Claude Code Mods

robinade/claude-mods-ko

대충 쓴 초안을 프로젝트의 CLAUDE.md와 설치된 스킬을 바탕으로 구체적인 프롬프트로 다시 써 줘요. 한국어 초안은 한국어로 다듬어요.

thinhkhuat/prompt-enhancer

A band above the prompt that rewrites your rough draft in place: your intent and your own words, the kind of work, and the finished result, as short as the request.

cosmin220304/claude-mods

Folder, branch, PR, context and model at the end of the prompt hint line

Kiko-42/claude-code-hist

Lists the prompts you typed this session, newest first; pick one to jump the transcript there (/hist)

nickhealthy/claude-code-prompt-jump

Jump back to any prompt you typed in a Claude Code session with /jump: newest first, search by words or number, works after --resume.

ruanss4/prompt-jump

A bar above the prompt input with a tick for every prompt of the session; hover to read one, click to jump to it

tmokmss/claude-mods

Jump the transcript to your own prompts with ctrl+up / ctrl+down (option+up / option+down on macOS)

JunSeo99/prompt-ladder

Claude does what you ask, so ask well. Press ctrl+q on a rough draft and prompt-ladder writes a well-built prompt from your session's own context, at the cost you pick: quick, balanced or deep.

sairam0424/claude-prompt-lift

Enhance your prompts using project instructions and skills

ssc327/prompt-nav

Shows your last prompt above the input and lets you jump between your own prompts

bai-collab/claude_code_mod

Attaches hidden clarify-or-proceed guidance to short or vague prompts

1cookstar2-web/prompt-polish

Claude Opus 5.5 fixes the spelling, punctuation and grammar of each prompt you type, then makes it clear and direct for Claude Code, before Claude sees it

humzahkiani/prompt-polish

For Claude Code: a band above the prompt that rewrites your draft before you send it, so you review, retry or reject the rewrite in place

Sor85/prompt-prune

删除 Claude Code 指定的安全、代词和环境模板，保留仅提交的署名提醒，移除 Bash 描述中的默认分支自动建分支要求。

tomikng/prompt-quest

An RPG layer for Claude Code: earn XP from sharp prompts and lean token use, spend skill points on perks, and learn AI lore.

Demo-0416/claude-code-mods

Codex-style queued follow-up inputs: the queue key while a turn runs holds the prompt until the turn ends, one per turn; alt+↑ edits the last one; an interrupt puts them back in the composer

florian-anthony/claude-code-mods

Keeps the prompts you send while Claude works in a queue, and sends them one by one once Claude has finished. Edit, reorder or remove any of them.

PulseRH/claude-prompt-queue

Queue prompts in a card grid above the input and send each later with a button, or auto-send them after each reply with a visible countdown

ezoushen/claude-mods

Replaces secrets and credentials with stable placeholders inside Claude Code before the model or the session file ever sees them — prompts, tool results and replies, plus attachments and compaction summaries where the platform lets this mod see them — and restores real values only in Edit/Write/NotebookEdit arguments. 220-rule corpus plus checksum detectors, a benign-shape allowlist, fail-closed scanning, a /redact pane and a redacted-values skill. No network, no subprocess, no model call.

anhtuan23004/claude-mod

Rewrites short, casual prompts with a fast model into Context / Objective / Steps / Output / Constraints, then lets you send the shaped or the original version

gonzaloserrano/cc-prompt-stash

/stash: a git-stash-like stack of prompts, kept between sessions, popped back into the prompt box.

heidiks/agent-kit

Keeps every stashed prompt draft in a list you can recall, remove or clear, without sending it

samaphp/prompt-stash

Stash a thought from the prompt box with ;; and bring it back in a later turn

Vibe-Commit/claude-context-mods

Prefixes every prompt you type with the local date and time, visible to you and Claude.

niijoey/prompter-mod

Talk through what you want, get the right terms and a clean brief for Claude, with this repo's context filled in.

jessetsai1024/claude-prompts

側邊欄的「我問過的」：主人這次對話打過的每一句話，點一下看全文、複製、放回輸入框。/prompts 開或關

Brrgg/ppd

GitHub-style heatmap of prompts sent per day, opened by an arrow beside the prompt.

PromptSign/promptsign-plugin

Verifies signatures on the instruction files Claude Code loads, meaning CLAUDE.md, skills, and agent definitions, before they reach model context. It re-checks a skill bundle before the Skill tool runs it. Sigstore keyless, offline verification against a pinned trust root, no telemetry.

Mar5929/claude-toolkit

Required workflow checks with Claude Code function hooks. Refuses a knowledge-file write, or a memory-service save in external memory mode, until knowledge-save is open, refuses hand edits to generated indexes, refuses a pull request, close or merge until knowledge-save (and the work or merge-and-clean-up skill) is open, and holds a final reply once when working memory or the index rebuild and checker did not follow the change. Fact checks only: no model call and no reading of the agent's words. Runs only when CLAUDE_CODE_ENABLE_FUNCTION_HOOKS=1.

ambareeshav/prs

Browse and review Azure DevOps pull requests from inside Claude Code via /prs

fran343/claude-mods

Con /playwright, lee el manifest y el contexto del desarrollo y genera y ejecuta pruebas Playwright en la sandbox de Salesforce.

chenyao0910/claude-ptt-mod

在 Claude Code 面板裡滑 PTT,可自訂看板,附老闆鍵

seanyyoo/claude-code-mods

Stops Claude from typing private terms into the browser or writing them into your publishing files, and keeps a log of what it blocked

its-coughfee/pulse-file-tree

Sidebar file tree that opens files in their default app and pulses a Claude mark on files edited in the latest turn

yasirshabbirservices/claude-mods

A slim glowing bar above the prompt that shows what Claude is doing: breathing when idle, a wave while thinking, a flow in the tool's colour while a tool runs, a green sweep when done, a red pulse on an error; /pulse and /pulse off

MrValraven/pulse-mods

Keeps the one-hour prompt cache warm during /keepwarm windows and holds a cold send once with its estimated rewrite cost. Pinging runs only after /keepwarm. Fork of karanb192/cache-tax.

im-adarsh/claude-mods

One officer and a traffic light above the prompt, nothing else — napping idle, alert waiting on you, working, done

MrValraven/pulse-mods

claude-reflect as a Claude Code mod: a model check on each short prompt finds reusable corrections (any language); a band above the prompt saves them to CLAUDE.md on one press

Eiyuo/Claude-Mods

Jauge, progression de Claude et des sous-agents, cap, relais et plume, au-dessus de la zone de texte.

jpoucabanillas-lang/claude-mods

/purgar: quita del contexto las salidas viejas de herramientas, sin resumen y sin gastar modelo; /purgar N deja solo los últimos N intercambios

kk5190/claude-code-mods

Blocks git push and gh pr create until you confirm the commits, their authors and the diff size, with a side pane of the last check

Risdon8/push-ups

Predicts how long Claude's turn will take and gives you push-ups to do while you wait, in a bar above the prompt. Local only: no model calls, no tokens.

geonhos/claude-code-mod

An animated pixel-art pyramid construction site in a side pane: the harness conductor cracks the whip, workers carry bricks, every report adds one.

AnatoliyShk/claude-qa-history

Keeps your questions, answers and follow-up Q&A in a side pane; /qa-testme quizzes you on all of it

cziorvis-commits/qa-only

Prompts that start with question / Q / q get an answer only: no plans, no edits. A ? pill shows when it is on.

imsungbin/quackpit-mod

A cockpit above your Claude Code prompt. The duck reads the gauges: task progress and how long the work will take, pace, context, plan limits, checks and cost in one instrument panel, with a rubber duck as Master Caution. Zero model tokens by default, no network, no processes, nothing added to context.

nu0ma/query-guard

Asks before Claude runs destructive or slow-looking SQL through a DB CLI: DELETE, UPDATE without WHERE, DROP, TRUNCATE, full scans and cartesian joins.

michelr/dotclaude

Draws BigQuery MCP, dbt MCP, bq query and dbt show results as an aligned, colored table