Codex Workflows — Development skill for Claude Code
Development workflows for Codex that keep technical rigor and edge-case handling from becoming product overengineering.
How to install Codex Workflows
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open shinpr/codex-workflows and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Codex Workflows does
Development workflows for Codex that keep technical rigor and edge-case handling from becoming product overengineering.
Alternatives in Development
- Claude Scholar — Semi-automated research assistant for academic research and software development 3k ★
- /prioritize — Prioritize initiatives with context-aware financial and strategic rigor 2.3k ★
- SOUL — You're not a chatbot 1.3k ★
README
codex-workflows
[](https://developers.openai.com/codex/cli) [](https://developers.openai.com/codex/skills/) [](https://opensource.org/licenses/MIT)
**English** | [简体中文](README.zh-CN.md) | [日本語](README.ja.md) | [Español](README.es.md) | [한국어](README.ko.md) | [Português (Brasil)](README.pt-BR.md)
On larger product work, Codex can pursue technical consistency beyond what the user needs. Handling every edge case and making each path deterministic can alter what users see even when the approved outcome does not require it.
codex-workflows keeps that work within the smallest approved outcome. It confirms which user-visible behavior may change, records what must not, and requires evidence before completion. Within those boundaries, Codex chooses reversible implementation details from the repository.
The workflows are installed as Agent Skills and custom agents for [OpenAI Codex CLI](https://developers.openai.com/codex/cli). The main Codex session checks scope and rough cost before design, owns progress and review decisions, and carries approved work through implementation and independent verification.
Why not use Codex directly?
Direct Codex is the better fit for a well-scoped fix, disposable experiment, or one-shot script. It is faster and cheaper when the intended outcome and safe implementation boundary are already clear.
Use codex-workflows when technical choices can change the product scope, user-visible behavior, or a decision that needs to survive across contexts.
For example, a request to extend an existing authentication path can lead to a technically cleaner second mechanism, broader validation, and a new response contract. The frontend may adapt and the tests may pass, while users receive behavior that was never part of the approve
Related Skills
Coding Skill
Portable TDD-first coding-agent skill for Codex and Claude Code: clarify behavior first, write RED tests, impl
Animus Sprint Loops
A lightweight, platform agnostic protocol for autonomous development and objective handling (repo acts as a Cl
Review Coderabbit
Fetch CodeRabbit review comments and process them with technical rigor - verify before implementing, push back
Claude Voice System
Add self-learning voice notifications for Claude Code with edge-tts, phrase pools, priority queues, and anti-r
Ctx Core
Obsidian-backed PRDs for unsettled product decisions and Lean execution for settled technical work—across Clau
Edge
Walk a deliverable through the Playbook §2 edge-case checklist and scaffold the tests that genuinely apply.
Related Agents
Hatch3r Edge Case Analyst
Domain edge-case + error-handling correctness specialist — enumerates functional edge cases across multi-entit
QA Specialist
Reviews test coverage, edge case handling, reliability, and verification strategy. Activate for any code chang
Dev Dev Delta
Hardening and resilience specialist. Use AFTER features are implemented to add error handling, retry logic, ed