#plugin

Turn feature requests into review-ready pull requests: issue, implementation, tests, a review-and-fix loop, and docs. Runs locally or on GitHub Actions, and is built for complex brownfield repos. Each week its retrospective reads what you actually merged and proposes improvements to your skill extensions.

A lightweight Grok plugin for Claude Code — delegate coding and review tasks to the Grok CLI. A simple reimplementation of OpenAI's codex-plugin-cc.

AI agent skill bundle for Storybook on React + Vite — audit real-vs-slop components, capture flows, write CSF3 stories, ship. Claude Code / Codex / Cursor.

Cmd+K for herdr: fuzzy-jump to any tab, agent, repo or branch. Python stdlib only.

Tell Claude Code what you want once. It works until the job is verifiably done — and gets smarter every time. Self-correcting goal loops with independent verification and growing memory.

Forge your Claude Code projects — pass them through, they come out faster.

Hermes image generation provider for OpenAI-compatible endpoints and Codex Auth

AI 코딩 비서(Claude·Codex·Gemini)가 확인도 안 하고 '다 됐어요' 하는 걸 자동으로 막아주는 품질 안전장치 — 비개발자·바이브코더를 위한 한국어 우선 하네스.

Local-first memory for Claude Code — remembers your decisions and the why, reloads the relevant slice every session. No API key.

Livingcolor plugin for Hermes agent

Claude Code plugin marketplace for mojiemoji.jozo.beer — expressive Japanese stamp rendering for GitHub markdown

从Claude Code、Codex、Reasonix等Agent工具导入迁移历史消息，并在DeepSeek Harness(DSH)中继续对话

Using Telegram bots easily deploy multiple Claude code tasks 使用Telegram bot部署轻松实现多Claude code任务的远程控制

Hardened Claude Code plugin that delegates work to the Grok Build CLI: tracked background runs, real process cancellation, honest failure codes, local spend ledger.

Qdrant-backed semantic memory provider for Hermes Agent

On-demand vision for text-only DeepSeek Harness (DSH) sessions: images become markers, and a vision_describe tool sends only image + question to an OpenAI-compatible vision model

Claude Code icin cok ajanli is rolesi + neon arayuz standardi. Talebini soyle, is bolumu ve denetim otomatik kurulsun.

Run an open-source repo as its maintainer: triage the tracker, delegate the work, review hard, merge on green. One loop, one version, and per-repo differences in config instead of prose.

Claude Code plugin for OpenAI Codex subagents, Codex Spark, parallel code review, and long-running Codex sessions via daemonless MCP

Portable, auditable, coverage-honest dev lifecycle plugin — spec→plan→build→review→test→merge with reviewer/QA handoff docs. Runs on Claude Code & Cursor.

Claude Code setup where skills fire on their own: 22 skills, 7 subagents, a routing hook, and a verification gate that blocks false completion claims

Hermes Agent plugin — extracts repeated tool-call patterns from live execution traces and proposes them as evidence-based micro-skills

A portable Claude Code skills library (plugin) for a Django 5.2 + Next.js 16 house stack: 30 model-agnostic, tenant-isolation-and-security-first skills.

A runtime spotter for coding agents — watches the trajectory and steps in before mistakes compound.

Give text-only DeepSeek models vision by describing images through an OpenAI-compatible vision model (DSH plugin)

Symlinks ~/.claude/projects/<absolute-slug> to ~/.claude-projects/<portable-slug> on every prompt, keeping Claude Code project memory portable across Linux and macOS machines.

A VS Code extension that plays distinct sounds and shows system-level notifications when Claude Code finishes a task, needs your approval, or needs clarification — even when VS Code is not in focus.

Brain-grounded SDLC pipeline for Claude Code — story → arch → slice → fleet → PR, with gates held in code

Autonomous goal-directed iteration loop for Claude Code, Codex CLI, and OpenCode. Modify, verify, keep, discard, repeat. Inspired by Karpathy's autoresearch.

Free AI supply chain security checks for GitHub repos — right from a Claude conversation

Ten Claude Code skills that fix bugs Anthropic closed as 'not planned'.

Plugin for Claude Code, Hermes Agent, and Codex that adds write operations (publish, sync, maintain) to a self-hosted SAG (Zleap-AI/SAG) knowledge base — without modifying SAG's source code. Agents self-assess and auto-publish durable knowledge under a safety floor (secret scan, dedupe, cost cap), with manual commands always available.

비개발자를 위한 Claude Code 세션 관리 플러그인. 3개 명령어(/hs, /ci, /co)로 프로젝트 컨텍스트 유지.

🪄 Reopen Claude Code exactly where you left off — a tiny plugin that drops a self-destructing resume_last_session.sh when a session ends.

Tell your coding agent to relax — a per-project posture plugin for Claude Code and Codex. Three tiers: normal, chill, reckless.

Top Free Context Engineering Plugin 2026 - Claude Code, Cursor & Codex Setup

Claude Code plugin — a CRISP-DM, 9-stage gated data-analysis workflow (skill + 3 subagents + 3 scripts), shipping a bilingual ko/en HTML data essay.

Standalone Chutes model-provider plugin for Hermes Agent

Installable multi-provider image generation bundle for DeepSeek Harness (Google Gemini, OpenAI, Volcengine Seedream)

Slack Socket Mode plugin for Paperclip — agent chat, notifications, approvals, ask-human tool. No public URL required.