Claude Code plugins
8 plugins from public Claude Code marketplaces. Each one bundles skills, slash commands, agents, hooks or MCP servers that install together.
Showing 8 plugins that match these filters. Clear filters
8 plugins from public Claude Code marketplaces. Each one bundles skills, slash commands, agents, hooks or MCP servers that install together.
Showing 8 plugins that match these filters. Clear filters
Submit the repo with .claude-plugin/marketplace.json and we list every plugin.
Submit marketplaceMulti-agent collaboration — spawn N parallel subagents that compete on code optimization, content drafts, research approaches, or any task that benefits from diverse solutions. 7 slash commands (/hub-init, /agenthub:spawn, /hub-status, /agenthub:eval, /agenthub:merge, /agenthub:board, /hub-run), agent templates, DAG-based orchestration, LLM judge mode, message board coordination.
Structured experiment-driven code optimization using tree search and parallel subagents
Complete system: 15 problem-shaped skills backed by 97 genius agents, 86 skills total, 30 commands, 71 tools, 36 hooks, authoritative coding-standards rules, goal-driven and autonomous build loops, and the shared Claude Code and Codex gates
Asks before Claude Code changes, moves or deletes a file that existed when the session started, and can enforce limits on subagents. Silent otherwise, so your own permission settings keep working.
88 curated skills (incl. workspace-mode for cross-repo flows), 30 composite slash commands, 14 specialist subagents with per-agent model + reasoning-effort tuning, and 10 hook scripts that quietly enforce discipline (confirm-to-commit on protected branches, destructive-git gating, no AI-attribution trailers in commits/PRs, dependency pre-flight, iron rules injected at session start). Covers the whole SDLC — including post-PR: CI diagnosis, releases, dependency audits, live incident response. Drives the senior-IC loop end-to-end via /orc:flow — workspace-aware: from a parent dir with multiple sibling repos, one flow spans them all with N linked PRs.
Seven tiered subagents, orchestration rules for the main session, and a read-budget hook
developmentResearch software engineering practice: 67 skills, fourteen workflow commands and six subagents for research code.
A QA test-session engine: a manager plus the qa-analyst/qa-manual/qa-automator subagents, a session file scheme, reports and a mandatory retro. One flow for many projects — everything project-specific (tracker, test management, environments, autotests) lives in the project's own profile.
testing