All mods
3,658 mods. Every one passed the check.
- jp-display 0.2.0 スピナーや操作ヒントなど Claude Code の英語表示を日本語にする 0
- limit-bars 0.4.0 プロンプトの上に 5時間 / Weekly / Fable の使用率を色付きバーで、横に今のモデルと Effort を常時表示する 0
- usage-forecast 0.1.0 Projects 5h usage at reset and shows it above the prompt. Optional: install only if you want it. 0
- agenda 0.7.0 Toggleable agenda pane: a focus view of the current arc story and Claude's tasks, and an overview of every open todo 0
- sidebar 0.1.0 Shows every live Claude Code session as a card in a side pane: title, status, current tool, git branch, model, context use and a last-turn recap. No tmux or daemon needed; in tmux a card's hotkey jumps to that session's pane 0
- walk-with-me 0.1.0 Band above the prompt showing the walk-with-me mode, with buttons for its commands. 0
- cache-expiry-notifier 0.1.0 Notifies you X minutes before your prompt cache expires so you can send a turn before paying the full re-cache cost. 0
- loopd-mod-pane 3.0.0 COMPANION, a mod. /board opens a pane that draws this bundle's board — in-flight tasks, the need-you rail, per-project counts, the last snapshot time — from .loopd/SNAPSHOT.json in the session's working directory, re-read every 5 s only when its mtime moved. A fourth renderer over the snapshot wr... 0
- nat-embedded 0.0.0 nat's own mod, loaded into every Claude Code session nat launches with --plugin-dir and nowhere else. 0
- gl-issues 0.4.4 Pane listing GitLab/GitHub issues assigned to me, grouped by board status label 0
- presence 0.0.1 Talk with Claude Code through the Avatar app: replies spoken as they are written by a face with lip sync, your voice into the prompt, and a pane with the conversation and its controls. 0
- usage-meter 0.3.0 One line above the prompt: model, effort, context fill and the 5-hour limit 0
- buddy 0.1.2 A panda colleague in a side pane who works along with each task and keeps a short management summary of the session. 0
- cortex-guard 0.1.2 Two rules no settings hook enforces, refused at the tool call: wiki pages and their generated ADR mirrors are written only through the Cortex wiki tool, and every git worktree lives at <repo>/.claude/worktrees/<name>/ (one created there is registered with disk_hygiene.py). 0
- cortex-wiki 0.1.1 /wiki <wiki/**.md>: compile a Cortex wiki page (Markdown with ```tikz blocks) to PDF through pandoc and xelatex, and open it. 0
- zetetic-genius 0.1.1 Grades every request before its turn starts (task class → effort rung, in one low-effort completion) and routes it to the genius reasoning patterns and problem-shaped skills whose trigger it matches, from the installed zetetic-team-subagents index; under enforce, the matched pattern's workflow ri... 0
- zetetic-autopilot 0.1.1 Automatic effort and model: every request runs at the effort its grade calls for (zetetic-genius) and the tool loop steps down the ladder; subagents run on the family their type and the turn's class call for (haiku, sonnet, opus, fable); under quota or context pressure everything goes one notch d... 0
- cortex-cockpit 0.3.1 The harness cockpit, a viewer: Cortex memory health and grooming, the context window against the Stop guard's thresholds (from zetetic-autopilot), the spec-to-code pipeline as observed, worktree and test-process hygiene, the autopilot's and genius router's decisions, and the guard's refusals. /co... 0
- harness-fleet 0.1.1 The owner's interface to the plugin fleet: /fleet shows each owned plugin's installed and offered version, the repository's open PRs with their CI state and its open issues (defects first, feature requests set apart), and the session's harness signals. The mod only reads (gh pr list, gh issue lis... 0
- agent-radar 0.3.1 Alle Claude-Code-Sitzungen und Subagents auf einen Blick, Kaltstart-Wächter gegen teure Cache-Neuaufbauten, Modellwahl-Pflicht für Subagents, Such-Agents auf Haiku. 0
- brain-mods 0.2.1 Kollisionsschutz für parallele Sitzungen, Kontext-Anzeige mit „Stand sichern“ und Brain-Band — 0 Tokens, nur lokal. 0
- wachhalter 0.1.0 /wach hält den Mac per caffeinate wach — ohne Umweg über das Modell, also ohne Tokens. /wach 1 · /wach 30m · /wach aus · /wach 0
- prompt-boost 0.4.2 Analysiert und optimiert Prompts und Agenten-Aufträge passend zum aktiven Modell und macht Subagenten sparsam: Lagebild, schlanke Varianten, Briefing-Gate, Fork-Sperre und Kostenanzeige. 0
- cache-glance 0.1.1 輸入框下方常駐一行提示快取狀態:還有多久過期、過期後重寫要多少錢 0
- task-progress 0.1.0 給 Claude 一個回報工具,把任務清單和進度寫進 cmux 左側欄 0
- auto-panes 0.1.0 每次開 Claude Code 自動打開右側的 Diff 和 Files 面板(Source Control 用 ◨ 手動開) 0
- clean-view 0.3.1 A calm, friendly view: hides tool calls, diffs and command output from the transcript. 0
- pinboard 0.2.4 Keeps open decisions, the task list and links Claude creates in a sidebar pane, updated through its own tool 0
- buffer-pane 0.2.4 A pane beside the transcript that holds the next things to tell the agent: write blocks of text while a turn runs, then press [+] to put one block into the prompt box. 0
- flightdeck 0.3.4 Flightdeck: a live agent dashboard for Claude Code. Main model vitals, an on-call architect, every permission check, subagent cards and swimlanes, a turn receipt and a session log, all from real session events 0