301 plugins from public Claude Code marketplaces. Each one bundles skills, slash commands, agents, hooks or MCP servers that install together.
Showing 301 plugins that match these filters.
nuclear-gradeFlyFission/nuclear-grade-context-engineering1
appstore-precheckberkayturk/appstore-precheck1
token-leanhurttlocker/token-lean1
superbrainstormingharrymunro/superbrainstorming1Submit the repo with .claude-plugin/marketplace.json and we list every plugin.
Submit marketplaceFleet band for Claude Code: which AOS sessions work or need you, context weather, read-only go-gate panel
AOS sessions viewer for Claude Code: every session of every harness plus the ACP workers (read-only, uses the aos-sessions CLI)
Alert mod for Claude Code: blinks a red bar around the prompt when the session needs you (go-gate block, permission request, question)
AOS Control mod for Claude Code: unified cockpit for fleet, pipeline, git worktree stages and AOS settings
Pay for APIs and buy supported tokenized shares with prepaid funds. Search, research, media, data, compute and more through one Vaaya account. Agent purchase and Instinct funding guide: https://vaaya.ai/llms.txt
Opt-in blocking gate. Registers one PreToolUse hook that denies agent edits to trust surfaces and asks a human before force pushes, tags, releases, publishes, and risky deletes. Needs python3 on PATH. See HOOKS.md.
Read-only iOS App Store pre-submission check (static scan, fastlane precheck, guideline drift, Pierre commentary, semantic deep review).
testingThe decisions-only orchestration discipline — run any agent fleet at frontier-orchestrator efficiency, on any model. One markdown skill, no dependencies.
workflowBrainstorm the design with your human partner, get approval, then build it. The brainstorming step from Superpowers, without the planning and execution machinery.
Achieve flow state safely with Claude Code. Auto-approves ~60% of actions, gates risky operations, hard-blocks dangerous patterns. Dual enforcement: skill layer + deterministic hooks. Token cap for cost governance. 120+ unit tests.
securityHard proof-of-done enforcement for Claude Code via a Stop hook.
Use the redi CLI for Redmine work, and block direct reads of ~/.config/redi/config.toml
CodeAlive context engine for semantic code search and AI-powered codebase Q&A. Enables AI coding agents to understand entire codebases beyond just open files — search across all indexed repositories, trace cross-service dependencies, discover usage patterns, and get synthesized answers to architectural questions. Includes a lightweight code exploration subagent, authentication hooks, and multiple search modes (fast lexical, semantic, and deep cross-cutting). Works standalone or alongside the CodeAlive MCP server for direct tool access via the Model Context Protocol.
Claude Code companion: what is due in the status line, a FehlerDNA card while Claude works, a live FehlerDNA pane, and a roleplay scene pane.
The /objection skill, accuser and defender agents, and a hook that blocks PR create, ready and merge without an APPROVED record for the exact commit.
Optional session-boundary reinforcement for the MSW kernel.
productivityIntercepts unclear prompts and forces restate-to-align with the user, then diagnose the root cause and reuse the domain's mature, established practices before proceeding
Asks TypeSafe Jev which installed skill fits the prompt and, in shadow mode, logs the answer instead of speaking it. Experiment concluded; kept as a reference implementation.
Stip spec lifecycle in Claude Code: approved-contract workers, ownership guards, approval and apply gates.
Live status line and agent telemetry — the active /command or skill run with a timer, per-subagent context bar, model, estimated cost, tokens, duration and tool count, plus a per-run report. Run /statusline-kit:setup once to switch the status line on.
