A catalog of ChatGPT & Codex plugins, sorted by people.
We list 34 plugins written mostly in Shell, about 10% of our 346-plugin catalog. They're ordered by editor's picks, then GitHub stars (checked 2026-10-27). The median one has 10 stars, and 22 of them got a push in the last 30 days.
Most-starred: Agent Guard, Claude Octopus, Sno Station Skills. Biggest shelves here: Miscellany (8), Agent Workflows (6), Docs, Content & SEO (6).
The language is what GitHub detects as the repo's main one, so a plugin can still ship scripts in other languages.
Stars measure popularity, not quality or safety. Descriptions are each project's own. Read the code before you install anything.
Other languages: Python (99) · JavaScript (90) · TypeScript (31) · Go (10) · Rust (9) · HTML (8) · PowerShell (3)
Local-by-default, no-telemetry hooks block or mask secret leaks in Claude Code and Codex, with opt-in PII filtering and Git/CI backstops.
★ 35 · by JeongJaeSoon#2Multi-LLM orchestration dispatching to 8 providers (Codex, Gemini, Copilot, Qwen, Perplexity, OpenRouter, Ollama, OpenCode) with Double Diamond workflows, adversarial review, and safety gates.
★ 4,314 · by nyldn#3Peer review, delegation, handoff and self-improvement skills that give Codex and Claude Code the working habits of a real team.
★ 883 · by sno-ai#4Russian text quality for AI agents — 2,000+ linguistic atoms for typography, information style, editorial standards, UX writing, business correspondence and AI-text cleanup, with a 0–10 text score.
★ 280 · by talkstream#5Live B2B company and contact intelligence for building lead lists, researching prospects, enriching contacts, and personalizing outreach.
★ 265 · by explorium-ai#6Goal-based planning and proof gate for Codex and Claude Code that turns requests into ownership, cutover, review-gate, and acceptance-evidence plans.
★ 132 · by jturntdev#7Places real outbound phone calls to US businesses (bookings, inquiries, quotes) through the PlaceCall API and returns the outcome and transcript.
★ 107 · by voygr-tech#8Accountable, time-bounded Codex shifts with a persistent punch list, parked decisions, and reviewable run history.
★ 78 · by orwa-mahmoud#9Lightweight documentation memory for AI coding agents that scaffolds a 7-category docs tree, runs readiness checks, validates docs before finishing, and keeps a monthly changelog across Claude Code and Codex.
★ 44 · by MedAdemBHA#10Search, scrape, crawl, and map the web from Codex with Firecrawl CLI skills for live research and extraction.
★ 28 · by firecrawl#11Human-on-the-Loop AI coding workflow plugin for Codex, Claude Code, and Cline with structured planning, review, and verification guardrails.
★ 27 · by yimwoo#1213 skills for image, video, and audio generation using 100+ models - FLUX, Midjourney v7, Veo3, Kling 3.0, Suno, and HunyuanVideo via muapi.ai.
★ 25 · by SamurAIGPT#1321 development lifecycle skills and 20 review and debug agents for Codex, Claude Code, Cursor, and OpenCode, where every step writes its output to disk instead of leaving it in the chat.
★ 16 · by yagizdo#14Full data-product lifecycle on dbt for Entropy Data: scaffold, audit, and integrate projects with ODCS, ODPS, OpenLineage, and GitHub Actions.
★ 13 · by entropy-data#15Triage Rust ELF, Mach-O, and PE binaries, demangle symbols, recover likely crate namespaces, trace runtime and FFI paths, and optionally export pseudocode with headless Ghidra.
★ 12 · by jingjing2222#16Read-only meta-skill that scans your MCP servers, skills, plugins, and CLI tools, then suggests up to three ranked approaches (Methodical / Fast / Deep) with a copy-paste Quick Action table.
★ 12 · by dragon1086#17Claim and manage free subdomains under makes.fyi or agentdomains.co for the sites and APIs AI agents build.
★ 10 · by tashfeenahmed#18Six-stage SDLC in committed Markdown where hooks enforce the loop at the tool-call level: an artifact gate refuses source writes no approved plan covers and keeps a change declared low-risk away from sensitive paths, with 8 skills and 2 read-only subagents.
★ 10 · by ghiaog123#19Three-phase Requirements → Design → Tasks workflow for Claude Code and Codex — EARS notation acceptance criteria, autonomous execution loop, cross-spec dependencies, and post-implementation acceptance testing.
★ 10 · by Habib0x0#20Enforce formal, textbook-grade written register across all agent output.
★ 8 · by lulucatdev#21Remote MCP server connecting Codex, Claude Code, Cursor, ChatGPT and other MCP clients to 1,000+ apps and 400+ Skills through one reusable setup, with Vault-protected credentials and Audit logging. Website: https://aident.ai
★ 7 · by Aident-AI#22macOS-only local camera plugin for explicit snapshots, streaming controls, and file-backed image input.
★ 4 · by zfifteen#23Engineering discipline pack for Claude Code & Codex CLI with task-scope locking, anti-drift braking, condition-based codex review, project-CLAUDE.md pitfall writeback, and PreToolUse hooks that block irreversible bash patterns.
★ 3 · by biefan#24Runtime governance for Codex with policy enforcement on terminal commands, advisory checks for non-terminal tools via skills, PII/secret detection, and compliance-grade audit trails. Self-hosted via Docker.
★ 3 · by getaxonflow#25Durable memory and shared graph state for Codex and OpenClaw agents, with live ValkyrAI schema awareness.
★ 3 · by ValkyrLabs#26Send cold email from Codex: connect and warm up mailboxes, build and launch outbound sequences, and answer replies through the Sendsets MCP server.
★ 3 · by AddisonHoff#27Generate and edit AI images, video, audio, and 3D on the WaveSpeed platform with a bundled MCP server and CLI skill, including live catalog search, local-file upload, and price quotes before running.
★ 3 · by WaveSpeedAI#28Generate, maintain, compress, and audit standard AI-agent onboarding files with AGENTS.md, CLAUDE.md, drift tracking, and lifecycle hooks.
★ 2 · by gustavo-meilus#29Codex hooks that print one stretch or eye-break line and play a soft chime once the agent has kept you waiting for minutes, with zero model tokens and no telemetry (also Claude Code and Gemini CLI).
★ 2 · by Eliasjunit#30Remote MCP server and skill for AbuzzHive, public Q&A boards where AI agents look up errors other agents solved and help each other.
★ 1 · by kubec#31Search and fetch current web sources in Codex through the official Exa MCP server with browser OAuth.
★ 1 · by zlsbksdxl#32Converts Word, Excel, and PowerPoint to PDF, PDF to Word, extracts text, and merges, extracts, or renders PDFs through the locally installed Jetformat CLI.
★ 1 · by jetformat#33Prove suspected bugs with a red-green-red test loop: verify the cause, watch the test fail, apply the fix, and confirm the test fails again when the fix is reverted.
★ 0 · by RooAGI#34Research what goes viral, make finished short-form videos (voice, captions, music, AI footage) and post them to TikTok, YouTube, Instagram and X through Revid's hosted MCP server.
★ 0 · by tmakersasHow many Shell plugins are on PickAPlugin?
34 plugins in our catalog are written mostly in Shell, as of 2026-10-27.
What's the most popular Shell plugin for ChatGPT or Codex?
Our editor's pick Agent Guard by JeongJaeSoon is listed first; after picks, plugins are ordered by GitHub stars.
How is this list ranked?
Editor's picks first, then GitHub stars, with archived repos last. Paid placements don't change the order, and we haven't tested these plugins ourselves.
Why don't some languages have a page?
We only make a page when at least 3 plugins share it. Smaller groups are still in the main catalog.
A weekly-ish email with new and notable ChatGPT & Codex plugins. No spam. Unsubscribe anytime with one click.