By theocarranza
AI Codex workflow plugin: SessionStart Codex orientation injection, PreToolUse markdown allowlist, init skills (CLAUDE.md tree, Obsidian vault, .agent/rules starter set), and mining skills (canonical style notes, refactor catalog entries).
Given a commit hash, derive a before/after entry for the AI Codex Style Refactor Catalog with the principle applied. Use when the user wants to capture a notable refactor as a teaching example, or asks to "add this commit to the refactor catalog" / "log this refactor".
Drop a starter set of `.agent/rules/*.md` template files (strict-implementation-lock, rules-architect-protocol, rules-git-workflow, rules-date-time-handling) at the project root. Use when bootstrapping a project that has no `.agent/rules/` yet, or when the user asks to "scaffold the agent rules" / "drop starter rule templates".
Scaffold an AI Codex Obsidian vault skeleton (README, Knowledge/, Agent_Sessions/, Tickets/, Architecture/, Features/, Agent_Reports/, assets/). Use when a project adopting the codex workflow has no vault yet, or when the user asks to "create the codex vault" / "scaffold the agent knowledge vault".
Scaffold the CLAUDE.md tree (root + per-project) for a project adopting the AI Codex workflow. Use when bootstrapping a new repository, when an existing repo has no CLAUDE.md, or when the user asks to "set up the codex workspace" / "create CLAUDE.md files".
Mine an author's commits to draft a canonical-style-examples Knowledge note with file/line anchors and Agent Rules. Use when the user wants to capture their own (or a teammate's) idiomatic style in the AI Codex, or asks to "mine my commits for style examples" / "build a style guide from my authored code".
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A single-plugin Claude Code marketplace shipping codex-workflow — portable hooks (and, soon, skills + templates) for the AI Codex workflow that pairs a code monorepo with an Obsidian vault as the agent's canonical knowledge base.
Add this marketplace and install the plugin in any project:
/plugin marketplace add <github-owner>/codex-workflow-marketplace
/plugin install codex-workflow@codex-workflow-marketplace
See codex-workflow/README.md for what the plugin does and how to configure it.
Layout:
codex-workflow-marketplace/
├── .claude-plugin/
│ └── marketplace.json ← marketplace manifest
├── codex-workflow/ ← the plugin itself
│ └── ... ← see plugin README
└── README.md ← this file
The marketplace manifest declares exactly one plugin (codex-workflow) sourced from the sibling directory.
Plugin version is declared in codex-workflow/.claude-plugin/plugin.json and mirrored in the marketplace manifest's plugins[].version. Bump both when releasing.
npx claudepluginhub theocarranza/codex-workflow-marketplace --plugin codex-workflowStructured Agile/XP spike skill: frames, investigates, builds a functional archived prototype, publishes to GitHub, and produces an Azure DevOps Wiki findings document — all in compliance with the accepted definition of a spike.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
Claude harness - A harness for solo developers (Vibecoders) to handle full-cycle contract development.
Intelligent prompt optimization: injects the right context at the right moment so Claude lands a better first output. Clarifies vague prompts with research-based questions, plus targeted nudges for approach selection, plan readability, workflow routing, background execution, subagent routing, output readability, user-decision questions, and plan-mode assessment