fairy-tale

Official

Budgeted, evidence-driven agent workflow harness.

Authorbonginkan
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Unstructured agent runs often exceed budgets, skip validation, or miss hidden gaps in code, documents, or requirements. This Skill imposes a disciplined harness with budget caps, evidence tracking, and multi-layer validation to keep complex workflows reliable and reproducible.

Core Features & Use Cases

  • Budgeted Execution: Define time, tool-call, and context limits before starting long tasks.
  • Validation Gates: Enforce residency checks, closure checks, negative-space discovery, and e2e completion discipline.
  • Use Case: Run a multi-file codebase migration with scoped edits and rollback paths, or execute a defensive security review with authorized-target enforcement and responsible-disclosure framing.

Quick Start

Invoke the fairy-tale skill to run your next complex agent workflow with automatic budget limits, evidence maps, and validation gates.

Dependency Matrix

Required Modules

None required

Components

references

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: fairy-tale
Download link: https://github.com/bonginkan/fairy_tale/archive/main.zip#fairy-tale

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 536,000+ vetted skills library on demand.