31 tagged llm-agents, measured the same way as everything else here.
Browse within: claude-code-plugin 11Multi-Agent 5
Plugin Claude Code
Bundles 1 skill, 2 agents, 4 hooks · 78 tokens together
Per-symbol maintenance optimizer for an agent's skill layer — learns skills from real runs and keeps them by adherence in use, not by an offline eval score.
Plugin Claude Code ✓ vendor
Bundles 2 commands, 1 agent, 5 hooks, 1 MCP server · 37 tokens together
Stripe development plugin for Claude.
Spark-To-Paper-Skills/paperjury
Plugin Claude Code
Bundles 1 skill · 263 tokens together
Pre-submission AI review and editing for CS-conference papers: direct-edit LaTeX or Markdown (Word via one-time extraction), run an adversarial multi-agent courtroom review with consensus-gated revisions, or run it unattended toward a goal.
Plugin Claude Code
Bundles 3 skills · 136 tokens together
Agent Skills for improving SKILL.md files: mine repeated workflows from history, personalize and audit existing skills, or generalize personal skills for publication.
Plugin Claude Code
Bundles 22 skills, 14 agents, 10 hooks · 2,100 tokens together
The Loop Engine: a harness for Claude Code. One router sends each request to one of eight workflows (build, debug, review, plan, QA, orient, triage, codebase health) run by specialist subagents, with fail-closed gates, workflow artifacts on disk, hook guardrails, test honesty gates, fresh-context verification, and…
Plugin Claude Code
Bundles 7 skills, 33 commands · 1,906 tokens together
AI-powered cascading development framework with design document system and multi-agent collaboration. Breaks down projects into Features (Mega Plan), Features into Stories (Hybrid Ralph), with auto-generated technical design docs, dependency-driven batch execution, Git Worktree isolation, and support for multiple AI…
Plugin Claude Code
Bundles 1 skill, 2 commands · 118 tokens together
Persistent causal memory for Claude Code — decisions, outcomes, and lessons that survive compaction. Same-context counterfactuals (natural experiments), a falsifiable prediction ledger, and an activation skill that teaches when to recall and record.
Plugin Claude Code
Bundles 1 skill, 3 commands, 1 MCP server · 143 tokens together
Fast, verified computer use for coding agents: read the screen as text (200ms), execute batched verified actions, and compile any task done once into a macro that replays in seconds with zero model calls.
Plugin Claude Code
Bundles 18 skills, 3 hooks, 1 MCP server · 913 tokens together
The kernel is the part that doesn't believe the agents. Bundles the DOS hooks (verify-on-stop, deny-a-refused-call, re-surface-a-stalled-stream), the DOS MCP server (verify / arbitrate / refuse-with-a-reason as tools), and the generic skill pack — one install. Requires the dos-kernel Python package: pip install 'dos.
Leehyunbin0131/claude-ros2-skills
Plugin Claude Code
Bundles 3 skills, 1 hook · 153 tokens together
ROS 2 Jazzy workflows, scoped evidence handoff, test-result checks and runtime diagnostics.
Plugin Claude CodeGemini CLI
KERNEL's methodology layer for Gemini CLI: 27 software-engineering agent skills plus llms.txt as ambient context. Skills cover systematic debugging (reproduce, isolate, regression-test), generating competing approaches before implementing, pre-implementation critique, code review, bounded context handoff and resume…
Plugin Claude Code
Bundles 7 commands, 4 agents, 3 hooks · 380 tokens together
Agent memory, charged rent. A Stop hook records what each session costs; expensive runs are distilled into candidate efficiency rules; each candidate is benchmarked on a frozen golden suite and kept only if it saves at least twice its context rent. Six commands. Two theorems survived measurement and three were deleted.
Plugin Claude Code
Bundles 4 skills, 5 agents · 541 tokens together
Methodology evolution engine — distill transferable principles from literature, search by problem structure.
Plugin Claude Code
Context Hub (chub) integration — MCP-powered documentation lookup, team annotations, and project context for AI coding agents.
Plugin Claude Code
Codex CLI reflector — independent critic, oracle, and metacognition layer.
Plugin Claude Code
Marketplace for dev-loop — a wiki-grounded implementation loop plugin for Claude Code (loop-orchestrator + dev-llm-wiki, merged).
Plugin Claude Code
Bundles 1 skill · 0 tokens together
Self-hosted audio-production API — stem separation, mastering, MIR analysis, DSP chains, MIDI, and AI restoration over REST and MCP.
Plugin Claude Code
Bundles 1 skill · 53 tokens together
Portable continuity protocol for long-running coding agents.
billylui/wordpress-performance-skills
Plugin Claude Code
Bundles 2 skills · 287 tokens together
Audit and fix performance on live WordPress sites across whatever stack they actually run — page builders, caching layers, CDNs and managed hosts. Fingerprints the stack, separates origin from edge TTFB, and applies fixes only under a guarded write loop with a rollback for every change.
Plugin Claude Code
Marketplace for loop-orchestrator — a methodology-grounded multi-session orchestrator plugin for Claude Code.
Plugin Claude Code
Bundles 2 skills · 424 tokens together
Run a task as an evolved multi-agent ORG. The compose-org skill makes the running Claude embody a proven team — one subagent per specialist talent — then grades and records the result so good teams get reused on similar future tasks. Backed by the liquid-org CLI (plan / compose / record).
Plugin Claude Code
Bundles 2 skills, 3 commands · 224 tokens together
War-game your hard calls. A council of non-colluding officers plus a mandated dissenter returns the strategy that wins — and what would make it lose.
Plugin Claude Code
Bundles 20 skills, 3 commands, 3 agents, 1 hook · 1,029 tokens together
Data mining skills library: EDA, validation, feature engineering, modeling, and proven analytical workflows for data analysts.
GuoCheng24/breakthrough-harness
Plugin Claude Code
Bundles 1 skill · 107 tokens together
Breakthrough-loop research discipline: hard-to-fool scoring harness + parallel cheap candidate generation, as a Claude Code skill.