Productivity plugins

A curated collection of agent skills from popular open-source repositories plus custom skills — all in one place.

Mem0 plugin placeholder for local Codex marketplace installation.

Claude Code mod that counts down the prompt cache, shows and sets Claude Code's own idle compaction, and can push a reminder to your phone.

Obsidian vault search, LSP, and MCP tools for Claude Code

Token efficient browser automation for Codex and AI coding agents

Status line: minutes left until the main thread's prompt cache goes cold (assumes a 60-minute cache; it is 5 minutes during usage overage, which the mod cannot detect)

MVP-focused feature planning and execution workflow for Jira. Plan features as Stories with flat Subtasks, create issues, and orchestrate work.

Tracks what Claude Code costs — session, calendar-week and calendar-month totals with the month's pace and week-over-week change, a /costs pane with a spend calendar, the most expensive prompts and what filled the context, plus prompt-cache awareness: a cache warm/cold countdown, warnings before a prompt, model switch or large write re-caches the context, a per-category breakdown priced at list or your own (e.g. AWS) rates, per-project and subagent splits, budget alerts, CSV export and a /costs doctor self-check, the cache lifetime learned from Claude Code's own pricing, what a cold re-cache will cost before you resume, and an optional keep-alive that holds the cache warm while a session sits idle

Fixes spelling and typos in each typed prompt with a fast model before the main model reads it.

冥想呼吸面板：/meditate 开始一段定时的引导呼吸（方箱 / 4-7-8 / 平静），记录累计次数与连续天数

An exoskeleton for Claude Code: guards against costly mistakes, a cockpit while working, a recap at the end and a few extras

No description.

Local Codex conversation map with branches and follow-up conversations.

Codex AI for Android - OpenAI Codex CLI 全栈安卓化

Paste a link with a short question and Claude's answer opens with a verdict for your projects: use it, later or skip, the effort, the cost and one line why

Every prompt carries your local date, weekday and the week ranges, and a reply whose dates miss the period you asked about gets flagged

Every look you reject becomes a rule for that project, with your screenshot, so Claude never brings it back

Enhance button above the prompt: Sonnet sharpens your draft using the recent conversation

A tiny pixel creature that lives above your Claude Code prompt. It counts down your prompt cache and guards it on model switches, wakes Claude when your usage limit resets, brings a helper for every subagent, makes sound on Windows and Linux, yelps before risky commands, rolls its eyes at "You're absolutely right", and brings back your old /buddy.

Usage panel beside the conversation (session, tokens, context, cost, Gemini, tools) with an animated mascot. Optional: bravesline stays the status bar.

The GTM operator mod for Claude Code: scores every go-to-market draft with its own skill pack's scorer, flags stale and inconsistent drafts across packs, pack dashboards, a guided sprint, analytics, and a guard that keeps brand-config.json and SOUL.md merged.

Preview 3D Gaussian splats in a Claude Code pane: orbit with the mouse, rendered by Spark in headless Chrome

Live agent dashboard with Clawd crabs: model vitals, permission gate, architect, subagent cards, the agent tree and plan/doc graph, and a three.js 3D view of agents interacting, in the pane (/crew 3d) or the browser (/crew web). Absorbs Flightdeck

A background Haiku watches the session and, at the right moment, suggests one of your installed skills above the prompt.

Lindo AI plugin for OpenAI Codex — create websites, pages, and blogs with AI

Ask follow-up questions in a side pane without touching the main conversation, or call an agent with /btw @name. Replaces the built-in /btw while installed.

Review Claude’s reply in place, block by block, and send your review as one prompt. A terminal mod for Claude Code.

Student-led, AI-assisted local-first whiteboard with a TypeScript/SVG editor, portable Windows runtime, and explicit AI editing through MCP.

Products of anicca

Puts non-Claude models into Claude Code's /model picker through the user's own provider logins, with an Anthropic guard on every routed request.