/subagent-testing

name: subagent-testing
description: 'Test skills via TDD in fresh subagents. Use when validating behavior or preventing bias.'
alwaysApply: false
category: testing
tags:
- testing
- validation
- TDD
- subagents
- fresh-instances
token_budget: 30
progressive_loading: true
modules:
- modules/testing-patterns.md
model_hint: standard

Subagent Testing - TDD for Skills

Test skills with fresh subagent instances to prevent priming bias and validate effectiveness.

When NOT To Use

• Writing the skill under test (use `abstract:skill-authoring`)
• A static quality audit with no execution (use `abstract:skills-eval`)

Table of Contents

1. [Overview](#overview) 2. [Why Fresh Instances Matter](#why-fresh-instances-matter) 3. [Testing Methodology](#testing-methodology) 4. [Quick Start](#quick-start) 5. [Detailed Testing Guide](#detailed-testing-guide) 6. [Success Criteria](#success-criteria)

Overview

**Fresh instances prevent priming:** Each test uses a new Claude conversation to verify the skill's impact is measured, not conversation history effects.

Why Fresh Instances Matter

The Priming Problem

Running tests in the same conversation creates bias:

• Prior context influences responses
• Skill effects get mixed with conversation history
• Can't isolate skill's true impact

Fresh Instance Benefits

• **Isolation**: Each test starts clean
• **Reproducibility**: Consistent baseline state
• **Measurement**: Clear before/after comparison
• **Validation**: Proves skill effectiveness, not priming

Testing Methodology

Three-phase TDD-style approach:

Phase 1: Baseline Testing (RED)

Test without skill to establish baseline behavior.

Phase 2: With-Skill Testing (GREEN)

Test with skill loaded to measure improvements.

Phase 3: Rationalization Testing (REFACTOR)

Test skill's anti-rationalization guardrails.

Quick Start

# 1. Create baseline tests (without skill)
# Use 5 diverse scenarios
# Document full responses

# 2. Create with-skill tests (fresh instances)
# Load skill explicitly
# Use identical prompts
# Compare to baseline

# 3. Create rationalization tests
# Test anti-rationalization patterns
# Verify guardrails work

Detailed Testing Guide

For complete testing patterns, examples, and templates:

• **[Testing Patterns](modules/testing-patterns.md)** - Full TDD methodology
• **[Test Examples](modules/testing-patterns.md)** - Baseline, with-skill, rationalization tests
• **[Analysis Templates](modules/testing-patterns.md)** - Scoring and comparison frameworks

Success Criteria

• **Baseline**: Document 5+ diverse baseline scenarios
• **Improvement**: ≥50% improvement in skill-related metrics
• **Consistency**: Results reproducible across fresh instances
• **Rationalization Defense**: Guardrails prevent ≥80% of rationalization attempts

See Also

• **skill-authoring**: Creating effective skills
• **test-skill**: Automated skill testing command

Exit Criteria

• [ ] Baseline (RED) phase documents at least 5 diverse scenarios run in fresh Claude instances

without the skill active, with full response text recorded.

• [ ] With-skill (GREEN) phase uses identical prompts in new fresh instances (not continuations

of the baseline conversation) and shows >= 50% improvement on skill-related metrics.

• [ ] Rationalization (REFACTOR) phase shows skill guardrails blocking >= 80% of rationalization

attempts tested across at least 3 pressure scenarios.

• [ ] Results are reproducible: the same prompts in a new fresh instance produce consistent

outcomes, confirming the effect is not conversation-history priming.