subagent-testing

subagent-testing is a skill for Claude Code from athola/claude-night-market. It costs 22 tokens per session (823 once invoked), scanned A, original, MIT.

A testing method for skills that uses new, independent agent sessions to check behavior without influence from earlier conversations. It follows TDD, or test-driven development, by testing a baseline, adding the skill, and comparing the results.

In plain words
What is it for?
Use it to test agent skills, compare before-and-after behavior, and validate effectiveness with isolated subagents.
Why use it?
It reduces bias caused by previous context and makes it easier to tell whether the skill itself improved the result. The process also supports repeatable measurements.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the abstract plugin — 16 skills, 17 commands, 5 agents, 4 hooks shipped together

Good fit Use it to test agent skills, compare before-and-after behavior, and validate effectiveness with isolated subagents.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/athola/claude-night-market/subagent-testing
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add athola/claude-night-market --skill subagent-testing
Clone the repo
git clone --depth 1 https://github.com/athola/claude-night-market

Made for: Claude Code.

Or install abstract, the plugin that ships this one along with the rest of its 16 skills, 17 commands, 5 agents, 4 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for subagent-testing

README.md
[![agentmods](https://agentmods.dev/badge/skills/athola/claude-night-market/subagent-testing/github.svg)](https://agentmods.dev/skills/athola/claude-night-market/subagent-testing)
Your own site
<a href="https://agentmods.dev/skills/athola/claude-night-market/subagent-testing"><img src="https://agentmods.dev/badge/skills/athola/claude-night-market/subagent-testing/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for subagent-testing

Your own site · 80×15
<a href="https://agentmods.dev/skills/athola/claude-night-market/subagent-testing"><img src="https://agentmods.dev/badge/skills/athola/claude-night-market/subagent-testing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 823 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00022 $0.00823
Opus 5 $0.00011 $0.00411
Sonnet 5 $0.00004 $0.00165
Haiku 4.5 $0.00002 $0.00082

Measured 6d ago against content hash f04b55c990c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

subagent-testing scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/abstract/skills/subagent-testing/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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
  2. Why Fresh Instances Matter
  3. Testing Methodology
  4. Quick Start
  5. Detailed Testing Guide
  6. 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:

Read the full file on GitHub · 114 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 114 lines · 22 tokens per session scan A f04b55c990c7

Subscribe to this mod's changes

subagent-testing is a skill published in the GitHub repository athola/claude-night-market (337 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 823 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

plan-to-tdd

Transform feature plans into test-driven implementation using Outside-In methodology. This skill should be used when converting documented plans from docs/plan/ into testable code w/ proper test structure (Unit, Integration, E2E).

georgekhananaev/claude-skills-vault · 49 tokens

webapp-testing

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

shajith003/awesome-claude-skills · 35 tokens

agentforge-protocol

Use when doing non-trivial coding with Hermes, OpenClaw, Claude Code, Codex CLI, or similar autonomous coding agents. Orchestrates Karpathy-style minimal-change discipline, grill-plan intake, TDD, systematic debugging, subagent-driven implementation, spikes, and pre-commit review into one end-to-end workflow.

Yat-mo/agentforge-protocol · 71 tokens

python

Python development with ruff, mypy, pytest - TDD and type safety.

alinaqi/maggy · 18 tokens

conductor-implement

Execute tasks from a track's implementation plan following TDD workflow.

rmyndharis/antigravity-skills · 17 tokens

principle-test-behavior-not-implementation

Apply when you write, change, or keep a test. Call the code the way its users do and assert the result they observe against a literal expected value. If the test would still pass when every imported function returns undefined, rewrite the assertion or delete the test.

michael-denyer/pstack-claude · 63 tokens