → Seed

def interaction_to_seed(interaction_text)
  # Shannon entropy of interaction
  chars = interaction_text.chars
  freq = chars.tally
  total = chars.size.to_f
  
  h = freq.values.sum { |c| 
    p = c / total
    -p * Math.log2(p) 
  }
  
  # Hash interaction with entropy weight
  fnv1a = 0xcbf29ce484222325
  interaction_text.bytes.each do |b|
    fnv1a ^= b
    fnv1a = (fnv1a * 0x100000001b3) & 0xFFFFFFFFFFFFFFFF
  end
  
  # Combine hash with entropy bits
  entropy_bits = (h * 1_000_000).to_i
  (fnv1a ^ (entropy_bits * GOLDEN)) & MASK64
end

Read the full file on GitHub · 291 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. 6d ago First seen · 291 lines · 31 tokens per session scan A 5f73020368b7

Subscribe to this mod's changes

parallel-fanout is a skill published in the GitHub repository plurigrid/asi (62 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 2,321 once invoked, about $0.0002 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.