testing-agents-with-subagents

testing-agents-with-subagents is a skill for Claude Code from notque/vexjoy-agent. It costs 21 tokens per session (1,626 once invoked), scanned A, original, MIT.

A way to test coding agents by sending them known inputs through separate helper agents and checking their exact outputs. It applies TDD, or test-driven development, by observing failures before changing the agent and checking again afterward.

In plain words
What is it for?
Testing reviewer, implementation, analysis, and routing agents across normal, complex, edge-case, ambiguous, and invalid inputs.
Why use it?
It tests what an agent actually does instead of assuming its written instructions produce the intended behavior.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents.

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.

agentmods
npx agentmods add skills/notque/vexjoy-agent/testing-agents-with-subagents
Any agent
npx skills add notque/vexjoy-agent --skill testing-agents-with-subagents
Clone the repo
git clone --depth 1 https://github.com/notque/vexjoy-agent

Made for: Claude Code.

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 testing-agents-with-subagents

README.md
[![agentmods](https://agentmods.dev/badge/skills/notque/vexjoy-agent/testing-agents-with-subagents.svg)](https://agentmods.dev/skills/notque/vexjoy-agent/testing-agents-with-subagents)
Your own site
<a href="https://agentmods.dev/skills/notque/vexjoy-agent/testing-agents-with-subagents"><img src="https://agentmods.dev/badge/skills/notque/vexjoy-agent/testing-agents-with-subagents.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,626 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00021 $0.01626
Opus 5 $0.00010 $0.00813
Sonnet 5 $0.00004 $0.00325
Haiku 4.5 $0.00002 $0.00163

Measured 2d ago against content hash 7e281fd16767, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

testing-agents-with-subagents 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 2d 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.

skills/testing/testing-agents-with-subagents/SKILL.md · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Testing Agents With Subagents

Overview

This skill applies TDD methodology to agent development — RED (observe failures), GREEN (fix agent definition), REFACTOR (edge cases and robustness) — with subagent dispatch as the execution mechanism.

Test what the agent DOES, not what the prompt SAYS. Evidence-based verification only: capture exact outputs from subagent dispatch, verify every prompt change through testing. Always test via the Task tool, always test via the Task tool rather than reading prompts.

Minimum test counts vary by agent type: Reviewer agents need 6 cases (2 real issues, 2 clean, 1 edge, 1 ambiguous), Implementation agents 5 cases (2 typical, 1 complex, 1 minimal, 1 error), Analysis agents 4 cases (2 standard, 1 edge, 1 malformed), Routing/orchestration 4 cases (2 correct route, 1 ambiguous, 1 invalid). No agent is simple enough to skip testing — get human confirmation before exempting any agent.

Each test runs in a fresh subagent to avoid context pollution. After any fix, re-run ALL test cases to catch regressions. One fix at a time — you cannot determine what changed the outcome with multiple simultaneous fixes.


Reference Loading Table

Signal Load These Files Why
example-driven tasks, errors examples-and-errors.md Loads detailed guidance from examples-and-errors.md.
dispatch-and-capture, negative, consistency, A/B, and routing-verification test patterns testing-patterns.md Loads detailed guidance from testing-patterns.md.

Instructions

Phase 0: PREPARE — Understand the Agent

Goal: Read the agent definition and understand what it claims to do before writing tests.

Step 1: Read the agent file

# Read agent definition
cat agents/{agent-name}.md

# Read any referenced skills
cat skills/{skill-name}/SKILL.md

Step 2: Identify testable claims

Extract concrete, testable behaviors from the agent definition:

  • What inputs does it accept?
  • What output structure does it produce?
  • What routing triggers should activate it?
  • What error conditions does it handle?
  • What skills does it invoke?

Read the full file on GitHub · 181 lines

Files

What ships with it

2 files 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. 2d ago First seen · 181 lines · 21 tokens per session scan A 7e281fd16767

Subscribe to this mod's changes

testing-agents-with-subagents is a skill published in the GitHub repository notque/vexjoy-agent (419 stars, last pushed yesterday), licensed MIT. It adds 21 tokens to every session and 1,626 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.