tdd-execute-codex

A test-driven development workflow in which Claude writes the tests, Codex or Claude implements the code, and Claude performs the final review. TDD means writing and checking expected behaviour before implementation.

In plain words
What is it for?
Use it to execute a written development plan, create tests first, route implementation work, validate each phase, and complete a final review.
Why use it?
It separates test ownership, implementation, and approval so changes are checked before delivery and the final decision remains with Claude.

Command

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/ching-kuo/claude-codex/tdd-execute-codex
Clone the repo
git clone --depth 1 https://github.com/ching-kuo/claude-codex
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,521 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 $0.00016 $0.03521
Opus 5 $0.00008 $0.01760
Sonnet 5 $0.00003 $0.00704
Haiku 4.5 $0.00002 $0.00352

Measured 2d ago against content hash 7360fec024e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tdd-execute-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 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.

commands/tdd-execute-codex.md · 265 lines

How it starts

The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deprecated: This command has been converted to a skill (/tdd-execute-codex). The skill version is recommended for new usage and supports eval-based testing. This command is retained for backward compatibility (model pinning, tool restrictions).

TDD-Execute-Codex — Tests First, Smart Routing, Claude Reviews

$ARGUMENTS


Core Protocols

  • TDD Mandate: Tests must be written and verified RED before any implementation begins
  • Code Sovereignty: Claude is the final authority — review and approve all changes before delivery
  • Stop-Loss: Do not proceed to next phase until current phase output is validated
  • Language: Use English when calling tools/models; communicate with user in their language
  • Test Ownership: Claude owns all test files. Codex never modifies test files.
  • 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 command. Do not proceed with a dirty worktree.

Read the full file on GitHub · 265 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 · 265 lines · 16 tokens per session scan A 7360fec024e2

Subscribe to this mod's changes

tdd-execute-codex is a command published in the GitHub repository ching-kuo/claude-codex (23 stars, last pushed 5mo ago), licensed MIT. It adds 16 tokens to every session and 3,521 once invoked, about $0.0001 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.