3,273 tagged ai-agents, measured the same way as everything else here.
Browse within: agentic-ai 236claude-code-plugin 213LLM 190cursor 177cli 133prompt-engineering 111agents-md 107Science 99agents 87ai-coding 81agentic-coding 62ai-tools 62skills 60ai-governance 54
bjornslib/mcp-to-uber-skills-converter
Plugin Claude Code
Bundles 1 skill, 1 hook · 72 tokens together
Convert MCP servers to Claude Skills with progressive disclosure. Reduces context usage by 90%+.
Plugin Claude Code
Free, open-source Claude Code and Codex tools by DBHQ.
Plugin Claude Code
Bundles 15 skills, 1 MCP server · 1,333 tokens together
Claude Code plugin for operating Sequenzy email marketing workflows with agent skills.
Plugin Claude Code
Plugin marketplace listing 1 plugin: turbocharge.
Plugin Claude Code
Continuous memory that survives context compaction — harvests your agent's own confidence-marked claims into a verbatim brief and re-injects it after compaction.
Plugin Claude Code
Bundles 1 skill, 1 hook · 0 tokens together
A communication layer for your AI coding agent: plain language, no jargon, no invented timelines, and one clear yes before anything irreversible — shaping how the agent talks to you, not how it works.
Plugin Claude Code
Plugin marketplace listing 1 plugin: harmonia.
Plugin Claude Code
Bundles 20 skills, 2 hooks · 602 tokens together
The reflex layer on top of superpowers. Tunes an agent's working instincts — verify against the source, instrument for remote diagnosis, write for humans, test with teeth.
Plugin Claude Code
Bundles 1 skill, 1 hook · 65 tokens together
Cross-platform secrets workflow for macOS, Windows, and Linux. The keys CLI routes values to explicit local sinks without returning plaintext in normal agent tool output. It also organizes local folders and explicit project scopes so approved workers receive only assigned entries and contributors can submit new entri.
Plugin Claude Code
Bundles 6 skills, 2 hooks · 444 tokens together
Subtraction-first engineering for AI agents. The smallest correct change wins.
Plugin Claude Code
Bundles 51 skills, 4 agents · 5,454 tokens together
Portable AI-agent skills for the deliverables knowledge workers ship — diagrams, ADRs, PRDs, runbooks, decks, reviews — installable into Claude Code, Cursor, Kiro, and any IDE that takes custom instructions. One command per skill or per role-based pack.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 95 tokens together
Persistent, governed memory for Claude Code. Remember decisions once; recall them in every future session, across every tool on the team.
valenciajinxed265/claude-skills-hub
Plugin Claude Code
Security reminder hook that warns about potential security issues when editing files, including command injection, XSS, and unsafe code patterns.
Plugin Claude Code
Bundles 1 skill · 86 tokens together
Turn a topic into an Instagram carousel delivered as animated vertical videos. Ten visual archetypes, fourteen slide roles, and a validation gate that refuses unreadable contrast, overflowing type, or a story arc that does not hold together.
Plugin Claude Code
Bundles 1 skill · 107 tokens together
Dual-lens feature ideation: mine the codebase for grounded direction signals and gather real user evidence to brainstorm, score, and spec new capabilities for any actively developed project.
2389-research/scenario-testing
Plugin Claude Code
Bundles 1 skill · 74 tokens together
End-to-end testing with real dependencies - no mocks allowed; scenarios with real data are the only source of truth.
Plugin Claude Code
Official Claude Code plugins from Wire — persistent memory, context management, and AI agent tools.
Plugin Claude Code
Bundles 1 skill · 135 tokens together
Defensive, local-first security recon that briefs your AI coding agent on your OWN codebase. Read-only by default: facts + tailored probes + a calibrated findings ledger, code-in / artifacts-out, no LLM / no server / no running app. Live probes are opt-in against a TEST instance you own; production is out of scope.
Plugin Claude Code
Bundles 5 commands, 12 agents, 1 hook · 1,348 tokens together
Five slash commands for the implementation half of the product lifecycle: /design turns a specification into a design, with Opus review and an optional three-take fan-out on a contested interface. /implement builds it, gated by Opus plan critique and code review before tests. /ready verifies an ARD/spec/design ch.
Plugin Claude Code
Bundles 1 skill, 10 commands · 71 tokens together
A structured 4-phase iterative development workflow for AI coding agents: Analyze, Design, Implement, Postmortem.
Plugin Claude Code
Bundles 1 skill · 175 tokens together
Consolidated design questionnaire — front-load an agent's clarifying questions into one convenient, capped, paginated web form so the design is right on the first go. The inverse (in cadence) of grilling.
Plugin Claude Code
Dravensoft's official plugins for Claude Code.
Plugin Claude Code
Bundles 10 skills · 388 tokens together
Ten focused engineering skills for planning, implementation, causal debugging, review, verification, complete execution, and recoverable deployment. Optional hook reminders; no forced router.
Plugin Claude Code
Bundles 1 command, 4 hooks · 21 tokens together
Pick up exactly where you left off. Per-project resume of your last task + next step. No DB, no API keys, no MCP.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: