claude-mod

Themeable rendering for replies: tables, code, Mermaid diagrams and charts with copy buttons. Adds ~630 tokens of formatting hints per prompt by default. Reviewed: Caution.

4 skills

One live line above the prompt per running subagent: time, tool count and what it's doing. /radar shows every agent and its messages. Reviewed: Recommend.

Keeps the one-hour prompt cache warm during breaks and stops a cold send once with its estimated cost. Warming spends tokens and can switch itself on. Reviewed: Caution.

Your context window as a stacked bar above the prompt, a color per category, with token counts and the compaction point. Reviewed: Recommend.

A resident product team in Claude Code, run from its own pane with buttons and fields, no command needed: a PM splits your PRD into features and acceptance criteria, QA writes a test case for each, a UI/UX designer writes a design for each feature that you approve on one page with the PRD draft and the roles' questions, a tech lead breaks the criteria into tasks and reviews the code, a full-stack agent builds the tasks on crew's own git branch and worktree, and crew runs your test command and maps the results to the test cases. Each role runs on Claude or Codex, from a floor you set, stepping up with how hard the work is. Gaps and product questions come back to you in the pane. A heartbeat looks after the work every five minutes, a restart asks before going on, and token reminders go to Claude, which acts on usage only as you allow. The board is held to the PRD as it stands. Keeps its memory in the repo. Made here. Work in progress.

An IDE-style file tree pane with git status that highlights files as Claude reads or edits them. Runs read-only git, find and du plus small helpers. Reviewed: Recommend.

A live agent dashboard pane: model vitals, every permission check, subagent cards and a session log. Observes only. Reviewed: Recommend.

Claude assigns you the tasks only you can do; they wait in a My tasks pane until you answer. Adds system-prompt guidance and sends your answers as prompts. Reviewed: Caution.

Stops secrets from leaking before they are written, printed or committed to git: masks prompts and tool output, holds or blocks commands that contain secrets. Reviewed: Caution.

A rail of your session's prompts beside the transcript or above the prompt; hover to reread one, click to jump to it. Reviewed: Recommend.

One line above the prompt: context, 5-hour and 7-day limits against elapsed time, prompt-cache time left, session cost and running agents. Reviewed: Recommend.

Your plan's 5-hour and 7-day usage as small bars above the prompt, with the reset countdown and the session's cost. Reviewed: Recommend.

A small box above the prompt that always says what Claude is doing right now, and expands to show what it has done. Reviewed: Recommend.

Makes Claude and its agents reply in Chinese (Traditional by default) and asks for a rewrite when a reply comes back in another language. Made here.