goal-checker
CommunityKeep subagent outputs on target and aligned.
Software Engineering#subagent#drift-detection#quality-assurance#intervention#goal-alignment#output-evaluation#long-running-pipelines
AuthorMinhThang1009
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Evaluates subagent outputs to ensure they address the original objective, flagging drift, tangential content, or overly brief results so that interventions can be triggered.
Core Features & Use Cases
- Score alignment by returning a 0–5 rating with thresholds for intervention (re-anchor for scores 2–3, compact + respawn for <2).
- Trigger prompts when users explicitly ask to check goal alignment or detect goal drift.
- Supports automated pipelines by providing a clear, actionable verdict and recommended actions to re-align outputs.
Quick Start
Evaluate the latest subagent output against the original objective and return a 0–5 alignment score along with recommended intervention steps.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 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: goal-checker Download link: https://github.com/MinhThang1009/dotclaude/archive/main.zip#goal-checker Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 510,000+ vetted skills library on demand.