Testing Skills With Subagents

Testing Skills With Subagents is a skill for Claude Code from obra/superpowers-skills. It costs 29 tokens per session (2,903 once invoked), scanned A, original, MIT.

A testing method for process documentation based on the RED-GREEN-REFACTOR cycle from TDD, or test-driven development. You first observe an agent without the skill, then write the skill to address the failures, and finally close remaining loopholes.

In plain words
What is it for?
Use it to test instructions about discipline, testing, required effort, or quality checks. It provides pressure scenarios and rationalization tables, while excluding pure reference material with no rules to follow.
Why use it?
It shows whether a skill prevents the specific mistakes it is meant to prevent instead of merely sounding clear. It is especially useful for rules that agents may be tempted to skip.

Skill for Claude Code

Written for Claude Code: when-to-use in frontmatter. Also seen: mentions CLAUDE.md; mentions subagents.

Good fit Use it to test instructions about discipline, testing, required effort, or quality checks. It provides pressure scenarios and rationalization tables, while excluding pure reference material with no rules to follow.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/obra/superpowers-skills/testing-skills-with-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.

Any agent
npx skills add obra/superpowers-skills --skill testing-skills-with-subagents
Clone the repo
git clone --depth 1 https://github.com/obra/superpowers-skills

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 Skills With Subagents

README.md
[![agentmods](https://agentmods.dev/badge/skills/obra/superpowers-skills/testing-skills-with-subagents/github.svg)](https://agentmods.dev/skills/obra/superpowers-skills/testing-skills-with-subagents)
Your own site
<a href="https://agentmods.dev/skills/obra/superpowers-skills/testing-skills-with-subagents"><img src="https://agentmods.dev/badge/skills/obra/superpowers-skills/testing-skills-with-subagents/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 Testing Skills With Subagents

Your own site · 80×15
<a href="https://agentmods.dev/skills/obra/superpowers-skills/testing-skills-with-subagents"><img src="https://agentmods.dev/badge/skills/obra/superpowers-skills/testing-skills-with-subagents.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,903 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
  • Socket pass 20 Feb 2026
  • Snyk pass 20 Feb 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 $0.00029 $0.02903
Opus 5 $0.00015 $0.01452
Sonnet 5 $0.00006 $0.00581
Haiku 4.5 $0.00003 $0.00290

Measured 11d ago against content hash f0dc03f68c34, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

Testing Skills 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 11d 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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

skills/meta/testing-skills-with-subagents/SKILL.md · 391 lines

How it starts

The opening of the file, as written. The whole thing — 391 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Testing Skills With Subagents

Overview

Testing skills is just TDD applied to process documentation.

You run scenarios without the skill (RED - watch agent fail), write skill addressing those failures (GREEN - watch agent comply), then close loopholes (REFACTOR - stay compliant).

Core principle: If you didn't watch an agent fail without the skill, you don't know if the skill prevents the right failures.

See skills/testing/test-driven-development for the fundamental cycle. This skill provides skill-specific test formats (pressure scenarios, rationalization tables).

Complete worked example: See examples/CLAUDE_MD_TESTING.md for a full test campaign testing CLAUDE.md documentation variants.

When to Use

Test skills that:

  • Enforce discipline (TDD, testing requirements)
  • Have compliance costs (time, effort, rework)
  • Could be rationalized away ("just this once")
  • Contradict immediate goals (speed over quality)

Don't test:

  • Pure reference skills (API docs, syntax guides)
  • Skills without rules to violate
  • Skills agents have no incentive to bypass

TDD Mapping for Skill Testing

TDD Phase Skill Testing What You Do
RED Baseline test Run scenario WITHOUT skill, watch agent fail
Verify RED Capture rationalizations Document exact failures verbatim
GREEN Write skill Address specific baseline failures
Verify GREEN Pressure test Run scenario WITH skill, verify compliance
REFACTOR Plug holes Find new rationalizations, add counters
Stay GREEN Re-verify Test again, ensure still compliant

Same cycle as code TDD, different test format.

RED Phase: Baseline Testing (Watch It Fail)

Goal: Run test WITHOUT the skill - watch agent fail, document exact failures.

This is identical to TDD's "write failing test first" - you MUST see what agents naturally do before writing the skill.

Process:

  • Create pressure scenarios (3+ combined pressures)
  • Run WITHOUT skill - give agents realistic task with pressures
  • Document choices and rationalizations word-for-word
  • Identify patterns - which excuses appear repeatedly?
  • Note effective pressures - which scenarios trigger violations?

Read the full file on GitHub · 391 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. 11d ago First seen · 391 lines · 29 tokens per session scan A f0dc03f68c34

Subscribe to this mod's changes

Testing Skills With Subagents is a skill published in the GitHub repository obra/superpowers-skills (748 stars, last pushed 11mo ago), licensed MIT. It adds 29 tokens to every session and 2,903 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 2026-08-30.