testing

A test-planning guide based on Beck's Test Desiderata, a set of properties for judging test quality. It focuses on deciding what a test should specify and which trade-offs matter.

In plain words
What is it for?
Use it to plan tests for a feature or refactor, review an existing test strategy, identify boundaries and assumptions, and balance speed, isolation, readability, and realism.
Why use it?
It helps teams choose useful tests deliberately instead of generating many tests without clear coverage or purpose.

Skill for Claude CodeCodex

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/tslateman/duet/testing
Any agent
npx skills add tslateman/duet --skill testing
Clone the repo
git clone --depth 1 https://github.com/tslateman/duet

Made for: Claude Code, Codex.

Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,838 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 $0.00066 $0.01838
Opus 5 $0.00033 $0.00919
Sonnet 5 $0.00013 $0.00368
Haiku 4.5 $0.00007 $0.00184

Measured 2d ago against content hash 2fbc0c857080, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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/SKILL.md · 215 lines

How it starts

The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Design as Thinking

Overview

Test strategy, not test generation. Treat test design as an act of specification, articulate the contract, find the boundaries, surface hidden assumptions. Use Beck's Test Desiderata to make testing tradeoffs deliberate instead of accidental.

Beck's 12 Test Desiderata

Every test balances these properties. No test maximizes all twelve. The skill is knowing which to prioritize.

Property Definition Tension
Isolated Same results regardless of run order vs. speed (shared setup)
Composable Test dimensions of variability separately vs. writability (more tests)
Deterministic Same results if nothing changes vs. realism (real services)
Fast Run quickly vs. predictiveness (integration)
Writable Cheap to write relative to code cost vs. thoroughness
Readable Comprehensible, invokes motivation vs. conciseness
Behavioral Sensitive to behavior changes vs. structure-insensitivity
Structure-insensitive Unaffected by refactoring vs. behavioral sensitivity
Automated No human intervention needed vs. exploratory testing
Specific Failure cause is obvious vs. breadth of coverage
Predictive Passing means production-ready vs. speed and isolation
Inspiring Passing builds confidence to deploy vs. all other properties

See references/desiderata.md for application guidance.

Test Design Workflow

1. Articulate the Contract

Read the full file on GitHub · 215 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 · 215 lines · 66 tokens per session scan A 2fbc0c857080

Subscribe to this mod's changes

testing is a skill published in the GitHub repository tslateman/duet (1 stars, last pushed 5d ago), licensed MIT. It adds 66 tokens to every session and 1,838 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories