Find plugins

by Zvi Rahamim

Measure what an AI coding session actually costs and get advice derived from your own transcripts — where the tokens went, which were re-read on every turn, and which fixes are worth making on this machine. Tells one person to install a compressor and the next that a compressor would be worthless, because it reads their numbers first.

by zhangq

运行时提醒 AI 节用 token：SessionStart 注入极简正向纪律，PreToolUse 在整读大文件时软提醒先定位行号，零硬拦。TOKEN_SAVER=off 关闭

by Ghast AI

Research onchain projects, financial metrics and methodologies with Token Terminal.

by cskwork

A live forecast of the context window, drawn above the prompt.

by Eidos AGI

Watch live local AI token burn and API-equivalent cost across OpenAI, Anthropic, and Google logs.

by Ghast AI

Find places, geocode addresses, compare routes and inspect traffic with TomTom Maps.

by Shrey Parikh

On the first prompt of every chat, recommends the best skills, connectors and plugins you already have installed, and lets you pick before work starts.

by awesome-claude-mods

Mission control for what Claude is doing: a live pane of every tool call with status, arguments, duration and failures, plus /radar summary.

by Claude Mods sample

A small Claude Mod that shows how long each tool call takes, tallies per-tool call counts and total time via /tool-stats, keeps a daily work log of every call, and tracks skill (/skill-stats) and agent (/agent-stats) usage.

by suwa-sh

汎用ワークフロースキル集. Includes 1 skill.

by GoatInAHat

Build an agent tool once; ship it as Agent Skills, MCP servers, Agent Plugins / Claude / Codex / Cursor bundles, OpenClaw and Hermes plugins, CLIs, and packages, with the tests and releases to match.

by dsh-agent-plugins contributors

Built-in toolset for DeepSeek Harness sessions: project init, codebase exploration, runtime verification, code simplification with the code-simplifier agent, offline session-history reviews with a self-contained dashboard, code review with the code-reviewer agent and command, AGENTS.md auditing and session-learnings capture, and automation recommendations for a codebase.

by Cedric Ziel

Cedric's personal layer on top of oss and skills: global working instructions and fleet brief, TDD hooks, hooks blocking fable-model subagents and forcing a fable session to delegate edits to a subagent, the GitHub issue/PR orchestration engine, code-review helpers, and SignalDB observability.

by juhyeon-cha

여러 스킬을 담는 도구 상자. 보고·공유용 HTML 자료 한 장 만들기, 소스에서 API 스펙을 뽑아 카탈로그 화면 만들기, 두 스냅샷의 API 계약 변경 화면 만들기, 성과 기록을 쌓아 대시보드로 뽑기, 사고 기록을 회고 문서로 만들기, PR 본문 쓰기, 발견한 것을 GitHub 이슈로 등재하기, 열린 이슈를 골라 닫기, 독자와 목적에 맞는 업무 문서 쓰기, 고정 코드 근거로 문서를 갱신하고 독립 리뷰 후 반영하기

by Sebastian Rädle

Werkzeuge mit ausschließlich expliziter Auslösung: /tools:ask und /tools:execute (die jeweils andere CLI non-interaktiv fragen bzw. beauftragen), /tools:unslop (KI-Muster aus Text entfernen), /tools:grimm (Sachverhalte ins Verwaltungs- und Anordnungsdeutsch überführen), /tools:orchestrator[-review|-cross] (Rollen-Prompt: steuern statt arbeiten, in drei Stufen bis zur anderen CLI als Arbeiter). Nachfolger der Plugins ask, unslop und grimm.

by Markus

tools-registry Script-Runner (stdio) + Skill tools-registry (Tool-Katalog als Trigger)

by Falconiere Barbosa

Dual-host engineering discipline for Claude Code and Codex: workflow skills, agents, commands, and registry-driven quality hooks.

by Falconiere Barbosa

Project-tuned pre-push code review mirroring CI falconiere/toolu-ghactions/code-review@v8 (Jev-enabled), writing the toolu push-review state so the gate passes. Standalone.

by Luis Perez Morales

Hide chosen topics from Claude: listed terms become stable placeholder names (or their lines are dropped) in tool output, prompts, CLAUDE.md, memory and skills before the model reads them.

by Topo

Run your Topo outbound workspace from chat: triage replies, clear tasks, start outreach, source leads, set up signals, playbooks and AI variables, and brief accounts.

by ncoleman

Verify that every citation and reference in a document is real, accurately described, and consistently used.

by erstaples

Walks through a diff with editor navigation and a persistent, evidence-backed living change dossier.

by L. Richard

Technical program management skills: /tpm runs a program through charter, buffered plan, risk register, stakeholder/communication plan, and audience-leveled status reports; each stage is also its own skill. Frameworks are distilled locally so the plugin works fully offline and never calls a RAG or network source at runtime.

by x-mesh

Agent execution tracing — timeline, token/cost tracking, replay, and diff for multi-agent observability