fan-out-then-update-ledger

Spawns helper subagents at run time and records results in an accounting ledger.

1|Updated Jul 1, 2026
One-click install
npx skills add https://github.com/ginaecho/skill-achievability-compiler --skill fan-out-then-update-ledger-ginaecho
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: fan-out-then-update-ledger
Source: https://github.com/ginaecho/skill-achievability-compiler/tree/main/corpus/skills/spawn_with_ghost_tool
Command: npx skills add https://github.com/ginaecho/skill-achievability-compiler --skill fan-out-then-update-ledger-ginaecho

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Coordinating distributed work across dynamically spawned subagents and reconciling their results into a single ledger entry is hard to do consistently. This Skill defines a planner workflow that fans work out to helper subagents created during execution and guarantees the outcome is recorded in the accounting ledger. ## Core Features & Use Cases - Dynamic Subagent Spawning: Helper subagents are created at run time, with their number decided during execution rather than in advance. - Result Collection: The planner gathers whatever the helper subagents return before proceeding. - Mandatory Ledger Update: The outcome is recorded in the accounting ledger via the update_ledger capability, and the job is not finished until the ledger reflects the work done. - Use Case: A bookkeeping agent splits reconciliation work across several helper subagents, collects their findings, and writes the consolidated result into the ledger so the books always match the work performed. ## Quick Start Ask the planner agent to fan the reconciliation work out to helper subagents and update the accounting ledger with the collected results.

Frequently Asked Questions about fan-out-then-update-ledger

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I spawn subagents dynamically during agent execution?▼

The planner spawns helper subagents at run time rather than predefining them, deciding the number of helpers during execution based on the work at hand. The planner then collects their results before completing the task.

How do I record multi-agent work results in an accounting ledger?▼

After collecting results from helper subagents, the planner records the outcome via the update_ledger capability. The ledger entry is mandatory, so the job is only finished once the books reflect the work done.

What tools does this skill require to run?▼

The skill itself is granted no tools, but the workflow requires the runtime to support spawning subagents and an update_ledger capability. Without these capabilities in the execution environment, the workflow cannot complete.

When should I use dynamic subagent fan-out instead of a fixed pipeline?▼

Use dynamic fan-out when the amount of parallel work is unknown upfront and must be decided during execution. A fixed pipeline is better when the number of workers and tasks can be determined before the run starts.