Prompt
353 mods. Bands above the prompt and tools that rewrite what you send.
- next-steps 1.3.1 After each Claude Code reply, suggests up to 3 next steps as one-click buttons above the prompt. A Claude Code mod. 1
- redact 0.1.0 Redacts secrets and PII from every row Claude Code stores, before the model reads it and before the transcript keeps it. Reach L0: no network, no processes, no files. 1
- subagent-models 0.1.0 Shows each running subagent's model and effort on the hint line above the agent list 1
- codex 0.4.5 OpenAI Codex as native Claude Code subagents: the Agent tool starts one and the mod drives codex app-server in its place, no model in between 1
- auto-handoff 0.2.0 Hands the work to a fresh, named session when the context gets too full, using your /handoff command 1
- handoff-pickup 0.1.1 Reminds you of a handoff you left behind, picks it up with /pickup, and deletes it when you're done 1
- slayer-corps 0.2.0 Tanjiro, Nezuko, Zenitsu, and Inosuke take turns against demons up to Muzan as you and Claude work, and spar between strikes. The story continues every session. 1
- night-feast 0.4.0 A vampire feeds on every tool call Claude finishes while the moon tracks how full the context window is. Between meals it stalks, swoops, and lies in wait. Dawn means it is time to compact. 1
- pocket-familiar 0.4.0 A fox spirit that lives on your work: passing tests feed it, finished turns cheer it, it plays while you are quiet, and it grows up to nine tails. 1
- cc-pokedex 0.1.0 Catch wild creatures above the Claude Code prompt: where your prompt leads (water, grass, fire, bugs, plans, builds) decides what appears. Pick a partner that draws under the logo, beside the spinner and above the prompt, and levels up and evolves as Claude works. Needs function hooks (early acce... 1
- oyen 0.1.0 An orange cat above the prompt that reacts to your commits, tests and builds 1
- quality 1.0.16 mod + skill Tools for reviewing code quality 1
- pdpa-thai 0.3.0 Helps reduce personal data sent to Claude: redacts detected Thai and international personal data before sending and masks it on screen. Detection runs locally and the mod makes no network calls of its own; the redacted conversation is still sent to your configured model provider (Anthropic by def... 1
- time-budget 0.1.0 Enforces a time budget per unit of work: the first tool call of a unit must be the estimate, every tool waits on a report at 1/3, 1/2, 2/3 and 5/6 of the calibrated budget, and a projected overrun denies every tool but the report, then aborts the main turn after a grace period. 1
- ctx-strip 1.1.0 컨텍스트가 무엇으로 차 있는지 입력창 위 막대로 보여주고, 서브에이전트가 돌면 한 줄로 알려줘요 1
- clawd-buddy 0.4.2 Animated pixel mascot Clawd above the prompt: reacts to Claude's work, waiting times, idle time, time of day, the mouse and a mood that builds up over the session. 1
- quick-replies 0.2.1 Claude Code's own next-message suggestion as a button above Clawd; click it or type 1 in the empty prompt to send it. With /replies more on, up to three more suggestions from a fork of the session. 1
- done-alarm 1.0.0 긴 작업을 맡기고 자리를 비워도 끝나거나 확인이 필요할 때 데스크톱·음성·휴대폰 푸시로 알려줘요 1
- streamer-mode 1.0.0 유튜브·라이브 방송, 화면 공유 회의, 페어 프로그래밍 중에 화면에서만 비밀 키·주민번호·전화번호·이메일 같은 민감한 값을 가려요. 화면만 바꿀 뿐, Claude가 읽는 내용과 저장되는 대화 기록은 그대로예요. 1
- block-creds 0.3.0 Redacts or blocks credentials (detected by betterleaks) before they are sent to the LLM 0
- wt-pack mod + skill wt-pack: every wt-* skill for running herdr agents on a ticket pipeline, plus wt-memory's hooks (preferences, pkill guard) and MCP server, and the wt MCP server (typed ticket, handoff, room and ask tools). The dashboard, board and rooms need the full ./setup. 0
- wake 0.1.0 Wakes an idle session when a watched PR, CI run, Eve review, devbox, vitrinka task or deployik deploy reaches the state it asked for — one shared poller (vybava watch) instead of per-session sleep loops. 0
- model-router Routes each turn and subagent to a model tier and reasoning effort using a classifier behind any server that speaks POST /v1/classify (model-router-api on Cloudflare Workers AI today), falling back to the engine's built-in classifier. 0
- ultimate-hud 0.2.0 Emoji HUD above the prompt: model, repo, branch, context, tokens in/out, cache hit/write %, cost and rate limits 0
- ai 0.14.1 mod + skill Multi-agent loop for Claude Code: Fable/Opus plans, Codex challenges, Opus builds (effort medium), cheap OpenCode models (free ones first) do the rote parts, Opus verifies at effort high, Codex QAs — with limit-aware fallbacks. Plus /ai:ship, /ai:test-audit and /ai:preship (checkers, or read-only... 0
- cn-converter 1.0.5 Convert Simplified Chinese prompts to Taiwan Traditional Chinese before sending, and render Claude replies as Mainland Simplified Chinese. Self-contained; no Node runtime dependency. 0
- resume-on-stop 0.1.0 Unexpected stops: when a turn ends right after saying it will act, the decision model spots it and one turn resumes the work. 0
- resource-committee 0.2.0 The Resource Committee assigns every turn its model and effort: sonnet/medium by default, opus/high for judgment, sonnet/low for mechanical work — decided once per prompt so the cache survives. 0
- pr-pane 0.2.0 Toggle your open GitHub PRs above the prompt; focus with Ctrl+X then Tab, then use arrows and Enter to open one in the browser. 0
- prompt-hint-trim 0.1.0 Drops the shell count and the agents shortcut hint from the prompt footer 0