Claude Code Mods

melandres8/claude-mods

Relay between two local sessions: one plans, the other builds, and they hand work back and forth on their own.

34823/remind-pane

Reminders in a Claude Code pane: checkboxes, delete, an add field, a small stdlib-only CLI; optional delivery to Telegram

im-ksc/ks-claude-code-mods

Replay Theater: step through the file edits Claude made in the last turn, one diff at a time.

kevinfactor/claude-kit

After Claude edits files, a Replay button steps through each edit as a before/after diff. No model calls; the last 60 edits are kept across sessions.

navin0812/claude-mods

Records every Edit/Write in a turn, then steps through them one diff at a time in a pane (/replay).

TLOBillyQ/claude-mods

Records the last turn's Edit and Write calls and steps through them one diff at a time with /replay.

yahyashareef48/claude-mods

Replay Theater: a live timeline of everything Claude does in a turn (commands, reads, searches, edits) with diffs and output.

smhasan-yad/claude-mod-replay-theater-ps

Step through every file change of the last turn, one diff at a time: Edit/Write edits plus files changed by PowerShell and Bash commands. Based on Anthropic's Replay Theater sample (Apache-2.0).

PRANAY-CHAPLOT/replaycast

Podcast-style listening for Claude replies: a Listen button under each reply and a now-playing bar with seek, sentence skip, 1x-4x speed and voice choice. Fully offline.

krishna-goutham-tls/cc-mods

Highlight part of Claude's answer and reply to it. The text goes into your prompt as a quote.

korenl137/reply-comment

Quote parts of Claude's reply into your prompt with a comment: /quote opens a pane with the last reply split into paragraphs.

LegendSilvia/claude-code-mods

Sets Claude's replies apart in the transcript: a rainbow edge, a violet tint, and bold text and headings in a rainbow

soonavi/claude-mods

Ends each reply with one status line: context fill, usage windows and their resets, each repo's unpushed work, and what the turn did. For sessions watched in an app that draws no status lines.

johnlewczuk/claude-mods

Adds the reply's time to the turn line when Claude Code leaves it off (while background agents run)

J-M-Pineapple-Express/repo-radar

A live GitHub dashboard for every repo across every account you're signed into. It installs an always-on-top desktop widget for you on first run.

rabanderlipe/claude-code-mods

Live map of the repo that lights up as Claude and its subagents read, edit and fail on files

debba/claude-mods

Commits changes to the claude-mods repository it lives in and offers a one-click push (opt-in per clone)

yahyashareef48/claude-mods

A git dashboard: repos in the chat's folder are watched on their own, every other repo on the computer is listed to add. Worktrees, branches, ahead/behind, changes, pull/push/sync, refreshed every minute.

timothylok/ClaudeCodeModsByTimLok

Spots research prompts and keeps them out of the main context: sends them to your own research endpoint (e.g. a NotebookLM bridge) if configured, otherwise makes Claude delegate to a cheap subagent.

tartinerlabs/claude-code-mods

Shows which Claude Code session is using each booted Apple simulator, Claude Design project and the Xcode app, above the prompt, and when another session already holds one this session picks up, toasts, messages that session and tells this session's agent.

Alexander-Prime/revdiff-relay

Annotate diffs in a floating Zellij revdiff pane; each flush is relayed into your Claude Code session

oakoss/claude-plugins

Automated multi-agent code review cycle that spawns reviewers in parallel (plus Codex when available), applies fixes per CLAUDE.md policy, admits a commit only when a reviewer saw exactly what it records, and asks before a push, pull request, merge or release you did not request, unless you let it go further.

ccdwyer/review-ghost

Attaches a file's unresolved GitHub PR review threads to the model's Read and Edit results, so review comments get fixed in the file it is already touching

ipartington/claude-mods

Keeps review findings (H1, M3, L2...) per repo across sessions and ticks them off when their PR merges

ramtinJ95/claude-mods

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

rudrasecure/claude-mods

Side pane showing the files changed in this conversation as diffs; mark lines, comment, and send the comments back to Claude

thorstenalpers/claude-code-mods

A live line above the prompt for each running code review: Codex or a review subagent, its model, what it reviews, time, and Codex's latest output. A toast with the findings when it ends.

LilianMLG/revo-flow

/revo-flow <demande> : l'orchestrateur lit les specs, fait un plan, répartit les tâches entre des sous-agents (modèle et effort choisis pour chacun) et affiche une barre de progression par agent dans le panneau latéral ; un cache par projet (graphe des fichiers et fiches de features apprises en fin de flow) lui évite de relire le code : /revo-flow cache. Un agent peut en attendre un autre (relancé quand il a fini) et reçoit l'extrait de fiche qui le concerne, qu'il vérifie et rafraîchit. Un flow vérifié : revo-flow apprend les commandes de vérification du projet (lint, typage, tests ciblés), les lance lui-même en fin de flow et refuse de le déclarer terminé tant qu'elles sont rouges (erreurs nouvelles seulement, base de référence prise pendant la planification) ; critères d'acceptation, vérificateur indépendant et tests gelés en option. Le score CRAP (complexité × couverture des tests liés) fait respecter la règle du scout : une fonction modifiée par le flow au-delà de 30 bloque la porte, une fonction ancienne qu'il ne touche pas jamais. Les agents installés sur votre Claude Code (projet, dossier personnel, plugins activés) sont proposés à l'orchestrateur : un sous-agent peut en prendre le type, avec son modèle et son effort. /revo-flow doctor montre ce que le mod a détecté sur le projet (stack, commandes de vérification, base de référence, cache, agents installés) et ce qu'il y fera ; un flow interrompu par un redémarrage peut être repris ou abandonné ; chaque flow laisse un rapport en markdown (plan, fichiers, verdict de la porte, critères, CRAP, coût). Preuve web : sur un critère observable, le vérificateur demande le serveur de dev, revo-flow le démarre sur votre accord et lui donne l'URL ; il navigue (console, réseau, capture par critère), les captures vont dans le rapport, le serveur est arrêté en fin de flow.

higorcesarqn/rich-input-editor

Warp-style Rich Input for Claude Code: the prompt box as a multi-line editor you switch on and off (Enter for a new line, Ctrl+Enter to send), an editor pane for mouse-capable terminals, and @ completion that browses folder by folder

ChiFungHillmanChan/ringside

Ringside: a ringside seat on every Claude Code session on your computer and what each one started (subagents, background shells, loops), what needs you or may be stuck, a Peek on any of them with Jump there, a task checklist and an agent launcher. Formerly Agent Map.

beerbox/rmod

Local LLM monitor: shows whether Ollama and LM Studio are listening, counts this session's local requests, and lists local models.

minjun0219/rocky

rocky — the owner's personal agent toolkit. Run many agent sessions from one machine: hand work out (board, handoffs, spawn), bring results back to merge (PR watch, default-branch verify, review-fix), watch and steer from anywhere (web UI, remote control, statusline), and record it all (worklog, token and usage logs). A Rust daemon (127.0.0.1:8636: board REST + streamable HTTP MCP todo_* / note_* / token_*, web UI) and CLI; this plugin is its thin Claude Code client. worklog_* is served per project by the CLI's stdio MCP server (`rocky mcp worklog`). Hooks: SessionStart boots the daemon and adds a short board summary plus worklog memory recorded in this work path (last recall digest, later decisions and blockers; off with worklog.sessionBrief), UserPromptSubmit injects human board changes, PostToolUse attributes a self-started doing to the session, Stop claims handoffs and auto-captures the turn. A function-hooks module (hooks/board-panel) shows this folder's board in a session pane (/rocky-board). Slash commands, skills and subagents (reviewer, quick-fix, merge-cleanup) cover picking work, PR flow from gate to merge, setup and usage review.

vinkdc/roclaude

Roblox Studio safety layer for Claude Code (Studio MCP): RemoteEvent security audit, undo, Team Create protection, a confirmation before destructive Luau, and a live activity view that replays every change.

s4duq/roco

Pixel-art mascot that reacts live to what Claude does. Pick one of 8, recolor it or create your own with /roco:crear. Mascota pixel art para Claude Code.

dim-owl/roll-call

Shows which other Claude Code sessions on this machine are waiting for you, and what they are working on.

4DvAnCeBoY/rook-claude-plugin

rook by TestMu AI inside Claude Code: Claude runs rook against the agent it is building and gets failures back grouped into root-cause clusters with rook's remedies, writes scenarios, a live pane with per-scenario lanes and openable failures, re-test prompts after agent edits, a status line score, /rook commands and a production-target guard.

DJPalefaceSD/rostech-mods

A Dashboard button above the prompt that opens a panel you fill yourself: effort, helper model, launch buttons and a status row. Fully customisable: just ask your Claude to put what you want in it.

DJPalefaceSD/rostech-mods

Keeps the notes that matter in the glovebox, and hands them back to Claude after it compacts its memory. Text notes only: never video, never the screen, never your location. Sends nothing anywhere.

joaofatoretto/round-changes

Review what each round changed: the files Claude touched, their diffs (shell commands included), and one key to open a change in VS Code.

HarzerHeribert/claude-modpack

Optional, and the one mod that needs an outside classifier model: hands feature and test work to delegate's cheaper worker. A fast classifier (TypeSafe's Jev or ScaleDown, with your API key) reads your prompt, and only where it is feature or test work does Claude get the order to implement it through a hand-off. Off until you turn it on and give it a key for one of them.

seanyyoo/claude-code-mods

Your scheduled routines at a glance from a Notion database: today's haul by source, the last 7 days, sources that went quiet and next runs

blackmath88/routing-mod-claude

Routes each subagent to Haiku, Sonnet or Opus by the [tier:...] tag from your plan. The main session never switches model, so its prompt cache stays intact.

AliakbarNateghi/cc-rtl

Draws Persian/Arabic text in Claude's replies joined and in right-to-left order on terminals that do no bidi or shaping. Terminal only; the transcript is untouched. Toggle with /rtl on|off.

barmoshe/bar-mods

Right-to-left for Claude Code mods: one file to copy into a mod that orders Hebrew and Arabic right on every surface, aligns wrapped text right, draws markdown, cards, tabs, tables and SVG headers, and reorders text for the terminal

itaym967/rtl-questions

Shows Claude's questions, and plans awaiting approval, right-to-left (Hebrew/Arabic) in the desktop app

ruah-dev/ruah-map

See the architecture of any repo, code and cloud, right inside Claude Code. /ruah:map scans packages, imports, Terraform, Kubernetes, Compose, Cloudflare, Vercel and CI, then opens a live map above the prompt.

davidparys/claude-mods

When you correct Claude, a band above the prompt offers to save the correction as a permanent rule in CLAUDE.md or a skill.

lunatictaco/claude-mods

A pane and toasts for background shells, monitors and subagents: status, elapsed time, latest output line, exit code