codex plugins

by Qi-Xuan Lu

A living knowledge base your agents build as they work. What they learn becomes source-cited wiki pages that refresh between sessions, so each new thread starts from your latest work.

by Bernhard Goetzendorfer

Loop engineering for AI coding agents — turn ad-hoc sessions into a repeatable research → plan → wave-execute → close loop with verification gates. Runs on Claude Code, Codex CLI, Cursor, and Pi.

by Plastic Labs

Persistent, cross-session memory for OpenAI Codex, powered by Honcho from Plastic Labs. Lifecycle hooks capture each session and inject the relevant context back at session start, so Codex remembers your preferences, projects, and decisions across restarts and context resets.

by Seyed Yahya Shirazi

Publication-quality figures plugin. Eight skills + one QA agent. figure-bible: scaffolds and validates the per-project theme.json (palette, typography, text limits, Codex model settings) that every other skill reads. ai-full-figure: gpt-image-2 through the Codex CLI (or the OpenAI Images API) renders single panels or whole multi-panel figures with large verbatim titles and panel letters, panels generated in parallel with reference-image consistency, composed at journal width; a text ladder routes dense labels to the SVG overlay and numerals to plot or vector skills. transparent-icons: flat scientific icons with native alpha through the same shared backend, with an explicit Atlas Cloud path. scientific-figure: svgutils composer with pre-export font-size validation and Inkscape/cairosvg export. svg-primitives: mm-precise SVG builder with auto-fit text, edge-snapped arrows, and layer ordering; svg-figure: hand-authoring conventions and editor handoff. plot-styling: library decision tree with SciencePlots recipes. figure-qa agent: type-dispatching QA with OCR of expected strings, palette compliance against the theme, geometry and font checks, a VLM rubric, and a JSON verdict that drives the generate, QA, fix loop.

by Soein

Multi-CLI swarm in tmux. discuss (roundtable with Codex/Claude/Gemini) + vote (LLM-first consensus with multi-round debate, file injection, auto-promote) + execute (15-role supervisor dispatch). Participants use real CLI tools across all modes.

by o11y.dev

Expert OpenTelemetry guidance for collector configuration, pipeline design, production telemetry instrumentation, and deployment architecture across Kubernetes, ECS, serverless, and standalone environments.

by Patrice Huetz

Drive Code Buddy, the multi-provider AI coding agent (64 providers, local Ollama at $0), from Claude Code: the skill teaches headless one-shot runs, provider/model pinning, permission modes and the verify loop; the MCP server exposes Code Buddy's read-only tools. Requires `npm i -g @phuetz/code-buddy`.

by Martin Richards

Personal development toolkit - spec-driven development, code quality, deep thinking, and ecosystem patterns

by xiaolai

One plugin to bridge and delegate across Claude Code, Codex CLI, and Antigravity CLI (agy) — single-source AGENTS.md, shared skills, mirrored hooks and MCP servers, and bidirectional delegation — plus Grok delegation and bounded Qwen review.

by Vanyangyang

Persistent Grok Build Leader/ACP supervision with verified local-proxy initialization and visible Windows Terminal TUI control.

by Alican Kiraz

Stage-aware security guidance for planning, risky implementation changes, review, and release checkpoints.

by AgentParty

Connect coding agents and humans through durable AgentParty channels, with safe launch guidance for Claude Cross-session coordination.

by Maksim Kochetkov

Codex-native workflows for agents, conventions, project rules, reviews, and teams.

by Maksim Kochetkov

Codex-native workflows for agents, conventions, project rules, reviews, and teams.

by Maksim Kochetkov

Codex-native documentation synchronization and Markdown-to-PDF workflows.

by Maksim Kochetkov

Codex-native documentation synchronization and Markdown-to-PDF workflows.

by Maksim Kochetkov

Codex-native text utilities plus user-invoked Manager, task-board, and terse-hook workflows.

by Maksim Kochetkov

Codex-native text utilities plus user-invoked Manager, task-board, and terse-hook workflows.

by VincentChuWaiChow

Cross-platform agent templates for a curated cloud and zero-trust AI workflow marketplace, with explicit portability boundaries across major coding-agent platforms.

by VincentChuWaiChow

Curated marketplace for cloud and zero-trust AI workflows. 331 agents, 286 skills, and rules across AWS, Azure, OCI, GCP, Alibaba Cloud, Huawei Cloud, Kubernetes, and Terraform.

by Alberto Leal

Install and maintain a "model routing" section in a project's CLAUDE.md that teaches Claude Code which model to use for which work, including delegating to GPT models via the Codex CLI. Use when adding model-picking guidance to CLAUDE.md, setting up Codex/GPT as a delegation target or fallback, or routing subagent and workflow tasks across models by cost, intelligence, and taste.

by Gopher Guides

Multi-LLM integration for second opinions and task delegation

by OthmanAdi

Build generative UI with OpenUI — any LLM provider, any backend language. Scaffold, integrate, validate.

by ulises-jeremias

18 AI agent personas: 11 holistic (planner, architect, designer, implementer, reviewer, qa-engineer, security-engineer, platform-engineer, researcher, data-engineer) + orchestrator (assistant, client-workflow-bootstrap) + 5 specialists (code-reviewer, agentic-security-reviewer, security-reviewer, e2e-runner, tdd-guide, build-error-resolver) — 7 specialists archived to references in #865 (typescript/database/performance/refactor → reviewer/references/*; docs/reference-lookup → researcher/references/LOOKUP_GUIDE.md; tech-assistant → platform-engineer/references/WORKSTATION_OPS.md) — see docs/AGENT_TAXONOMY.md §8.