test-list

test-list is a command for Claude Code from marcoemrich/EXACT-Coding-Exercises. It costs 0 tokens per session (862 once invoked), scanned A, original, MIT.

A test-planning command for the test-driven development (TDD) stage where expected behavior is written down before the test code. It creates a list of planned tests with Jest's `it.todo()` markers rather than running tests.

In plain words
What is it for?
Use it to read a specification and list tests for every requirement and example, ordered from simple cases to complex ones.
Why use it?
It turns a written feature specification into a checklist, reducing the chance that rules or examples are missed.

Command for Claude Code

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 commands/marcoemrich/exact-coding-exercises/test-list
Clone the repo
git clone --depth 1 https://github.com/marcoemrich/EXACT-Coding-Exercises

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 test-list

README.md
[![agentmods](https://agentmods.dev/badge/commands/marcoemrich/exact-coding-exercises/test-list.svg)](https://agentmods.dev/commands/marcoemrich/exact-coding-exercises/test-list)
Your own site
<a href="https://agentmods.dev/commands/marcoemrich/exact-coding-exercises/test-list"><img src="https://agentmods.dev/badge/commands/marcoemrich/exact-coding-exercises/test-list.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 862 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 $0.00000 $0.00862
Opus 5 $0.00000 $0.00431
Sonnet 5 $0.00000 $0.00172
Haiku 4.5 $0.00000 $0.00086

Measured 3d ago against content hash 8a886725ca25, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-list 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 3d 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.

.claude/commands/test-list.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TDD Test List Phase

You are now in the Test List Phase of TDD. Follow these instructions to create a comprehensive test list.

Your Mission

Create a test list using it.todo() that covers every rule and every example from the specification:

  1. Read the specification (prompt.md) thoroughly — every rule, every example, every clarifying question (❓)
  2. Turn each example into at least one it.todo() test case
  3. Order tests from simplest to most complex
  4. Use it.todo() only — NO executable tests yet

Context: $ARGUMENTS

Process

Step 1: Understand the Feature

Read the complete specification. Pay special attention to integration examples and clarifying questions (marked with ❓) — these disambiguate rules that may seem open to interpretation in isolation.

  • What are all the operations the system must support?
  • What rules govern each operation?
  • Which examples in the spec illustrate these rules?

Step 2: Identify Test Cases from the Spec

Walk through the specification section by section. For each rule and each example:

  • Create a test case that verifies the described behavior
  • Include the expected values from the spec in the test description
  • If a clarifying question (❓) resolves an ambiguity, create a test for the clarified interpretation
  • If the spec uses an example-mapping format (rules, examples, questions), every listed example must have a corresponding test

Step 3: Order Tests (Simple → Complex)

Arrange tests in increasing complexity:

  1. Simplest case (often empty/zero/single item)
  2. Individual rules in isolation
  3. Rules with modifiers
  4. Combinations of multiple rules
  5. Multi-step scenarios (e.g., operations that reference earlier results)

Step 4: Write Test File

Create the test file with it.todo() entries:

import { describe, it, expect } from "vitest";
import { functionName } from "./implementation.js";

describe("Feature Name", () => {
  it.todo("should [behavior] — [expected value from spec]");
  it.todo("should [next behavior] — [expected value from spec]");
  // ... ordered simple → complex, covering ALL spec examples
});

Read the full file on GitHub · 106 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.

  1. 3d ago First seen · 106 lines · 0 tokens per session scan A 8a886725ca25

Subscribe to this mod's changes

test-list is a command published in the GitHub repository marcoemrich/EXACT-Coding-Exercises (13 stars, last pushed 14d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 862 tokens. 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.