Coding plugins

if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize with confidence.

60 skills · 2 agents

Bring Vercel ecosystem guidance into Codex with curated skills and the connected Vercel app. Packages the upstream vercel/vercel-plugin skills, agents, and commands under the local `vercel` plugin identity for the Codex plugin marketplace.

47 skills · 6 commands · 3 agents · app connector

Build and deploy web apps and agents

47 skills · 6 commands · 3 agents · app connector

TDD discipline for Codex: per-lane gates (unit/integration/e2e/contract), spec-strength levels S1-S6 with property tooling, adversarial spec review, red receipts, per-path critical thresholds, 9-format coverage merging and mutation testing, as 11 workflow skills ($tdd-guardian-init, -plan, -design-tests, -implement, -gate, -workflow, ...). A PreToolUse hook denies git commit/push until the gating lanes are fresh; Claude Code's TaskCompleted auto-gate has no Codex event, so $tdd-guardian-gate runs those lanes.

32 skills · 16 commands · 7 agents · hooks

Procedural knowledge that guides AI coding agents to the right Twilio APIs for any use case. Covers channel selection, production best practices, compliance requirements, and common pitfalls across Messaging, Voice, Verify, SendGrid, and 30+ products. Skills follow a progressive disclosure architecture — your agent sees lightweight metadata at startup and loads full guidance only when a task matches.

55 skills

Internal life-science research workflows that help Codex interpret a user's research question, normalize the relevant entities, choose the right skills, and synthesize evidence-backed answers across public resources. The plugin spans human genetics, functional genomics, expression, pathways, protein structure, chemistry, pharmacology, literature, clinical evidence, and public study discovery, with a research-router entrypoint for broad tasks and optional subagent-assisted parallel work when evidence lanes are independent.

50 skills

Self-contained Codex plugin for the HITL AI-Driven Development platform. Installs Codex project instructions, lifecycle hooks, git hooks, convention checks, templates, and optional Graphify support.

6 skills · 43 commands

SpecAI workflow: planning, TDD, debugging, and delivery workflows for coding agents.

35 skills · 12 commands · hooks

Documentation quality and freshness for Codex: $docs-guardian-audit checks staleness, accuracy, coverage and quality into one report with a fixing plan; $docs-guardian-coverage finds undocumented public APIs; $docs-guardian-generate writes missing docs in the project's framework format (Markdown, MkDocs, VitePress, Docusaurus, Sphinx). A PreToolUse hook warns on, or blocks, code-only commits.

35 skills · 5 commands · 5 agents · hooks

Shared engineering practices, principles, language standards, research, debugging, docs, operations and presentation.

43 skills

Natural-Language Programming reference knowledge as Codex skills — the 50 Rules, the 100-point scoring rubric, per-tool conventions (Claude Code / Codex CLI / Antigravity), anti-patterns, vocabulary discipline, and authoring guides. Knowledge skills, not commands: load $nlpm-rules + $nlpm-scoring to score an artifact, $nlpm-conventions-codex for the Codex skill layout. The interactive /nlpm:* linting commands remain a Claude Code plugin; cross-tool deterministic checks use the standalone bin/nlpm-check.

17 skills · 15 commands · 8 agents · hooks

Brainstorm, plan, debug, review, and compound learnings with AI agents

39 skills

Brainstorm, plan, debug, review, and compound learnings with AI agents

37 skills

Codex-native research workflow, cowork, memory, self-distillation, kit sync, and skill-entry aliases.

20 skills · 15 commands · hooks

Emmett Shaughnessy's personal Claude Code plugin — bundles self-routing agentic prompt engineering, cross-runtime subagent brief compilation, Claude Fable/Opus and GPT-5.6 Sol overlays, evidence receipts, loop escape, convergence recovery, progressive slicing, the broader coding and creative toolkit, and advisory guidance for optional MCP connections. No MCP servers are bundled.

33 skills · 1 command

Systematic software engineering pipeline — brainstorm, plan, TDD, quality gates, code review, and full orchestration from spec to PR.

32 skills

Android knowledge for Claude Code and Codex: a topic router, adversarial testing and error-handling skills, vendored official Android skills, 80/20 pattern detection, and five standalone agents for Kotlin/Compose/Gradle

19 skills · 5 agents · 1 MCP server · hooks

iOS knowledge for Claude Code and Codex: a topic router, TCA and SwiftUI skills, pattern detection, vendored community and Xcode skills, the Xcode MCP, and five agents for Swift/SwiftUI/Xcode

18 skills · 5 agents · 1 MCP server · hooks

Agentes generales (planner, architect, coder, tester, reviewer, documenter) e información compartida del proyecto. Recomendado instalar junto con los plugins de stack

8 skills · 9 commands · 6 agents · hooks

Evidence-first debugging for Codex.

21 skills · 2 agents

Infiquetra lifecycle spine with thin external-provider routes over the native Codex harness.

22 skills · hooks

Software developer agent and skills for any language: implementing and reviewing code, framework practices for ASP.NET Core and Spring Boot, implementing architecture designs, clean code, refactoring, testing, debugging, secure coding, APIs, production readiness, user interfaces, design patterns, algorithms, relational databases, pragmatic practices, commits and pull requests.

22 skills · 1 agent

Frozen legacy v1 workflow: roles, orchestration, design, planning, implementation, review and handoffs. Requires sunstack-dev. Do not edit without explicit owner instruction.

23 skills

Unofficial Avalonia 12 focused Codex plugin for building, reviewing, designing, porting, and migrating desktop applications through focused skills.

21 skills

Agentes y skills para NestJS, FastAPI, LangChain, LangGraph y LangSmith

9 skills · 3 commands · 7 agents · hooks

Linear-backed delivery from an idea to a reviewed PR.

17 skills · 3 agents

QA automation memory, test-case catalogs, Playwright skills, hooks, and MCP tools.

6 skills · 8 commands · 3 agents · 1 MCP server · hooks

A frontend assignment workflow kit for Toss Place style take-home assignments. It helps with planning feedback loops, product-focused assignment strategy, requirement analysis, assumptions, trade-offs, README rationale, stack selection, cache-efficient Next.js RSC architecture, Simple FSD, API design, component boundaries, React performance review, test quality review, parallel agent orchestration, review-fix loops, feature-sized commits, git delivery, reliability review, and final polish.

18 skills

Codex Chrome DevTools plugin with route sessions, upstream MCP delegation, live evidence bundles, API discovery, redacted cURL, performance workflows, and sync guardrails.

9 skills · 7 agents · hooks

Focused skills for product, engineering, design, and writing decisions.

16 skills