red

A guide for the Red phase of test-driven development (TDD), where you activate exactly one test and confirm that it fails for the expected reason. Other planned tests remain inactive until their turn.

In plain words
What is it for?
Use it to select one test, predict compilation and runtime failures, activate it, and verify the failure without writing implementation code.
Why use it?
It makes the behavior being added explicit before implementation begins. This helps catch tests that fail for the wrong reason and keeps development changes small.

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/agentic_coding_lab/red
Clone the repo
git clone --depth 1 https://github.com/marcoemrich/agentic_coding_lab

Made for: Claude Code.

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 790 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 $0.00790
Opus 5 $0.00000 $0.00395
Sonnet 5 $0.00000 $0.00158
Haiku 4.5 $0.00000 $0.00079

Measured 2d ago against content hash 347f6390b290, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

red 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/2026-05-03_04-15-52_mars-rover-prose_v5-exact-single-context_haiku-4-5/.claude/commands/red.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TDD Red Phase

You are now in the Red Phase of TDD. Follow these instructions to activate ONE test and make it fail.

Your Mission

  1. Activate exactly ONE test from the test list
  2. Make explicit predictions about how it will fail
  3. Verify the test fails for the right reason
  4. Maintain strict discipline - NO implementation during Red phase

Context: $ARGUMENTS

Red Phase Rules

  • One test at a time: Convert exactly ONE it.todo() to executable test
  • All other tests remain as it.todo(): Never have more than one failing test
  • Two-stage failure: First compilation error, then runtime/assertion error
  • Make predictions: Explicitly state expected failures before running tests
  • No implementation: Don't write code to make test pass yet

Process

Step 1: Activate One Test

Identify the next it.todo() and convert it to executable test code:

// Convert from:
it.todo("should return 0 for empty input");

// To:
it("should return 0 for empty input", () => {
  expect(calculate("")).toBe(0);
});

Leave all other tests as it.todo().

Step 2: Predict Compilation Error

Before running the test, state your prediction:

🔴 Red Phase - Compilation Error Prediction:
- Test: "should return 0 for empty input"
- Expected: Compilation error
- Reason: Function `calculate` doesn't exist yet
- Error: "Cannot find name 'calculate'"

Step 3: Run Test - Verify Compilation Error

Run pnpm test:unit:basic and verify:

  • ✅ Compilation error as predicted, OR
  • ❌ Prediction wrong → STOP and explain discrepancy

Step 4: Create Empty Function

Create minimal function stub (no logic):

export const calculate = (input: string): number => {
  return undefined as unknown as number; // Intentionally wrong
};

Step 5: Predict Runtime Error

Before running again, state your prediction:

🔴 Red Phase - Runtime Error Prediction:
- Test: "should return 0 for empty input"
- Expected: Runtime assertion error
- Expected value: 0
- Actual value: undefined
- Diff:
  Expected: 0
  Received: undefined

Read the full file on GitHub · 135 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 · 135 lines · 0 tokens per session scan A 347f6390b290

Subscribe to this mod's changes

red is a command published in the GitHub repository marcoemrich/agentic_coding_lab (11 stars, last pushed 15d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 790 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.