Havuz

Eco mode for Claude Code. /eco: -31% to -73% output tokens with critical findings intact; /eco-max: up to -75% with lowered effort. Measured

Make Claude Opus 4.8 behave like Claude Fable 5 — doctrine output style, drift-catching hooks, and an eval loop against golden Fable transcr

Shorter replies with Claude Code. Save output token spend.

Moteur de recherche libre sur le droit français et européen — jurisprudence et textes (loi à n'importe quelle date), en web, API et MCP. Fre

Your whole product team, not just a coding agent. Plan → design → build → QA, with you as the PM who signs off.

Tech-lead orchestration for Claude Code — the top-tier model (Fable) keeps architecture & decisions, cheap subagents (Sonnet/Opus) do the ro

Your engineering crew for Claude Code — 12 specialists plan, build, review and ship in any stack; the rules that matter are enforced, not re

OKF-powered knowledge context for Claude Code — injects your project's knowledge base at every session

Lightweight Codex/Claude/Antigravity loop harness with strict evidence gates.

RuvNet Brain — a downloadable, source-grounded brain for Claude Code over Reuven Cohen's (rUv's) RuvNet stack: RuVector/RVF, Ruflo, AgentDB,

Bionic reading for Claude Code: bolds the leading part of each word in Claude's streamed replies so your eyes move faster. Zero dependencies

Staged context pruning for OpenCode, Oh My Pi, pi, and Claude Code.

Stop agents from over-engineering. Inspired by Ponytail, but without the plugin madness. Just one AGENTS.md file.

Local AI Coding Hub: Run Claude Models Offline in 2026

Claude Mythos Engine 2026: AI Sub-Agent Framework for Epic Interactive Storytelling

AI Coding Agent Orchestrator 2026: Pro-Level Strategy & Review Framework

Claude 3.5 Sonnet Desktop Client for Windows Mac Linux 2026

Advanced AI Code Strategy Advisor for Developer Agents (2026)

Self-hosted agentic OS — a Vibe-Engineering platform for Builders. Connect Claude Code Agent to Discord, Telegram, WhatsApp, Slack & Email.

Claude Code plugin marketplace — agentic-engineering (spec-driven shape→decide→execute→measure→eval with adversarial review) + github-keeper

Build, govern, and ship Streamlit-in-Snowflake apps with Claude Code and AI agents

23 practical agent skills: TeamWorkflow, multi-model review, media ingestion, and writing. Original Claude Code packages plus a Codex deskto

Six Claude Code skills + an unattended build loop, each measured with and without the plugin. 19/19 evals passing.

Persistent memory for AI agents, for code, research and everyday life. Facts are typed, sourced, and retired when they change. Local SQLite,

Run different Claude Code providers in different terminals. 支持同时在不同终端窗口用不同 API Key 跑 Claude Code，互不影响

Local pull-request review brief for coding agents: the diff, the tests and callers of changed code, and change signals in one report. No LLM

Dex lets your agent build your analytics.

Context optimization for AI coding agents — lower token cost and latency without sacrificing accuracy.

A Claude Code skill that scaffolds ready-to-run LangChain Deep Agents and dcode CLI agents into any project.

Idea-to-store autonomous harness for Flutter/Flame games across Claude Code, Antigravity, and Codex. Automates research, planning, design, g

Keeps AI assistants on track during long conversations by tracking tasks across sessions

Web UI for spinning up isolated devcontainer instances for multiple simultaneous Claude Code workflows using VS Code.

Design UI changes from real source code — verify data, iterate faithful HTML mockups, then delegate. A Claude Code plugin & Codex skill by n

Stop wasting tokens and re-explaining your project every session. Recall gives Claude Code , Opencode durable memory — entirely offline.

Compact coding-agent context without summarizing it away. Verbatim, offline, with a receipt and recall for every cut. CLI, MCP server, Claud

Claude Code plugin for autonomous AI research — multi-agent loops take a bare topic all the way to running experiments, with no human-writte

Build with Claude Code without your brain going numb — a plugin that quizzes you on the code it just wrote and gates the session until you p

🏛️ The patent plugin for AI coding agents — turn technical ideas into patent disclosures with Claude Code, Codex, and OpenCode.

Claude Code plugin for visual docs — annotated screenshots, feature demos, flow walkthrough recordings (gif/mp4), terminal captures and befo

Long-term memory for AI agents with no LLM call: an MCP server and Claude Code plugin, plus local-first context compression for LLM apps.

Claude Code에 '15명 전문가 관점 + 자동 트리거' AI 개발 파트너 페르소나를 입히는 플러그인. 항상켜짐 hook + 조건부 skill + 인터뷰형 생성/편집 명령어, 세무·법률 면책 자동, 새 PC 이식형. Apache-2.0.

The OKF toolkit for Claude Code — author, maintain, validate & visualize Open Knowledge Format bundles. Plugin, agent skills, and a GitHub A

Fable-style verification gate for Claude Code: don't say done until it's verified. Port of the Codex plugin by Agent Korea (플라잉따릉이).

Make every model cheaper or better. Zero-config behavioral harness for Claude Code, with a reproducible 408-run benchmark

Claude Code harness and alternative to context compaction: at 80% context it writes a verified capsule, runs /clear and resumes with persist

A discipline plugin for Claude Code + OpenAI Codex — plan first, verify against the real code, receipts on every decision, independent adver

CLI over the freehire job API for agents

Ponytail, AI coding agent'lara daha az ve daha yalın kod yazmayı teşvik eden bir skill ve araç paketi sunuyor.

Neden yükseliyor · 108 günde 146 bin yıldız, güçlü ilgiye işaret ediyor. Agent'ların gereğinden fazla kod üretmesi yaygın bir şikâyet; proje bu ihtiyaca kolay denenebilir bir skill ve ölçüm sonuçlarıyla yanıt veriyor. Ancak son 28 günde 14 commit ve 2 farklı yazar olması, yıldız sayısının tek başına benimsenme veya sürdürülebilirlik kanıtı olmadığını gösteriyor.

Keep Claude Fable 5 in the chair all day without draining your usage limit — token-frugal multi-agent orchestration plugin for Claude Code:

When Claude says “tests pass”, makoto checks the record — every claim held against the agent's own logged deeds; fakes blocked, not warned.