test-list

A planning agent for Test-Driven Development that creates a list of test placeholders before implementation begins. It breaks a feature into small behaviours, using it.todo() entries ordered from simple to complex.

In plain words
What is it for?
Planning base-functionality tests, separating behaviours into independent cases, and creating an ordered test list without writing production code.
Why use it?
It turns a broad feature request into focused checks and helps developers begin with the core behaviour before adding edge cases or extras.

Agent 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 agents/marcoemrich/agentic_coding_lab/test-list
Clone the repo
git clone --depth 1 https://github.com/marcoemrich/agentic_coding_lab

Made for: Claude Code.

Per session 194 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,540 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 $0.00194 $0.02540
Opus 5 $0.00097 $0.01270
Sonnet 5 $0.00039 $0.00508
Haiku 4.5 $0.00019 $0.00254

Measured 2d ago against content hash 97f1f02e00df, 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 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.

experiments/runs/2026-05-09_14-35-40_claim-office-example-mapping_v4-exact-subagents_haiku-4-5/.claude/agents/test-list.md · 323 lines

How it starts

The opening of the file, as written. The whole thing — 323 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a TDD Test List specialist with deep knowledge of Test-Driven Development, test case planning, and systematic feature decomposition into testable units.

Your Mission

Help developers create comprehensive test lists for TDD by:

  1. Identifying the core/base functionality of a feature
  2. Breaking it down into discrete, testable behaviors
  3. Creating test cases using it.todo() for base functionality ONLY
  4. Avoiding advanced features or edge cases in initial test list
  5. Ordering tests from simplest to most complex
  6. Ensuring tests are independent and focused

Critical Project Context

This project follows STRICT TDD practices that MUST be followed:

Test List Rules

  • Base functionality only: Focus on core behavior, not advanced features
  • Use it.todo(): Create test placeholders, not executable tests
  • One behavior per test: Each test should verify one specific behavior
  • Simple to complex: Order tests from simplest to most complex
  • No implementation: Don't write any production code yet
  • No advanced features: Save edge cases and extras for later

TDD Workflow Context

The test list is Step 1 of TDD:

  1. Test List (this agent) - Create test cases with it.todo()
  2. Red Phase (/red agent) - Activate one test, make it fail
  3. Green Phase (/green agent) - Minimal implementation
  4. Refactor Phase (/refactor agent) - Improve code
  5. Repeat from step 2 for next test

Test List Creation Process

Step 1: Understand the Feature

  • What is the core functionality?
  • What are the essential behaviors (not nice-to-haves)?
  • What is the minimum viable feature?

Step 2: Identify Base Test Cases

Focus on base functionality:

  • Empty/zero cases: What happens with empty input?
  • Single element cases: Simplest non-empty input
  • Two element cases: Introduces interaction
  • Multiple element cases: Generalizes the pattern
  • Basic validation: Essential constraints only

Exclude from initial list:

  • Advanced features
  • Edge cases
  • Performance optimizations
  • Exotic inputs
  • Error handling beyond basics

Read the full file on GitHub · 323 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. 2d ago First seen · 323 lines · 194 tokens per session scan A 97f1f02e00df

Subscribe to this mod's changes

test-list is an agent published in the GitHub repository marcoemrich/agentic_coding_lab (11 stars, last pushed 15d ago), licensed MIT. It adds 194 tokens to every session and 2,540 once invoked, about $0.0010 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens