fusion

fusion is a command for Claude Code from tboome33/openrouter-fusion-mcp. It costs 26 tokens per session (619 once invoked), scanned A, original, MIT.

An interactive command for OpenRouter Fusion, which lets several AI models and a coordinating model consider a request together. It guides you through choosing a preset, reasoning level, and temperature before starting.

In plain words
What is it for?
Use it to inspect Fusion presets, compare their estimated costs and model panels, select a configuration, and start an asynchronous deliberation.
Why use it?
It helps you compare available model setups and choose how much reasoning to use before launching a run. It also pauses for your choices instead of assuming them.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions Claude Code.

Part of the openrouter-fusion plugin — 1 skill, 1 command, 1 hook, 1 MCP server shipped together

Good fit Use it to inspect Fusion presets, compare their estimated costs and model panels, select a configuration, and start an asynchronous deliberation.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/tboome33/openrouter-fusion-mcp/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/tboome33/openrouter-fusion-mcp

Made for: Claude Code.

Or install openrouter-fusion, the plugin that ships this one along with the rest of its 1 skill, 1 command, 1 hook, 1 MCP server.

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/tboome33/openrouter-fusion-mcp/fusion/github.svg)](https://agentmods.dev/commands/tboome33/openrouter-fusion-mcp/fusion)
Your own site
<a href="https://agentmods.dev/commands/tboome33/openrouter-fusion-mcp/fusion"><img src="https://agentmods.dev/badge/commands/tboome33/openrouter-fusion-mcp/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/tboome33/openrouter-fusion-mcp/fusion"><img src="https://agentmods.dev/badge/commands/tboome33/openrouter-fusion-mcp/fusion.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 619 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00026 $0.00619
Opus 5 $0.00013 $0.00309
Sonnet 5 $0.00005 $0.00124
Haiku 4.5 $0.00003 $0.00062

Measured 11d ago against content hash af59aa50c7c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

fusion 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 11d 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.md · 44 lines

What it actually says

Drive OpenRouter Fusion interactively. Follow these steps in order, stopping to wait for the user's answer after each question (don't chain ahead).

1. List the configs. Call fusion_list. Present EVERY preset returned as a full TABLE (one row per preset; columns: #, preset, est. cost ~$low–$high (from cost_estimate.low/.high), panel, judge/orchestrator, reasoning_effort). ALWAYS render this full table at the moment you ask the user to choose — even if you showed it earlier, and even when you recommend one: never reduce it to just the recommendation. The cost is an estimated RANGE per run (floor = little web, ceiling = full max_tool_calls web budget); real cost also scales with prompt size (each preset's cost_estimate.usd_per_prompt_token) and reasoning effort. State it's indicative, not a quote.

fusion_start is gated by a permission confirmation in Claude Code (the user approves each paid launch). You don't manage it — the harness prompts.

2. Recommend + ask for the preset. Mark (⭐) the preset best suited to the request (with its cost_tier), then ask "Which preset (number or name)?" and WAIT. Never pick for them. (Skip this ONLY if the user named the preset themselves in the request — you proposing one does not count.)

3. Ask for the reasoning effortxhigh · high · medium · low · minimal · none, recalling the chosen preset's default. Then WAIT.

4. Ask for the temperature — a number 0–2, or "model default". Then WAIT.

5. Ask for the question if it wasn't already provided.

6. Run. Call fusion_start with preset, prompt (the full question), and reasoning_effort / temperature only if the user chose an explicit value (otherwise omit them). Get the job_id.

7. Poll. Call fusion_result with that job_id; while {status:"running"}, call again with the same job_id until the final answer (~45 s long-poll per call).

8. Return the synthesized answer verbatim (cost footer included), without reformulating.

On error (unknown preset, expired job_id, 401…), explain briefly and don't loop.

Request (may be empty — then ask for it at step 5): $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. 11d ago First seen · 44 lines · 26 tokens per session scan A af59aa50c7c8

Subscribe to this mod's changes

fusion is a command published in the GitHub repository tboome33/openrouter-fusion-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 26 tokens to every session and 619 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 2026-08-31.