fusion-setup

A command for configuring or reconfiguring the opencode Fusion agent team, which divides work among agents with different roles and permissions.

In plain words
What is it for?
It is for starting a full Fusion setup or changing a subscription profile, agent model, or team role.
Why use it?
It turns setup instructions or a requested model or role change into the corresponding Fusion configuration process.

Command

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 commands/mihneaptu/opencode-fusion/fusion-setup
Clone the repo
git clone --depth 1 https://github.com/mihneaptu/opencode-fusion
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 188 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00010 $0.00188
Opus 5 $0.00005 $0.00094
Sonnet 5 $0.00002 $0.00038
Haiku 4.5 $0.00001 $0.00019

Measured 3d ago against content hash 017809a29b4d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fusion-setup 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.

.opencode/skills/fusion-setup/commands/fusion-setup.md · 11 lines

What it actually says

Load and follow the fusion-setup skill to configure the Fusion agent team.

$ARGUMENTS

If arguments are empty, run the full interactive setup: offer the bundled subscription profiles first, then ask which model to use for each role (main/build, sidekick, explore, and the optional research/design/reviewer/vision specialists), then write the global config and install the agent prompts as the skill describes. If arguments name a subscription or profile (for example "opencode-go" or "use my GitHub Copilot subscription"), jump straight to the skill's Step 0 confirmation for that profile. If arguments describe a change (for example "reconfigure sidekick" or "change explore model"), treat them as the specific change the user wants and jump to the relevant part of the skill instead of re-running the whole interview.

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 · 11 lines · 10 tokens per session scan A 017809a29b4d

Subscribe to this mod's changes

fusion-setup is a command published in the GitHub repository mihneaptu/opencode-fusion (216 stars, last pushed 9d ago), licensed MIT. It adds 10 tokens to every session and 188 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 2026-08-30.