What is aid-design-test?

A planning aid for deciding what specific tests should check. It records the code or behavior under test, test cases, and the test framework and supporting data needed.

Use it to design individual tests before another step writes them; it does not write production code or run existing test suites.

It prevents test writing from starting before the expected behavior and test setup are clear.

aid-design-test — Skill for Claude Code by AndreVianna

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 AndreVianna/aid-methodology --skill aid-design-test

Clone the repo

git clone --depth 1 https://github.com/AndreVianna/aid-methodology

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/andrevianna/aid-methodology/aid-design-test/github.svg)](https://agentmods.dev/skills/andrevianna/aid-methodology/aid-design-test)

Your own site

<a href="https://agentmods.dev/skills/andrevianna/aid-methodology/aid-design-test"><img src="https://agentmods.dev/badge/skills/andrevianna/aid-methodology/aid-design-test/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/andrevianna/aid-methodology/aid-design-test"><img src="https://agentmods.dev/badge/skills/andrevianna/aid-methodology/aid-design-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 155 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 985 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.

Origin 86% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5.1	$0.00155	$0.00985
Opus 5	$0.00077	$0.00492
Sonnet 5	$0.00031	$0.00197
Haiku 4.5	$0.00015	$0.00098

Measured 12d ago against content hash 9b0949a920ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

aid-design-test 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 12d 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

This is a copy

86% identical to aid-design-cli — 54 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/skills/aid-design-test/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Test (develop a design seed, resolve nothing)

Bind VERB=design, ARTIFACT=test -- the design stage in the contract's vocabulary -- then follow the shared contract at .claude/aid/templates/design-lifecycle.md. This skill binds that contract and restates none of its rules. The seed it writes is .aid/design/test.md; realizing it into authored tests is /aid-create-test's job, not this one's.

Boundary vs /aid-create-test: that skill authors the tests from a ready seed; this one only develops the seed. Neither resolves anything on its own -- the user decides when a seed is ready to realize.
Boundary vs /aid-design-testing-strategy and /aid-test: the first designs the testing policy, not specific tests; /aid-test runs existing suites rather than designing them.
Not a numbered pipeline phase; does not route to /aid-execute.

State machine: INTAKE -> DESIGN -> VERIFY (loop) -> PRESENT [user decides] -> DONE, as design-lifecycle.md § Skill shape defines it. Print the [State: NAME] -- {purpose} entry line on each state.

State: INTAKE

Require a subject. Empty argument -> ask one bootstrapping question ("What tests do you want to design -- the units under test, the cases, and the framework?") and wait.
Allocate through the Work Initiation Gate exactly as the contract's Allocation rule requires (.claude/skills/aid-design/SKILL.md INTAKE step 4 is the shape), with initiator: aid-design-test. phase is not driven.
Acquire .aid/design/ per the contract, then read .aid/design/test.md if a prior seed exists -- re-invocation iterates it rather than starting over.
Classify complexity for the aid-architect dispatch (verifier tier >= producer).

Advance: DESIGN.

State: DESIGN

Dispatch aid-architect (clean context, tiered) to write or iterate .aid/design/test.md in the seed shape the contract fixes (design-seed.md; feature-002 §4), grounded in .aid/knowledge/ and the project source plus any seed read in INTAKE. What this artifact's seed must settle: the units under test, the cases, and the framework and fixtures; its ## Destination names where the authored tests land. Never writes .aid/knowledge/ and never writes production code -- the design invariant (design-lifecycle.md).

Read the full file on GitHub · 89 lines

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.

12d ago First seen · 89 lines · 155 tokens per session scan A 9b0949a920ac

Subscribe to this mod's changes

aid-design-test is a skill published in the GitHub repository AndreVianna/aid-methodology (5 stars, last pushed 2d ago), licensed MIT. It adds 155 tokens to every session and 985 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to aid-design-cli, differing in 54 lines, and is treated as a copy.

Testing

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

aid-design-test