llm agents plugins

49 tagged llm agents, measured the same way as everything else here.

Browse within: Multi-Agent 6

stripe

01

stripe/ai

Plugin Claude Code

Plugin marketplace listing 1 plugin: stripe.

1.8k +4 yesterday A tokens not measured original MIT

stripe

02

stripe/ai

Plugin Claude Code

Stripe development plugin for Claude.

1.8k +4 yesterday A tokens not measured original MIT

autoharness

04

tigerless-labs/autoharness

Plugin Claude Code

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.

1.4k 1mo ago A tokens not measured original MIT

paperjury

06

Spark-To-Paper-Skills/paperjury

Plugin Claude Code

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.

1.0k 18d ago A tokens not measured original MIT

cc10x

07

romiluz13/cc10x

Plugin Claude Code

Plugin marketplace listing 1 plugin: cc10x.

164 28d ago A tokens not measured original MIT

cc10x

08

romiluz13/cc10x

Plugin Claude Code

The Loop Engine — harness and loop engineering plugin for Claude Code. Router-kernel orchestration, workflow artifacts, sub-agent delegation, hook enforcement, Test Honesty Gates, fresh-context verification, and memory that persists. 73% leaner than v11, zero quality regression.

164 28d ago A tokens not measured original MIT

skill-optimizer

09

hqhq1025/skill-optimizer

Plugin Claude Code

Agent Skills for improving SKILL.md files: mine repeated workflows from history, personalize and audit existing skills, or generalize personal skills for publication.

163 3mo ago A tokens not measured original MIT

plan-cascade

10

Taoidle/plan-cascade

Plugin Claude Code

Plugin marketplace listing 1 plugin: plan-cascade.

124 5mo ago A tokens not measured original MIT

plan-cascade

11

Taoidle/plan-cascade

Plugin Claude Code

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…

124 5mo ago A tokens not measured original MIT

axstream

12

milind-soni/axstream

Plugin Claude Code

Fast, verified computer use for coding agents — screen-as-text perception, batched verified actions, self-compiling macros.

20 23d ago A tokens not measured original MIT

axstream

13

milind-soni/axstream

Plugin Claude Code

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.

20 23d ago A tokens not measured original MIT

dos

14

anthony-chaudhary/dos-kernel

Plugin Claude Code

DOS — the domain-free trust substrate for fleets of autonomous agents.

19 7d ago A tokens not measured original MIT

dos-kernel

15

anthony-chaudhary/dos-kernel

Plugin Claude Code

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.

19 7d ago A tokens not measured original MIT

vukkt-plugins

17

vukkt/token-warden

Plugin Claude Code

Plugins by Vuk Topalovic — currently token-warden, a measurement and selection layer that makes Claude Code subagents measurably cheaper over time.

13 3d ago A tokens not measured original MIT

token-warden

18

vukkt/token-warden

Plugin Claude Code

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.

13 3d ago A tokens not measured original MIT

kernel-marketplace

19

ariaxhan/kernel-claude

Plugin Claude Code

Safety guardrails, cross-host hooks, and agentdb memory for Claude Code and Codex in auto mode.

12 yesterday A tokens not measured original MIT

kernel

20

ariaxhan/kernel-claude

Plugin Claude Code

KERNEL is a Claude Code and Codex plugin that replaces per-action approval prompts with guardrails enforced by hooks. Hook context is shaped for both hosts' plain and structured output parsers. In auto mode, destructive commands and secret writes are blocked before they run; irreversible operations require a one-time…

12 yesterday A tokens not measured original MIT

kw-engine

21

chenpg2/kw-engine

Plugin Claude Code

Methodology evolution engine — distill transferable principles from literature, search by problem structure.

11 2mo ago A tokens not measured original MIT

kw-engine

22

chenpg2/kw-engine

Plugin Claude Code

Methodology evolution engine — distill transferable principles from literature, search by problem structure.

11 2mo ago A tokens not measured original MIT

chub

23

nrl-ai/chub

Plugin Claude Code

Context Hub (chub) integration — MCP-powered documentation lookup, team annotations, and project context for AI coding agents.

11 5mo ago A tokens not measured original MIT

odin-reflector

24

OutlineDriven/odin-reflector

Plugin Claude Code

Marketplace for the codex-reflector Claude Code plugin — independent second-model reviewer using OpenAI Codex CLI.

9 22d ago A tokens not measured original Apache-2.0