superspecs: Skill for Claude Code

.skills/execute-tdd/SKILL.md

execute-tdd is a skill for Claude Code, Codex from fokkerone/superspecs. It costs 68 tokens per session (1,107 once invoked), scanned A, original, MIT.

A test-first development workflow called TDD, or test-driven development. It requires writing a failing test, making it pass, and then improving the code.

In plain words
What is it for?
Reading a task’s test requirement, creating and running its test first, then implementing and refining the change.
Why use it?
It prevents implementation from getting ahead of clear, runnable checks for the required behaviour.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

This is fokkerone/superspecs's own configuration. It tells Claude Code and Codex how to work on superspecs itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything superspecs configures →

Reuse

Borrowing it

Nothing to install: this file belongs to fokkerone/superspecs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/fokkerone/superspecs/main/.skills/execute-tdd/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/fokkerone/superspecs

Made for: Claude Code, Codex.

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 execute-tdd

README.md
[![agentmods](https://agentmods.dev/badge/skills/fokkerone/superspecs/execute-tdd.svg)](https://agentmods.dev/skills/fokkerone/superspecs/execute-tdd)
Your own site
<a href="https://agentmods.dev/skills/fokkerone/superspecs/execute-tdd"><img src="https://agentmods.dev/badge/skills/fokkerone/superspecs/execute-tdd.svg" alt="Measured on agentmods" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,107 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 5.1 $0.00068 $0.01107
Opus 5 $0.00034 $0.00553
Sonnet 5 $0.00014 $0.00221
Haiku 4.5 $0.00007 $0.00111

Measured 6d ago against content hash d4214fe246bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

execute-tdd 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 6d 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/execute-tdd/SKILL.md · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: execute-tdd

You are enforcing test-driven development. This skill runs inside every subagent task — it is not a separate phase that happens after subagent development. Every implementation task, in every wave, follows this cycle.

If you are implementing code outside of subagent mode (e.g., a quick fix or a standalone task), this skill applies exactly the same way.

The Law

RED → GREEN → REFACTOR

This is not a suggestion. It is the only permitted order of operations.

Code written before a failing test exists gets deleted.

Steps

RED Phase

1. Read the task's test requirement

Every task in tasks.md has a Test requirement: field. Read it before touching any implementation file.

2. Write the test

Write a test that:

  • Tests the behavior described in the task (not implementation details)
  • Is specific enough to fail for the right reason
  • Uses the same test framework as the rest of the project (detect from existing test files)

The test should read like documentation: given this setup, when I do this, I expect this outcome.

3. Run the test — confirm RED
# Run ONLY the new test (not the full suite)
<test-runner> <test-file> -t "<test-name>"

Expected: FAIL

Check the failure reason:

  • ✅ Right reason: the feature doesn't exist yet → proceed
  • ❌ Wrong reason: import error, syntax error, test setup problem → fix the test, not the implementation
  • ❌ Passes immediately: the test is wrong — it's not testing anything new → rewrite it

Do not proceed to GREEN until the test fails for the right reason.

GREEN Phase

4. Write the minimum implementation

Write the smallest amount of code that makes the test pass. That's it.

Rules:

  • No code that isn't needed for this test
  • No "I'll need this later" additions (YAGNI)
  • No refactoring yet (that's REFACTOR phase)
  • No changing the test to make it pass easier
5. Run the test — confirm GREEN
<test-runner> <test-file> -t "<test-name>"

Read the full file on GitHub · 171 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. 6d ago First seen · 171 lines · 68 tokens per session scan A d4214fe246bf

Subscribe to this mod's changes

execute-tdd is a skill published in the GitHub repository fokkerone/superspecs (4 stars, last pushed 2mo ago), licensed MIT. It adds 68 tokens to every session and 1,107 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.