tdd-claude-codex

tdd-claude-codex is a skill for Claude Code, Codex from ching-kuo/claude-codex. It costs 89 tokens per session (3,123 once invoked), scanned A, original, MIT.

A test-driven development workflow in which tests are written before the code, then the implementation and tests are reviewed in stages. TDD is a way to use tests to define expected behavior before building a feature.

In plain words
What is it for?
Implement planned features with tests-first development, verify that tests fail before implementation, review the completed code, and refactor it afterward.
Why use it?
It adds separate checks for the tests and the final implementation, helping catch weak tests or code that only appears to work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; names the AskUserQuestion tool; mentions Codex.

Good fit Implement planned features with tests-first development, verify that tests fail before implementation…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ching-kuo/claude-codex/tdd-claude-codex
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 ching-kuo/claude-codex --skill tdd-claude-codex
Clone the repo
git clone --depth 1 https://github.com/ching-kuo/claude-codex

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 tdd-claude-codex

README.md
[![agentmods](https://agentmods.dev/badge/skills/ching-kuo/claude-codex/tdd-claude-codex.svg)](https://agentmods.dev/skills/ching-kuo/claude-codex/tdd-claude-codex)
Your own site
<a href="https://agentmods.dev/skills/ching-kuo/claude-codex/tdd-claude-codex"><img src="https://agentmods.dev/badge/skills/ching-kuo/claude-codex/tdd-claude-codex.svg" alt="Measured on agentmods" height="20"></a>
Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,123 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 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 $0.00089 $0.03123
Opus 5 $0.00044 $0.01562
Sonnet 5 $0.00018 $0.00625
Haiku 4.5 $0.00009 $0.00312

Measured 7d ago against content hash 4a593c8df004, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

tdd-claude-codex 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 7d 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/tdd-claude-codex/SKILL.md · 269 lines

How it starts

The opening of the file, as written. The whole thing — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TDD-Claude-Codex — Tests First, Claude Implements, Codex Reviews

Input

The user's message after the trigger is either:

  1. A file path to a plan (e.g. .claude/plan/feature.md) — read it and extract task description, implementation steps, key files
  2. A direct task description — use as-is

Confirm with user before proceeding if key context is missing.

Model Recommendation

Works with claude-sonnet-4-6 (default). Override with /model opus for tasks requiring deep architectural reasoning.

Tool Requirements

Advisory checklist — ensure these tools are available:

  • AskUserQuestion — confirm missing context
  • Task — dispatch tdd-guide and implementation subagents
  • Read, Glob, Grep — context retrieval
  • Write, Edit — write tests and implement
  • Bash — run tests/lint/git commands
  • mcp__codex__codex and mcp__codex__codex-reply — Codex test audit and implementation review

Core Protocols

  • TDD Mandate: Tests must be written and verified RED before any implementation begins
  • Sovereignty: Claude implements; Codex is the external reviewer — do not skip review
  • Stop-Loss: Do not proceed to the next phase until the current phase output is validated
  • Language: Use English when calling tools/models; communicate with user in their language
  • MCP for review: Always call Codex review via mcp__codex__codex. Do NOT use Bash codex review
  • Context Sanitization: Never pass .env, secrets, tokens, API keys, or credentials to any external agent or MCP. Exclude files matching .env*, *secret*, *credential*, *.pem, *.key. Redact inline secrets before sending.

Execution Workflow

Phase 0: Read Plan

  1. If argument is a file path, read it and extract: task description, implementation steps, key files
  2. If no plan file, use the argument as the task description directly
  3. Confirm with user before proceeding if key context is missing

Phase 1: Context Retrieval

  1. Read key files using Read, Glob, Grep (sanitize before passing to agents)
  2. Identify existing test framework, patterns, test file conventions, and configuration
  3. Establish test baseline:
    • Fast suite (<2 min): run the full suite, record pass/fail counts
    • Slow suite (>2 min) or partially failing: run only tests related to the task scope, record known failures
    • No test suite: skip — note "no baseline available", regression detection relies on new tests only
  4. Record $START_SHA via git rev-parse HEAD for diff scoping
  5. If worktree is dirty (uncommitted changes), stop and ask the user to commit or stash their changes before running this skill. Do not proceed with a dirty worktree.

Read the full file on GitHub · 269 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 7d ago First seen · 269 lines · 89 tokens per session scan A 4a593c8df004

Subscribe to this mod's changes

tdd-claude-codex is a skill published in the GitHub repository ching-kuo/claude-codex (23 stars, last pushed 5mo ago), licensed MIT. It adds 89 tokens to every session and 3,123 once invoked, about $0.0004 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.