agentmods.dev

fusion

fusion is a command for Claude Code from Rylaa/fable-GPT-5.6-fusion. It costs 37 tokens per session (626 once invoked), scanned C, original, MIT.

A command that asks several AI models to solve a task, then has other models judge and combine their answers.

In plain words
What is it for?
Use it for coding or research tasks where you want multiple model opinions and a combined answer.
Why use it?
It reduces reliance on one model by comparing independent answers and producing a reviewed result.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: reads .claude/ paths; mentions Codex.

Part of the fable-sol-fusion plugin — 1 skill, 2 commands shipped together

not rated 2repo 2mo ago C scan 37 tokens original MIT

Good fit Use it for coding or research tasks where you want multiple model opinions and a combined answer.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/rylaa/fable-gpt-5.6-fusion/fusion
View source ↗ Rylaa/fable-GPT-5.6-fusion
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/Rylaa/fable-GPT-5.6-fusion

Made for: Claude Code.

Or install fable-sol-fusion, the plugin that ships this one along with the rest of its 1 skill, 2 commands.

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 fusion

README.md
[![agentmods](https://agentmods.dev/badge/commands/rylaa/fable-gpt-5.6-fusion/fusion/github.svg)](https://agentmods.dev/commands/rylaa/fable-gpt-5.6-fusion/fusion)
Your own site
<a href="https://agentmods.dev/commands/rylaa/fable-gpt-5.6-fusion/fusion"><img src="https://agentmods.dev/badge/commands/rylaa/fable-gpt-5.6-fusion/fusion/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 fusion

Your own site · 80×15
<a href="https://agentmods.dev/commands/rylaa/fable-gpt-5.6-fusion/fusion"><img src="https://agentmods.dev/badge/commands/rylaa/fable-gpt-5.6-fusion/fusion.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 626 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00037 $0.00626
Opus 5 $0.00018 $0.00313
Sonnet 5 $0.00007 $0.00125
Haiku 4.5 $0.00004 $0.00063

Measured 10d ago against content hash bcfb23106641, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade C, and why

fusion scanned grade C with 1 finding 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 10d 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.

Tells the agent never to refusehighAnti-refusal

Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.

do NOT judge whether fusion "fits" the task, do NOT ask for clarification, and do NOT refuse —
commands/fusion.md · 30 lines

What it actually says

Invoke the fusion skill on the task below. This is a direct execution request, not a suggestion: do NOT judge whether fusion "fits" the task, do NOT ask for clarification, and do NOT refuse — $ARGUMENTS is the task, run it (code or research, whatever it is).

Follow the skill's SKILL.md exactly:

  1. Step 0 — run detect_panel.sh to confirm both claude and codex are available (the panel needs claude for the Fable 5 seats and codex for the GPT-5.6 Sol seats). If either is missing, say so before proceeding.
  2. Step 1 — write the task verbatim to /tmp/fusion_question.txt, then run preflight.sh on it and show its (non-blocking) estimate. It always exits 0; for a heavy task prefix FUSION_TIMEOUT=3600 on the Step 2 runners.
  3. Step 2 — fan out the panel in parallel and blind: 1× Claude Fable 5 (run_claude.sh, locked --effort max, model claude-fable-5) and 1× GPT-5.6 Sol (run_codex.sh, locked ultra, model gpt-5.6-sol). Task verbatim, no lenses. Each seat is bounded by FUSION_TIMEOUT; a seat that exits 124 (timeout), exits non-zero, or is empty is absent — degrade.
  4. Step 3 — judge both answers with a fresh GPT-5.6 Sol seat (run_codex.sh, ultra) per judge_rubric.md: write a judge prompt (verbatim task + both panel answers + judge instructions) and run it. Analysis only, do not write the final answer.
  5. Step 4 — synthesize the final answer with a separate Claude Fable 5 seat (run_claude.sh, locked max) from the judge analysis + panel answers.
  6. Step 5 — save the provenance record with save_run.sh to ~/.claude/fusion-runs/ (slug fable5-gpt5.6sol; labels fable5= / gpt5.6sol=; skip with FUSION_NO_SAVE=1).
  7. Step 6 — present the final answer first, then the audit trail (per-seat attribution + judge analysis), and note where the provenance record was saved.

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.

  1. 10d ago First seen · 30 lines · 37 tokens per session scan C bcfb23106641

Subscribe to this mod's changes

fusion is a command published in the GitHub repository Rylaa/fable-GPT-5.6-fusion (2 stars, last pushed 2mo ago), licensed MIT. It adds 37 tokens to every session and 626 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents
Related

Other commands, from other repositories

checklist

Generate a custom checklist for the current feature based on user requirements.

github/spec-kit · 13 tokens

clarify

Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.

github/spec-kit · 27 tokens

specify

Create or update the feature specification from a natural language feature description.

github/spec-kit · 13 tokens

analyze

Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.

github/spec-kit · 26 tokens

converge

Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.

github/spec-kit · 35 tokens

implement

Execute the implementation plan by processing and executing all tasks defined in tasks.md.

github/spec-kit · 14 tokens