Agent skill

Subagent Testing

Test skills via TDD in fresh subagents. An agent skill from athola/claude-night-market.

MITAuto-check passedTesting & QA

Install Subagent Testing

skills CLI

$ npx skills add athola/claude-night-market --skill subagent-testing -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install athola/claude-night-market subagent-testing --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/athola/claude-night-market.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/abstract/skills/subagent-testing .claude/skills/subagent-testing && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "subagent-testing" agent skill from https://github.com/athola/claude-night-market/tree/master/plugins/abstract/skills/subagent-testing into .claude/skills/subagent-testing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "subagent-testing", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/athola/claude-night-market/tree/master/plugins/abstract/skills/subagent-testing

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add athola/claude-night-market --skill subagent-testing -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install athola/claude-night-market subagent-testing --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/athola/claude-night-market.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/abstract/skills/subagent-testing .agents/skills/subagent-testing && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "subagent-testing" agent skill from https://github.com/athola/claude-night-market/tree/master/plugins/abstract/skills/subagent-testing into .agents/skills/subagent-testing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "subagent-testing", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add athola/claude-night-market --skill subagent-testing -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install athola/claude-night-market subagent-testing --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/athola/claude-night-market.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/abstract/skills/subagent-testing .cursor/skills/subagent-testing && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "subagent-testing" agent skill from https://github.com/athola/claude-night-market/tree/master/plugins/abstract/skills/subagent-testing into .cursor/skills/subagent-testing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "subagent-testing", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/athola/claude-night-market.git --path plugins/abstract/skills/subagent-testing

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add athola/claude-night-market --skill subagent-testing -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install athola/claude-night-market subagent-testing --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/athola/claude-night-market.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/abstract/skills/subagent-testing .gemini/skills/subagent-testing && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "subagent-testing" agent skill from https://github.com/athola/claude-night-market/tree/master/plugins/abstract/skills/subagent-testing into .gemini/skills/subagent-testing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "subagent-testing", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install athola/claude-night-market subagent-testing

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add athola/claude-night-market --skill subagent-testing -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/athola/claude-night-market.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/abstract/skills/subagent-testing .github/skills/subagent-testing && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "subagent-testing" agent skill from https://github.com/athola/claude-night-market/tree/master/plugins/abstract/skills/subagent-testing into .github/skills/subagent-testing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "subagent-testing", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add athola/claude-night-market --skill subagent-testing -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install athola/claude-night-market subagent-testing --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/athola/claude-night-market.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/abstract/skills/subagent-testing .opencode/skills/subagent-testing && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "subagent-testing" agent skill from https://github.com/athola/claude-night-market/tree/master/plugins/abstract/skills/subagent-testing into .opencode/skills/subagent-testing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "subagent-testing", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: subagent-testing
GitHub stars: 342
Token cost: ~837 tokens
SKILL.md length: 307 words
Files: 2
Skills in repo: 160
Repo updated: Oct 6, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Test skills via TDD in fresh subagents. An agent skill from athola/claude-night-market.

Works in 3 steps: Baseline Testing (RED) → With-Skill Testing (GREEN) → Rationalization Testing (REFACTOR)
Validating behavior
SKILL.md covers When NOT To Use, Overview, Why Fresh Instances Matter and Testing Methodology, plus 5 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Subagent Testing is an agent skill from athola/claude-night-market. Test skills via TDD in fresh subagents. Use when validating behavior or preventing bias.

Its SKILL.md is about 840 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `modules/testing-patterns.md`).

It sits in Testing & QA, covering Subagents and Test-driven development. The repository describes itself as: 23 Claude Code plugins: TDD enforcement hooks, git/PR workflows, spec-driven development, code review, project lifecycle, fix-from-error, maintenance automation, context… The licence is MIT.

When your agent uses it

Validating behavior
Preventing bias

Example prompts

“/subagent-testing”

Workflow steps

3 steps, taken from the step headings in SKILL.md.

Baseline Testing (RED)
With-Skill Testing (GREEN)
Rationalization Testing (REFACTOR)

What it can do on your machine

Read from SKILL.md and the folder at commit 9f3eb00. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Subagent Testing loads about 837 tokens when it runs. Until then it costs about 26 tokens; SKILL.md has 307 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~26
When it runs · the whole SKILL.md, loaded when a task matches: ~837

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from athola/claude-night-market at commit 9f3eb00, republished under its MIT licence (© athola). 307 words, ~837 tokens.

Download SKILL.mdSave it as .claude/skills/subagent-testing/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.

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)

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

bash

# 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 - Full TDD methodology
Test Examples - Baseline, with-skill, rationalization tests
Analysis Templates - 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

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.

Files

SKILL.md and 1 other file in plugins/abstract/skills/subagent-testing of athola/claude-night-market.

SKILL.md
modules/testing-patterns.md

Open the folder on GitHubat commit 9f3eb00

Compare with similar skills

Subagent Testing next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Subagent Testing compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Subagent Testing this skillathola/claude-night-market	342	—	~837	Automated safety check: Pass	MIT	yesterday
Testing Skills With Subagentsed3dai/ed3d-plugins	250	2 repos	~3.5k	Automated safety check: Pass	None	1 mo ago
Nv Implementnovuhq/novu	40k	—	~1.7k	Automated safety check: Pass	Custom licence	today
Tapd Story ImplementTencentBlueKing/bk-bcs	840	—	~1.2k	Automated safety check: Pass	Custom licence	13 days ago
Implementopen-octo/octo-agent	125	—	~2.3k	Automated safety check: Pass	MIT	2 days ago
Ab Start Taskayoubben18/ab-method	192	—	~376	Automated safety check: Pass	MIT	6 days ago

Similar skills

Testing Skills With Subagents
ed3dai/ed3d-plugins
A skill your agent uses when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation…
250 GitHub starsUsed in 2 repos~3.5k tokens
Testing & QAAuto-check passed
Nv Implement
novuhq/novu
Implement planned work by fanning out parallel subagents on isolated worktrees — TDD at pre-agreed seams, per-slice nv-park-and-review, merge back, full suite once at the end.
40k GitHub stars~1.7k tokensUpdated today
Testing & QAAuto-check passed
Tapd Story Implement
TencentBlueKing/bk-bcs
迭代执行流水线代码实现阶段。基于 tasks.md 调用 /speckit.implement 以 TDD 模式完成全部任务。
840 GitHub stars~1.2k tokensUpdated 13 days ago
Testing & QAAuto-check passed
Implement
open-octo/octo-agent
Implement a technical design by decomposing it into dependency-ordered vertical slices, executing each with TDD red-green, reviewing each via an isolated sub-agent, and persisting progress to a…
125 GitHub stars~2.3k tokensUpdated 2 days ago
Testing & QAAuto-check passed
Ab Start Task
ayoubben18/ab-method
Run an existing task autonomously to completion — each remaining mission in a subagent with tdd, tracker updated per mission, a commit after every green mission.
192 GitHub stars~376 tokensUpdated 6 days ago
Testing & QAAuto-check passed
Writing Skills
ed3dai/ed3d-plugins
A skill your agent uses when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with subagents before writing…
250 GitHub starsUsed in 1 repo~1.3k tokens
Agent WorkflowsAuto-check passed

Questions about Subagent Testing

What does Subagent Testing do?

Test skills via TDD in fresh subagents. An agent skill from athola/claude-night-market. Subagent Testing is an agent skill from athola/claude-night-market. Test skills via TDD in fresh subagents.

When should I use Subagent Testing?

Subagent Testing fits situations like: validating behavior; preventing bias.

How do I install Subagent Testing in Claude Code?

Run `npx skills add athola/claude-night-market --skill subagent-testing -a claude-code`. Or copy the skill folder (plugins/abstract/skills/subagent-testing in athola/claude-night-market) into .claude/skills/subagent-testing in your project. Claude Code loads it when a task matches its description.

How do I install Subagent Testing in Codex?

Run `npx skills add athola/claude-night-market --skill subagent-testing -a codex`. Or copy the skill folder (plugins/abstract/skills/subagent-testing in athola/claude-night-market) into .agents/skills/subagent-testing in your project. Codex loads it when a task matches its description.

Can I use Subagent Testing in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add athola/claude-night-market --skill subagent-testing -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/subagent-testing, .gemini/skills/subagent-testing, .github/skills/subagent-testing and .opencode/skills/subagent-testing in your project.

What does Subagent Testing need to run?

SKILL.md names no scripts, command-line tools or credentials: Subagent Testing is instructions for the agent only.

Does Subagent Testing access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Subagent Testing safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Subagent Testing use?

Subagent Testing is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Subagent Testing use?

About 837 tokens (SKILL.md is roughly 3.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Subagent Testing?

Skills that share tags, products or a category with Subagent Testing: Testing Skills With Subagents (ed3dai/ed3d-plugins, 250 stars), Nv Implement (novuhq/novu, 40k stars), Tapd Story Implement (TencentBlueKing/bk-bcs, 840 stars) and Implement (open-octo/octo-agent, 125 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Subagent Testing?

athola (a GitHub user) maintains it in athola/claude-night-market, which has 342 GitHub stars. The repository holds 160 skills in this directory. The repository was last updated on October 6, 2026.

Source: athola/claude-night-market on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Subagent Testing

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Subagent Testing - TDD for Skills

When NOT To Use

Overview

Why Fresh Instances Matter

The Priming Problem

Fresh Instance Benefits

Testing Methodology

Phase 1: Baseline Testing (RED)

Phase 2: With-Skill Testing (GREEN)

Phase 3: Rationalization Testing (REFACTOR)

Quick Start

Detailed Testing Guide

Success Criteria

See Also

Exit Criteria

Files

Compare with similar skills

Similar skills

More from athola/claude-night-market

Related

Questions about Subagent Testing