A command that asks three different AI models to solve the same task in parallel, then has one model judge their work and produce a final answer.

It is for research, analysis, coding, and artifact tasks that benefit from comparing answers, recording where they came from, and merging suitable results.

It gives the task several independent attempts and a review step, while still allowing the process to finish if some models are unavailable.

fusion-3 — Command for Claude Code by duolahypercho/fusion-fable

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/duolahypercho/fusion-fable

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/duolahypercho/fusion-fable/fusion-3/github.svg)](https://agentmods.dev/commands/duolahypercho/fusion-fable/fusion-3)

Your own site

<a href="https://agentmods.dev/commands/duolahypercho/fusion-fable/fusion-3"><img src="https://agentmods.dev/badge/commands/duolahypercho/fusion-fable/fusion-3/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/duolahypercho/fusion-fable/fusion-3"><img src="https://agentmods.dev/badge/commands/duolahypercho/fusion-fable/fusion-3.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 393 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.

Model	Per session	Once invoked
Fable 5.1	$0.00052	$0.00393
Opus 5.5	$0.00021	$0.00157
Sonnet 5.5	$0.00010	$0.00079
Haiku 4.5	$0.00005	$0.00039

Measured 2mo ago against content hash d124465d4701, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fusion-3 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 2mo 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/fusion-3.md · 22 lines

What it actually says

Invoke the fusion skill on the task below, forcing the richest panel opus4.8-gpt5.5-gemini3.1pro: Opus 4.8 (Agent subagent), GPT-5.5 (via codex exec), and Gemini 3.1 Pro (via agy, pseudo-TTY) answer the SAME prompt IN PARALLEL, each independently with web + bash and none seeing the others' work → Opus 4.8 judges all three → Opus writes the final answer grounded in the analysis.

Follow the skill's SKILL.md exactly (preflight → fan out in parallel → judge picking the track that fits the task → grounded final deliverable → save provenance → present). For a research/analysis task, present the standard audit-trail sections (Consensus / Contradictions / Partial coverage / Unique insights / Blind spots); for a code/artifact task, run both candidates and merge them into one working result with a merge rationale. Pass the task verbatim to all three; no "lenses". Three families, one of each — do not add a second Opus run.

This command targets the FULL panel but degrades gracefully: if codex or agy is missing or a panelist fails/times out, drop it, note the degraded panel in the output, and finish with what remains (opus4.8-gpt5.5, then ultimately opus4.8-4.8) rather than aborting.

Task: $ARGUMENTS

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.

2mo ago First seen · 22 lines · 52 tokens per session scan A d124465d4701

Subscribe to this mod's changes

fusion-3 is a command published in the GitHub repository duolahypercho/fusion-fable (471 stars, last pushed 3mo ago), licensed MIT. It adds 52 tokens to every session and 393 once invoked, about $0.0002 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 2026-08-30.

Building agents

fusion-3 next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
fusion-3duolahypercho/fusion-fable	Command	471	3mo ago	MIT	A	52	Claude Code
checklistgithub/spec-kit	Command	148k	yesterday	MIT	A	13	Claude Code
clarifygithub/spec-kit	Command	148k	yesterday	MIT	A	27	Claude Code
specifygithub/spec-kit	Command	148k	yesterday	MIT	A	13	Claude Code
analyzegithub/spec-kit	Command	148k	yesterday	MIT	A	26	Claude Code
convergegithub/spec-kit	Command	148k	yesterday	MIT	A	35	Claude Code
implementgithub/spec-kit	Command	148k	yesterday	MIT	A	14	Claude Code