13509 plugins available.
by Hermes Labs
A guided, project-local first experience for Claude Code that helps beginners start making something real.
by David Kooi
Skills from agent-ops-patterns: hand your agent a source (a course, a paper set) and get a disposition record with a quoted file:line or a scoped command with its exit code and output per verdict. First skill: Stanford CS329A "Self-Improving AI Agents".
by henemm
8-Phase Workflow Engine with TDD Enforcement for Claude Code
by Chandan Singh
tqdm-style progress bars in the Claude Code statusline for any long-running job. Long commands are tracked automatically; Claude picks how to observe each one, and the ETA corrects itself from what is observed.
by Filippo Merante Caparrotta
Drops `name` from Agent tool calls so the subagent reports back on its own: a named agent becomes a mailbox teammate that notifies idle without a report body, leaving fan-out skills (code-review, research, printing-press) chasing the report with SendMessage. Opt out per call with `[mailbox]` in the description, or session-wide with ALLOW_NAMED_AGENTS=1.
by Pavel Guzenfeld
Skills, slash commands, rules and a diff-scoped mutation gate for a ticket-to-PR software development lifecycle.
by cjthompson
End-to-end Agent Teams orchestration for cross-cutting work requiring inter-agent communication and worktree isolation.
by Jared Wray
Operation manuals as Agent Skills for shipping, hardening, releasing, and reviewing OSS software — engineering disciplines plus one-PR-at-a-time release, security, and ops workflows.
by Antonio Antenore
A Codex plugin for contract-driven delivery, verified assessments, and visual project lineage.
by wrzonance
Board-aware parallel issue and PR review skills, with lifecycle hooks and a per-repository contract.
Throwaway rig that measures what a hook can tell the model, and whether a worker is distinguishable. Not for general use.
by Edge City
Edge Esmeralda 2026 — popup knowledge, EdgeOS calendar & directory, Geo knowledge graph access, and Index Network discovery.
by Sebastien Rousseau
The universal agent skills registry — polyglot engineering skills and system prompts, symlinked or installed into consumer repos.
by sumik5
AI/LLM/エージェント開発スキル群を提供するプラグイン。6個のスキル（GenAIデザインパターン・AIエージェント構築・Web AI統合・promptfoo評価/レッドチーミング・AI支援開発方法論・AI開発セキュリティ戦略）を含む。
by d-morrison
Morrison-Lab AI agent skills, rules, commands, and lifecycle hooks for Codex.
Hooks-only skills-directory plugin: registers hooks/hooks.json in sessions that open the ai-config checkout itself, where the marketplace plugin is not installed (ai-config#2004).
by luisander2651
Flujo de desarrollo guiado por especificaciones (AI-Driven Development): init, specify, plan, tasks, implement, review y release, con constitución, trazabilidad y puertas de aprobación humana.
by Daniel Galvan
AI Engineering Workflow Framework for Codex
by ai-skills-hub
Italian Work Skills Hub for codex (254 originals + 24 pinned third-party).
by Josh / Arcane Ops
Parallel Agent Orchestration - The A(i)-Team transforms PRDs into working, tested code
Optional post-install Agent plugin manager for Copilot customizations from teggr/ai-toolkit, focused on inventory, updates, and reconciliation.
by Jake Bowers
Jake Bowers's research skills for Claude Code: math, citation verification, referee reports, review responses, decks, style audits, first-reader passes, and simulation studies.
The same rules translated for the Claude app, which has no CLAUDE.md and no working tree: drafting rules with worked examples, coding rules, the style audit, mathematical work in voice mode, and the handoff into Claude Code.