Skip to content
Back to skills

Fan Out

ASecurity

Parallel agent orchestration for OST exploration. Fan-out multiple solution explorations, fan-in results to compare and select winners.

  • 46 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added May 28, 2026
developmentgit

Security analysis

A100/100

Scanned September 30, 2026

npx -y skills add haabe/mycelium --skill fan-out --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Fan Out?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Fan Out
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/haabe-fan-out/badge)](https://www.skillsdirectory.com/skills/haabe-fan-out)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: fan-out
description: "Parallel agent orchestration for OST exploration. Fan-out multiple solution explorations, fan-in results to compare and select winners."
metadata:
  instruction_budget: "22"
  framework_dependency: "mycelium"
  framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin install mycelium@haabe-mycelium."
---

# Fan-Out / Fan-In Orchestration

## When to Use
- OST has 2+ solutions for the same opportunity that need parallel exploration
- Independent delivery work items that can be parallelized
- Multiple research streams needed simultaneously

## Workflow

### 1. Prepare (Lead Agent)
- Read .claude/canvas/opportunities.yml
- Identify solutions needing parallel work
- For each: identify riskiest assumption and design test

### 2. Fan-Out (Spawn Workers)
For each solution:
- Spawn subagent or Agent Team member
- Provide: clear task, read-only canvas context, worktree isolation, time bound
- Each worker runs independently

### 3. Fan-In (Collect Results)
- Collect all worker results
- Update ICE scores in canvas
- Run `/mycelium:bias-check` on combined findings
- Select winner(s) based on evidence
- Log decision in .claude/harness/decision-log.md

### Leaf Bakeoff Mode

When comparing competing OST leaves for the same opportunity:
- Each worker returns a structured **scorecard** (Four Risks + ICE + assumption test result + segment fit)
- Lead agent applies **winner selection rules**: clear winner (>20% ICE delta), close race (tiebreaker), segment split (both advance), both fail (archive and re-evaluate)
- Losers are archived to `.claude/canvas/archived-solutions.yml` with full evidence snapshot

See `${CLAUDE_PLUGIN_ROOT}/orchestration/leaf-bakeoff.md` for the complete bakeoff protocol.

## Rules
- Workers NEVER write to canvas (lead agent does)
- Workers NEVER progress diamonds
- Lead agent ALWAYS runs bias check on combined results
- Minimum 2 workers for meaningful comparison
- Maximum 3 leaves per bakeoff (respects L3 WIP ceiling)
- Inside an L3 (v0.301.0), the leaves are its set under the L2's target, and a clear winner is the candidate for its `front_runner`; recording it is the human's choice

See `${CLAUDE_PLUGIN_ROOT}/orchestration/agent-teams.md` for full orchestration patterns.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.