fuse

A workflow that asks several local coding agents to solve the same task in separate Git worktrees, then compares and combines their results. A worktree is an isolated working copy of a repository.

In plain words
What is it for?
Use it for tasks where you want Claude, Codex, Gemini, or other local agents to produce competing solutions that can be reviewed and integrated.
Why use it?
It lets you compare independent implementations and select useful ideas before bringing a final change into the main working copy.

Skill for Claude CodeCodex

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 skills/taekwonv/fuse-skill/fuse
Any agent
npx skills add taekwonv/fuse-skill --skill fuse
Clone the repo
git clone --depth 1 https://github.com/taekwonv/fuse-skill

Made for: Claude Code, Codex.

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,660 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 $0.00062 $0.04660
Opus 5 $0.00031 $0.02330
Sonnet 5 $0.00012 $0.00932
Haiku 4.5 $0.00006 $0.00466

Measured 2d ago against content hash d4f30994dfe8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fuse 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 2d 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.

claude/fuse/SKILL.md · 695 lines

How it starts

The opening of the file, as written. The whole thing — 695 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Skill: Fuse

You are Claude Code running the fuse skill. When the user invokes /fuse, you are the orchestrator by default.

User arguments, if provided by Claude Code, are:

$ARGUMENTS

Parse those arguments as the Fuse request. Then follow the workflow below.

Fuse — Multi-Agent Worktree Fusion

Fuse helps coding agents produce better results by making multiple agents work in parallel, then taking the strongest parts of each result.

Instead of asking one model or agent to solve a task once, Fuse sends the same task to several agents such as Claude Code, Codex, Gemini CLI, OpenCode, Qwen Code, or other local coding agents. Each worker agent solves the task independently in its own isolated git worktree. The orchestrator compares their patches and reports, identifies the best ideas, optionally asks for peer review, and integrates the strongest final result.

                 User task
                    |
                    v
            Orchestrator agent
                    |
       +------------+------------+
       |            |            |
       v            v            v
   Claude worker  Codex worker  Gemini worker
   private tree   private tree   private tree
       |            |            |
       +------------+------------+
                    |
                    v
          Judge + final integrator
                    |
                    v
             Best final result

The non-negotiable rule is:

1 selected worker agent = 1 private git worktree

Claude, Codex, Gemini, Qwen, OpenCode, or any other worker must never share one worktree.


Invocation Syntax

Treat all of the following as Fuse requests:

/fuse agents: claude,codex task: Fix the booking status race condition.
/fuse agents: claude,gemini tests: ./gradlew test task: Refactor notification dispatch.
/fuse agents: claude@sonnet,[email protected],gemini@pro base: main task: Improve auth middleware.

Read the full file on GitHub · 695 lines

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. 2d ago First seen · 695 lines · 62 tokens per session scan A d4f30994dfe8

Subscribe to this mod's changes

fuse is a skill published in the GitHub repository taekwonv/fuse-skill (2 stars, last pushed 2mo ago), licensed MIT. It adds 62 tokens to every session and 4,660 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens