Skill

fan-out

Orchestrates fan-out of subagents for parallel exploration of 2+ OST solutions, fans in results for ICE scoring, bias check, and winner selection via bakeoff. Use for independent research streams.

automation

developer-tools

npx claudepluginhub haabe/mycelium --plugin mycelium

Tool Access

This skill uses the workspace's default tool permissions.

Preview

- OST has 2+ solutions for the same opportunity that need parallel exploration

SKILL.md

Similar Skills

orchestration

Orchestrates multi-agent workflows with parallel pipelines, sync barriers, state tracking, checkpointing, and progress metrics. Use for coordinating 3+ agents across sessions.

18 files12 tools

jerry

fleet

549

Orchestrates parallel campaigns in coordinated waves, spawning 2-3 agents per wave in isolated git worktrees. Collects discoveries and shares context between waves. For 3+ independent work streams.

2 files

citadel

oma-orchestrator

928

Automates multi-agent execution with task decomposition, parallel dispatch, memory coordination, and verification loops for complex features.

oma

Stats

Parent Repo Stars24

Parent Repo Forks4

Last CommitMay 9, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

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)

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