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.
npx agentmods add skills/mihneaptu/opencode-fusion/fusion-setupnpx skills add mihneaptu/opencode-fusion --skill fusion-setupgit clone --depth 1 https://github.com/mihneaptu/opencode-fusionWrote 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.
[](https://agentmods.dev/skills/mihneaptu/opencode-fusion/fusion-setup)<a href="https://agentmods.dev/skills/mihneaptu/opencode-fusion/fusion-setup"><img src="https://agentmods.dev/badge/skills/mihneaptu/opencode-fusion/fusion-setup.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00166 | $0.06788 |
| Opus 5 | $0.00083 | $0.03394 |
| Sonnet 5 | $0.00033 | $0.01358 |
| Haiku 4.5 | $0.00017 | $0.00679 |
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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fusion setup
This skill configures the Fusion agent team (a main agent, a sidekick executor, an explore searcher, and optional specialists) by writing the user's GLOBAL opencode config at ~/.config/opencode/ (on Windows: %USERPROFILE%\.config\opencode\). It does not require cloning any repository.
opencode resolves that directory as $XDG_CONFIG_HOME/opencode/ when XDG_CONFIG_HOME is set and non-empty, falling back to ~/.config/opencode/ otherwise. Every ~/.config/opencode/... path below means that resolved directory. The bundled installer in Step 4 works this out itself, so the normal flow needs no special handling; only the manual fallback in Step 4b and the verification in Step 5 need you to resolve it by hand. Installing into ~/.config/opencode/ on a machine with a different XDG_CONFIG_HOME writes a tree opencode never reads - the install looks successful and Fusion silently never loads.
What Fusion is
Fusion splits work across agents with asymmetric permissions:
build(main, primary): a strong model that plans, makes judgment calls, and reviews. It CANNOT edit files, search the codebase, or run arbitrary shell. Its only path to changing files is delegating to the sidekick via thetasktool.plan(primary): plan mode - the same planning brain as build. Produces a reviewed plan and delegates exploration, but does not execute; switch to build to carry it out. Overrides opencode's built-in plan agent so plan mode stays Fusion-aware.sidekick(subagent): a cheaper, fast model with fulleditand broadbashaccess (directgit commit/git pushand common wrappers are denied as defense-in-depth - committing stays with the main agent). It executes precise specs handed to it by the main agent.explore(subagent): a cheap model used for read-only codebase exploration.research(subagent): read-only external research - web search and docs. No edit access.design(subagent): frontend/UI implementation. Loads design skills, edits files, runs the dev/build tooling.reviewer(subagent): critiques a plan before implementation and audits a diff before commit (correctness, scope, security). Read-only plus lint/test; no edit access.vision(subagent): reads images/screenshots the main model cannot see and reports them as text. Only needed when the main model lacks image input.
What ships with it
17 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agent/build.md 14 KB
- agent/design.md 4.7 KB
- agent/plan.md 6.5 KB
- agent/research.md 3.3 KB
- agent/reviewer.md 6.0 KB
- agent/sidekick.md 4.2 KB
- agent/vision.md 2.8 KB
- commands/fusion-setup.md 914 B
- commands/fusion-status.md 3.4 KB
- plugins/fusion-audit.js 4.0 KB runs code
- plugins/fusion-claude.js 17 KB runs code
- profiles/chatgpt.json 592 B
- profiles/github-copilot.json 782 B
- profiles/opencode-go.json 786 B
- profiles/opencode-zen-free.json 645 B
- profiles/opencode-zen.json 884 B
- scripts/install.js 32 KB runs code
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.
- 4d ago First seen · 236 lines · 166 tokens per session scan A a84ccc2f23e2
fusion-setup is a skill published in the GitHub repository mihneaptu/opencode-fusion (216 stars, last pushed 10d ago), licensed MIT. It adds 166 tokens to every session and 6,788 once invoked, about $0.0008 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.
Other skills, from other repositories
debate
Structured adversarial analysis protocol. Quick single-agent modes (challenge, panel, pre-mortem, red team) plus a decision-review protocol where one agent proposes, one critiques, the proposer revises, and a binding/advisory judge panel decides ADOPT/REVISE/REJECT/ESCALATE.
update-to-latest
Safety-critical operational pipeline for analyzing and executing OpenCode/OMO updates with explicit approval, patch preservation, rollback capability, and evidence-state discipline.
patch-tracker
Track and verify custom patches to external dependencies. Register, audit, and verify patches survive updates. CRUD lifecycle for patch entries with post-update verification.
reader-report
Reader-first writing for any deliverable a human reads to understand a result: HTML reports, MD design docs, debate-result summaries, survey dashboards, executive briefs, handoff notes, panel-review syntheses. Writes for a reader who has NOT read the preceding material. NOT for: bug reports, incident reports, status…
merge-agent
Safely merge a worktree branch into main with strict local state tracking, lock discipline, and deterministic rollback.
parallel-dev
Skill "parallel-dev" from EZotoff/ez-omo-config, covering parallel-dev, should i parallelize? decision framework, mandatory preconditions (all must be yes), risk assessment (proceed if acceptable) and decision matrix.