Codex Lattice: installable Codex skills, hooks, custom agents, MCP search, and docs-first workflow harness.
Skill Claude CodeCodex
Agent and tool security review workflow. Use when adding or changing MCP servers, Codex plugins, hooks, sub-agents, tool permissions, prompt flows, automation loops, or model-visible logs.
Skill Claude CodeCodex
A guide to designing REST and GraphQL APIs, which are interfaces that let software exchange data and actions. It covers resources, HTTP methods, schemas, naming, versioning, and API documentation.
Skill Claude CodeCodex
A guide to Python’s asyncio and async/await tools for running waiting-heavy work without blocking the program. It covers coroutines, tasks, event loops, and concurrent input/output operations.
Skill Claude CodeCodex
A parallel version of an autonomous development loop that gives independent PRD or checklist items to separate coding agents. Each agent works in an isolated worktree, which is a separate working copy of the repository.
Skill Claude CodeCodex
An autonomous development loop for working through a product requirements document, or PRD, one checklist item at a time. It records progress, verification results, and possible commits while using Codex goals to track when the work is complete.
Skill Claude CodeCodex
A step-by-step workflow for diagnosing and fixing TypeScript and build errors. TypeScript is a programming language and type checker commonly used in JavaScript projects.
Skill Claude CodeCodex
An image-generation skill for the OpenAI Codex command-line tool. It can create one image or up to five images at the same time using Codex’s built-in image tool.
Skill Claude CodeCodex
A workflow for committing Git changes, pushing a branch to a remote repository, and opening a pull request. A pull request is a proposed change that others can review before it is merged.
Skill Claude CodeCodex
A guide for managing the conversation context—the information available to the coding agent—and reducing its token use. It explains when to compact, hand off, or clear a session.
Skill Claude CodeCodex
Data governance workflow. Use when handling PII, privacy, retention, data classification, access control, audit logs, schema ownership, data migrations, analytics events, or compliance-sensitive changes.
Skill Claude CodeCodex
A guide for using agent-browser, a command-line tool that controls a headless web browser without opening a visible window. It uses page snapshots to find buttons, links, fields, and other elements for interaction.
Skill Claude CodeCodex
A process for testing a finished feature through a real browser from the user's point of view. E2E means end-to-end: checking the complete flow rather than only individual functions.
Skill Claude CodeCodex
A code-output evaluator that scores a result across function, quality, originality, and security, using a separate evaluator agent.
Skill Claude CodeCodex
A guide for creating Python web APIs with FastAPI, including project structure, asynchronous code, dependency injection, error handling, and testing. An API lets software exchange data over the web.
Skill Claude CodeCodex
Azure FinOps and resource review workflow. Use when Azure resources, infrastructure specs, cost estimates, budgets, quotas, scaling, monitoring, or cloud operations are involved. Defaults to read-only Azure CLI discovery.
Skill Claude CodeCodex
A workflow for planning and building frontend interfaces—the visible parts of websites and applications—using defined visual styles, components, layouts, and responsive behavior.
Skill Claude CodeCodex
A short HANDOFF.md document that records a coding session's status so another session can continue the work. It notes completed and unfinished tasks, next steps, warnings, related files, and the last development state.
Skill Claude CodeCodex
A diagnostic workflow that checks the health of a coding-agent setup, including its instructions, skills, helper agents, automatic hooks, rules, tool connections, evaluation checks, and multi-agent coordination.
Skill Claude CodeCodex
A read-only diagnostic skill for checking an agent workspace against 12 principles for a well-organised, verifiable development setup.
Skill Claude CodeCodex
Production incident and major-error response workflow. Use for outages, degraded service, repeated hook/tool failures, security incidents, data loss, rollback decisions, on-call triage, or when MAJORERRORS.md shows blocking failures.
Skill Claude CodeCodex
Build, configure, and troubleshoot Microsoft Agent Framework (agent-framework repo) in Python, including ChatAgent setup, OpenAI/Azure clients, tool/function calling, multi-agent workflows, and environment setup. Use when requests mention Agent Framework, ChatAgent, OpenAIChatClient, AzureOpenAIResponsesClient…
Skill Claude CodeCodex
REQUIRED for all image generation requests. Generate and edit images using Gemini CLI with image models. Handles blog featured images, YouTube thumbnails, icons, diagrams, patterns, illustrations, photos, visual assets, graphics, artwork, pictures. Use this skill whenever the user asks to create, generate, make, draw…
Skill Claude CodeCodex
Observability and SLO design workflow. Use when adding or reviewing logs, metrics, traces, dashboards, alerts, SLIs, SLOs, error budgets, runbooks, or production monitoring for a service or feature.
Skill Claude CodeCodex
Create backend/frontend layered .md memory during Plan mode. Use when request includes requirements capture, memory bootstrap, or plan preparation with backend/frontend separation.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: