All mods
4,078 mods. Every one passed the check.
- pupitre 1.0.12 Jauge, progression de Claude et des sous-agents, cap, relais et plume, au-dessus de la zone de texte. 0
- delegator 0.1.0 Every subagent Claude starts waits for your approval: approve, refuse, approve all for the turn, change its model (suggested by the task's complexity) or add a note to its task. A pane lists the agents waiting, the full task and recent decisions, the same in the terminal and the desktop app. 0
- model-badge 0.1.0 Shows the model in use above the prompt, colored by family: Sonnet in blues, Opus and the latest model in reds. 0
- usage-guard 0.1.0 Asks before a large or token-heavy prompt is sent, showing your 5-hour and weekly usage and an estimate of what it may cost 0
- dungeon-master 3.8.0 Run Claude Code like a D&D table: a DM screen of pixel heroes for every helper Claude sends out, a strip with your character, a rolling d20, a Realm Map to manage your sessions, levels, achievements and ten D&D themes in light and dark. No tokens used. 0
- blast-radius 0.1.0 Holds risky Bash commands (rm -r, force push, reset --hard, clean, find -delete, drop/truncate), shows what they would affect, and waits for Proceed or Cancel. 0
- cache-tax 0.1.0 Holds a prompt once when the prompt cache has gone cold and shows the estimated re-write cost; /keepwarm pings the cache. 0
- filetree 0.1.0 Project file tree in a pane: files Claude reads or edits shimmer, committed ones turn green, uncommitted changes are marked. Toggle with /filetree. 0
- handoff 0.1.0 Hands a long session over to a fresh one before context runs out: watches the context fill, offers to write HANDOFF.md from the session's own transcript, and loads it into the next session. 0
- reflect 0.1.0 Turns your corrections into saved rules: spots a stated preference in your prompt and offers to save it to CLAUDE.md from a band above the prompt. 0
- replay-theater 0.1.0 /replay steps through every file edit Claude made in the last turn, one colored diff at a time. 0
- savvy-progress 0.1.0 Live panel and progress band for subagents: model, context fill, tokens, estimated cost and time. Toggle with /agents-info. 0
- skins 0.1.0 Switch colour skins live with /skin <name>: tool rows with icon, name, argument summary and duration, edits as diff cards, a styled spinner. 0
- you-should-know 0.1.0 A second agent on the side reads what Claude just did and flags anything you might miss, as a note above the prompt. Toggle with /should-know. 0
- producer-tag 0.1.0 Plays an anime-voice producer tag (「マスター!確認してください」, 'Master! Please check this.') when Claude finishes or needs your approval. 0
- usage-forecast 0.1.0 A live forecast of your context window, plus your session and weekly usage limits, in the band above the prompt. 0
- deviation-kernel 0.1.0 Holds a project's refused assumptions in Claude's system prompt, flags edits and answers that re-impose them, and pauses on the step where it happens 0
- cache-meter 0.1.0 Shows above the prompt how warm the prompt cache is, what a cache miss would cost to rewrite, context fill, and the session's API-rate cost 0
- goal-board 0.1.0 Each session's goal, task progress and ETA above the prompt, and a /goals board of every running session on this machine 0
- file-tree 0.1.0 A file tree of the working directory in a pane beside the transcript, with folders you open and close and the files Claude just changed marked 0
- close-worktree 0.1.0 After a PR is opened from a git worktree, tells Claude if the worktree can be closed (clean and pushed) or what is still not saved. 0
- drawio-viewer 0.1.0 Anteprima dei diagrammi draw.io nel pannello, aggiornata quando Claude o tu li modificate 0
- review-pane 0.3.0 Review the working diff in Neovim beside Claude Code, or the last response in a pane: annotate lines, ask questions inline and prepare a follow-up prompt 0
- md-preview 0.1.0 Preview a markdown file in a pane: /md-preview lists the markdown files edited in this session, and Claude can show one itself. 0
- agent-board 0.7.0 이 세션의 서브에이전트(모델 포함), 스킬, MCP, 백그라운드 작업 현황을 한 패널에 보여줍니다. 세션을 열면 자동으로 열리고, /agent-board로 열고 닫습니다. 0
- auto-model 0.1.1 프롬프트의 작업 종류(키워드)에 따라 메인 세션 요청의 모델을 Haiku/Sonnet/Opus로 고릅니다. 기본 꺼짐, /auto-model on|off|status. /model로 직접 고르면 그 세션은 자동 선택을 멈춥니다. 0
- secret-guard 0.1.0 Oscura i segreti (token, chiavi, password) nei risultati degli strumenti prima che Claude li legga 0
- command-deck 0.2.0 Da fare: quello che ti resta da fare dopo le risposte di Claude, con i comandi da copiare e quelli negati dai permessi 0
- checks 0.2.0 Verifiche: i test veloci a fine risposta e la CI su GitHub, in un pannello e nella riga di stato 0
- work-diary 0.1.0 Diario e calendario del lavoro fatto con Claude: settimana, mese e giornata, con i riassunti 0