rich-terminal
xiaolai/claude-rich-terminal
Mermaid diagrams drawn inside Claude Code replies, and a truecolor status line under the prompt with a Token Weather forecast of the context window.
9,065 mods
xiaolai/claude-rich-terminal
Mermaid diagrams drawn inside Claude Code replies, and a truecolor status line under the prompt with a Token Weather forecast of the context window.
Akramovic1/jev-pilot
TypeSafe's Jev decides how Claude Code works on each prompt: the main conversation's reasoning effort (low to xhigh, raised to max mid-turn when tool calls keep failing), each subagent's model, whether to split the work across subagents, and the one skill the prompt needs. Brings in custom OpenRouter models (a junior coder reviewed by Opus, or cheap bulk work) and Codex or OpenCode as...
cookys/autopilot
Development autopilot — 31 lifecycle skills + 3 methodology agents + 53 hooks (34 default-on, 19 opt-in) enforcing Three Red Lines discipline. Standalone-capable orchestration that coexists with Superpowers.
thkt/dotclaude
Read ツールの結果に含まれる認証情報の形をした文字列を、モデルが読む前に伏せる。
yugabyte/meko
Kode's link into the Claude Code sessions it runs: takes Kode's prompts and reports usage.
yugabyte/meko
Draws Kode's prompts in the Claude Code sessions it runs as one line each; ctrl+o shows them in full.
KyongSik-Yoon/cc-desktop-mod
Claude Code mod that redraws the terminal transcript to look like the Code tab of the Claude desktop app: prompt bubbles, markdown tables, mermaid diagrams, folded tool calls, agent cards, plan cards in the transcript, a progress band of the current step and what runs now, GitHub/GitLab PR bar, diff, activity, context, background tasks, session monitor and Markdown preview panes. The Asana and...
KyongSik-Yoon/cc-desktop-mod
Claude Code mod that opens your Asana tasks in a side pane (/desk-asana): the tasks assigned to you, a search across the workspace and your projects' tasks by section, with details, comments, adding a comment, assignee, dropdown fields and status. Reads Asana through the Asana MCP server Claude Code already has connected. Pairs with desk-look
KyongSik-Yoon/cc-desktop-mod
Claude Code mod that opens the Slack DMs and group DMs sent to you as conversations in a side pane (/desk-slack): recent messages, replying, closing, and a notification when a new one arrives. Reads Slack through the Slack MCP server Claude Code already has connected. Pairs with desk-look, whose status band shows the unread count
KyongSik-Yoon/cc-desktop-mod
Claude Code mod that asks for plan approval (ExitPlanMode) in a card above the prompt instead of the full-screen engine dialog, with the plan open in desk-look's preview pane: 1 approves, 2 views the plan, type what to change or comment on plan lines in the pane (c, then 3) to send it back, 9 for the engine dialog. Needs desk-look
KyongSik-Yoon/cc-desktop-mod
Claude Code mod with a /desk-review:simplify-review skill (/simplify, then /code-review medium) whose report opens in a side pane: each fixed, skipped, found or dismissed item with its reason, its diff or current source unfolding in place, and the file opened in desk-look's diff pane. Needs desk-look
jyooi/agent-simple-english
Apply technical and house-style writing rules to writes, edits, git commit messages, and replies. Needs Claude Code 2.1.296 or later.
rbinar/cli-dispatch
Delegate tasks to the right worker CLI — multi-backend delegation hub. Backends: DeepSeek-powered Claude Code (claude-ds), Antigravity / Gemini (agy, ag-agent), OpenAI Codex CLI (codex, cx-agent), OpenCode via OpenRouter (opencode, oc-agent), GitHub Copilot CLI (copilot, cp-agent), and a local Ollama model (ol-agent). Setup-time backend selection, deterministic runner (cli-dispatch-run —...
nerviz-ai/nerviz
Draws what ArchHook already decides: the open skill phase and its write territory above the prompt, /nerviz-doctor in a pane, and a guard refusal held behind two buttons.
nerviz-ai/nerviz
A pane over ArchHook.jar config: the settings a project owns in its own .claude/, in the nerviz identity, changed only through config set and config unset after a dialog.
xuanji86/claude-agentpane
A side pane for Claude Code that lists the subagents a session runs, what each is doing and what it costs in tokens, with each one's conversation a click away.
gabe4coding/claude-code-mode
Code mode for MCP: the model writes one JavaScript program that calls MCP tools in a sandbox, instead of one tool call per step.
AkshitTiwarii/mantle
One theme everywhere: Claude Code, Windows Terminal (scheme, wallpaper, acrylic) and claude.ai, alive to what Claude is doing.
davekiss/mods
Know when main is broken before you build on it: a red row above the prompt says how long your repo's default branch has been failing CI and how many pushes landed on top, and the agent is told too.
davekiss/mods
Find where your Claude Code week went and fix it: /leaks ranks the avoidable spend in your transcripts with one-press fixes, and a strip above the prompt flags a leak while it happens.
alexandernicholson/agent-router
Choose a model and effort for five agent roles and for agent team teammates with /agent-models, and inspect routing and usage. Requires Claude Code Mod function hooks enabled.
alexandernicholson/agent-router
A prompt cache bar for every conversation, subagent and teammate, a dashboard with /keepalive, per-conversation cache TTLs, and upkeep that keeps an idle cache warm or compacts it before it expires. Requires Claude Code Mod function hooks enabled.
vayaan-labs/cache-maxxer
Shows the prompt cache's countdown and hit rate above the input box, explains every cache break and cache expiry, and can keep the cache warm to cut Claude Code cost
jsk4581/jev-blindspot
A one-glance summary of jev-blindspot in the band above the prompt: the blind spot count, the deeper question, and the top findings for the prompt you just sent.
No tracking cookies, no third-party scripts. How we handle data