goal-quench

Estimate token budgets, alert on thresholds, and verify output quality for /goal sessions.

7|Updated May 26, 2026
One-click install
npx skills add https://github.com/chrono-meta/forge-harness --skill goal-quench
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: goal-quench
Source: https://github.com/chrono-meta/forge-harness/tree/main/plugins/fh-meta/skills/goal-quench
Command: npx skills add https://github.com/chrono-meta/forge-harness --skill goal-quench

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Running /goal sessions carries two hidden risks: silent token exhaustion from unbounded execution, and unvetted output quality since Haiku only checks task completion not correctness. goal-quench closes these gaps with built-in budget controls and quality verification.

Core Features & Use Cases

  • Tiered Safety Modes: Core mode adds pre-run token budget estimates, mid-run budget threshold alerts, and post-run quality verification via pipeline-conductor. Pro mode adds token reduction and goal decomposition into sequential sub-goals for large tasks. Max mode adds external tool discovery and capability gap filling for complex, research-heavy work.
  • Autonomy Ladder: Supports graduated unattended operation for recurring loops, with strict irreversible-action guardrails and mandatory human review for high-risk work.
  • Use Case: Run high-stakes /goal sessions for cross-system refactors, full-project migrations, or complex feature builds without risking unexpected token overages or unvetted AI-generated outputs.

Quick Start

Use the goal-quench skill to run your planned /goal task with a token budget pre-check and automatic post-run quality verification.

Frequently Asked Questions about goal-quench

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

FAQPage Schema
How do I prevent silent token exhaustion during Claude Code goal sessions?▼

Prevent silent token exhaustion during Claude Code goal sessions by applying pre-run budget estimation and mid-run threshold alerts to strictly bound execution costs before they overage.

What is AI quality gating for code generation and how does it work?▼

AI quality gating for code generation is a post-run verification process that checks output correctness, ensuring AI-generated work meets specific quality standards rather than just confirming task completion.

How do I decompose large cross-system refactoring tasks into manageable sub-goals?▼

Decompose large cross-system refactoring tasks by using goal orchestration to sequentially break down complex work into manageable sub-goals, reducing token usage and improving execution control.

Can I run unattended AI goal execution loops for recurring tasks?▼

Yes, you can run unattended AI goal execution loops for recurring tasks using a graduated autonomy ladder, provided strict irreversible-action guardrails and mandatory human review are active for high-risk work.

What are the limitations of running complex feature builds without a token budget pre-check?▼

Running complex feature builds without a token budget pre-check risks unbounded execution that silently exhausts token limits and outputs unvetted AI-generated code lacking correctness verification.