All Claude Code mods/Browse

Claude Code mods starting with A

314 mods. Each name opens the mod’s page with its hooks, API calls, access and install hint. See what a Claude Code mod can access.

• a11y-guardPlagemes/claude-modsL1 Reads

  Flags accessibility misses as Claude writes UI: images without alt, unlabeled buttons, clickable divs.

• a2a-modNovusEdge/a2a-modL3 Uses the network

  A2A protocol client for Claude Code: Claude hands tasks to non-Claude worker agents over Agent2Agent and picks up their results.

• abo-usagetw67/claude-modsL2 Writes or runs

  Zeigt die Nutzung des Claude-Abos live als farbige Balken über dem Eingabefeld, mit Reset-Zeit, sowie die Higgsfield-Credits

• absolutely-notJvrd97/claude-absolutely-notL1 Reads

  Stop "You're absolutely right!": a tone rule in the system prompt, praise openers stripped from what the model reads back, and /tics to count the ones that sti…

• acabei-de-baixarplasdigital/mods-claude-code-kit-alunoL1 Reads

  Quando o pedido fala em baixar/gerar um arquivo, anexa os arquivos novos de Downloads ao pedido, com caminho completo

• account-badgeAmnesiac9/claude-modsL1 Reads

  Signed-in org abbreviation in the prompt footer

• account-swaptrongtaiz/account-swapL2 Writes or runs

  Switch between saved Claude accounts from inside Claude Code, and auto-swap before the active one hits its rate limit.

• account-switchersam-ruff/account-switcher-claude-code-modL3 Uses the network

  Mod: run each Claude Code session on its own Claude subscription account, and switch live from a sidebar (Ctrl+Alt+Shift+numpad -) or /account-switch

• achievementvincentlauriat/ModsToolsL0 Draws & remembers

  Playful badges unlocked once ever from real events (tool calls, turns, subagents, tests, git); /achievements lists them

• achievementsPlagemes/claude-modsL1 Reads

  Unlock achievements as you work: first commit, 100 green test runs, a week-long streak and more.

• achievementsbaselane-sh/modsL1 Reads

  Unlocks eight badges once each (first session, first green test run, 100 and 1,000 tool calls, 7-day streak, 10 blocked calls, a 2 hour session, night owl), wi…

• achievementsmako-code/gobworksL1 Reads

  A little game layer: 32 achievements for how you use Claude Code, with lifetime progress and a /achievements pane.

• acp-uihuydepzai121/claude-acp-uiL2 Writes or runs

  Restyles the Claude Code terminal like an ACP chat: prompt and tool cards, inline diffs, a status band, footer stats, a /dash pane and a done toast

• act-now-guardUtakataKyosui/utakata-cc-modL3 Uses the network

  計画フェーズの要らない依頼で EnterPlanMode や Plan エージェントに入ろうとしたら止め、すぐ実装に着手させる function hook

• action-inboxsamuelnyamukapa/claude-code-action-inboxL2 Writes or runs

  A cross-session inbox of the decisions and manual actions you owe, grouped by project and session, with replies routed back to the owning session.

• action-pinKilimcininKorOglu/claude-code-modsL3 Uses the network

  After an edit that adds a GitHub Actions step pinned to a tag or a branch, names the commit SHA to write instead, from the GitHub API.

• active-time0xGondarxyz/claude-code-modsL2 Writes or runs

  Counts the time you really spend with Claude Code (typing and Claude working, not an idle terminal) and shows it in the status line and /claude-time.

• activitygveshk/barebone-modsL2 Writes or runs

  A live crew panel: every agent, its model, effort, tokens and estimated cost, with a friendly pixel crab.

• activitymishgoldenberg/claude-modsL1 Reads

  Live panel of what Claude is doing: running tools with real commands and timers, what is waiting for your approval, subagents, and its current todo plan.

• activity-heatmapPlagemes/claude-modsL1 Reads

  A heat map of when you use Claude Code, by hour and weekday.

• activity-logdiegorv/claude-mods-diegorvL2 Writes or runs

  Every event of the session, tool calls and their full results included, appended to a JSONL file per session

• activity-widgetoMaN-Rod/claude-code-widgetsL1 Reads

  The most recent tool calls with how long each took and whether it failed.

• ad-ldapseanGSISG/ad-ldap-pluginL1 Reads

  Active Directory administration over LDAPS for Claude Code: an MCP server (FastMCP + ldap3) with 15 tools, admin agents, slash commands, a safety skill, and a…

• adaflow-governanceAdalink-ai/ada-modsL3 Uses the network

  Trilha de auditoria do Claude Code no Adaflow: /adaflow login (device flow) e envio em lote so de metadados (sessao, turno, ferramenta negada)

• adaflow-guardAdalink-ai/ada-modsL1 Reads

  Guardrail para apps integrados ao Adaflow: impede vazar o app token (x-ada-token) para o browser, para o codigo-fonte ou para o transcript

• add-to-chatFunJim/claude-code-add-to-chatL1 Reads

  Select text in the fullscreen transcript and attach it, with an optional comment, to your next prompt

• adlib-lyricsbixxter/adlib-lyricsL3 Uses the network

  Synced lyrics of what's playing in Music or Spotify, word by word, above the prompt

• advanced-rust-cliUtakataKyosui/utakata-cc-modL2 Writes or runs

  Rustで実装された基礎的なコマンドの改善版のみを常に使用するように挙動を変更するMod

• adversarial-review-loopleinardi/adversarial-review-loopL2 Writes or runs

  Implement an agreed plan with an enforced adversarial review loop: every phase commit is gated on an external review.

• aeo-auditjbauman-26/aeo-audit-modL3 Uses the network

  Audits a URL for AI answer engines (ChatGPT search, Perplexity, Google AI Overviews, Copilot, Claude): crawler access, firewall, indexing directives, no-JS con…

• afferentMark-Hickey/claude-nineL2 Writes or runs

  Senses upstream change: keeps ~/projects current, flags rule, tool and branch drift, and leaves the acting to but, chezmoi and the SOPs

• afkCamdenBopp/claude-afkL2 Writes or runs

  Spoken and iMessage pings when Claude finishes a turn or needs you. Turns itself on when you reply from your phone.

• afkswitchaugbastos/afkswitchL2 Writes or runs

  AFKSwitch by augbastos: Tell your agents when you're away and when you're back.

• aftermidudev/after-for-claude-codeL2 Writes or runs

  A real prompt queue for Claude Code: /after <task> runs it after the current task, without steering. See, reorder and remove queued tasks from a band and a liv…

• agendadjbrandl/claude-modsL2 Writes or runs

  Pane of open questions, items Claude left undone, and a cross-session scratch pad; answer, dismiss or fire off each one.

• agent-aquariumnogu66/claude-codeL1 Reads

  A Claude Mod (function-hooks plugin): /aquarium draws the session as a fish tank in a pane with kitty graphics: the main loop is the parent fish, each subagent…

• agent-autopilotapolenkov/agent-autopilotL2 Writes or runs

  Answers AskUserQuestion polls for you only when the assistant marked one option (Recommended) and nothing looks irreversible; default is a hint.

• agent-boardMasterZul/claude-agent-mod-progressL1 Reads

  Live pane showing each subagent's progress, tokens, tools and time, with role-based pixel crabs

• agent-boardOualid0/claude-modsL1 Reads

  A row above the prompt for the subagents Claude starts: running and done per model, a token bar, and a working pixel crew

• agent-boardwhyashthakker/awesome-claude-code-modsL0 Draws & remembers

  Inspect the subagents reported by the session.

• agent-bridgerennerdo30/agent-bridgeL3 Uses the network

  Talk to OpenAI Codex from Claude Code: live peer messaging over a local pipe, plus headless delegation (ask_codex).

• agent-busazoof-ahmed/claude-modsL2 Writes or runs

  A message bus between agent sessions: mail is served between tool calls, a Monitor wakes an idle agent, urgent mail can be typed into Orca terminals, a /bus ch…

• agent-cardkavidu-hettiarachchi/claude-code-modL2 Writes or runs

  Styled Agent Card workflow with live lifecycle, task, worker and gate UI

• agent-catsanthonyzng/agent-catsL2 Writes or runs

  A dashboard of the session's agents as coloured cats: their tasks, skills and run time, their questions answered in place with a meow, and the skills each task…

• agent-charterboxiaolanya2008/claudecode-plus-modUnknown access

  Pin an agent charter into the system prompt: skills-first workflow, per-language comment standards, commit format and branch discipline.

• agent-chatAhmedNazihX/claude-modsL1 Reads

  A side pane with the conversation between Claude and its subagents: what each was asked and what it sent back

• agent-ClaudeRoutervisualife/ClaudeRouterL3 Uses the network

  Picks the model and effort per request, and shows a live band above the prompt: routing, running agents, skills, MCP, context and plan usage, plus a /ClaudeRou…

• agent-cockpitdgsantana/claude-modsUnknown access

  The instruments around each Claude Code session: themed status line, TTSR and layered rules, AGENTS.md and APPEND_SYSTEM, an edit advisor

• agent-coloursMadAppGang/magus-alphaL1 Reads

  Colours subagent and skill names in Claude Code by their own color: field. An agent's name sits on a coloured badge in its Agent row and in replies; a skill's…

• agent-compact-advisorapolenkov/agent-compact-advisorL3 Uses the network

  Status line score 0-100 for how good a moment it is to /compact now, with reasons; offers a ready /compact that keeps goal, decisions, leftovers and paths, and…

• agent-councilapolenkov/agent-councilL3 Uses the network

  A council of independent code reviewers (Codex, Pi, Devin, OpenCodeReview) runs over your working diff in parallel; one summary of agreements, disagreements an…

• agent-crewErikMTaylor/claude-modsL1 Reads

  Bubbles above the prompt showing each subagent as a mini Claude, colored by what it is doing, with a progress % and a short label.

• agent-crewbekir1184/agent-crewL1 Reads

  Shows your subagents above the prompt as pixel-art Claude crew members: what each one is doing, how far along it is and how many tokens it used.

• agent-crewxinhuagu/oh-my-claude-modsL1 Reads

  A live pane of your subagents as a little pixel crew: who is working, on what, and how far along

• agent-cross-checknaoanao/agent-cross-checkL2 Writes or runs

  When another coding agent (or a person) commits to your repo, Claude notices, runs mechanical checks (line endings, secrets, .env files, and the agent's report…

• agent-ctxTekkiiiii/the-agencyL1 Reads

  Each agent loop's own context %, measured per request; a one-line CONTEXT_PCT_ALERT rides that agent's next tool result when it crosses 70% or 80%

• agent-dashrasa-mrankovic/agent-dashL2 Writes or runs

  Sessions, subagents and agent teams in one terminal pane (/dash)

• agent-deckNeedSomeFoodMr/claude-modsL2 Writes or runs

  A pane showing the main loop and every subagent of the session as pixel crabs, each under its role's hat: a short name, role, model, plan progress, context fil…

• agent-deckPrabal-Singh/claude-modsL2 Writes or runs

  A pane on the right that tracks this session's subagents as a tree: status, current action, files changed, tokens and cost

• agent-deckSamRoels1/agent-deckL2 Writes or runs

  Agent dashboard (derived from Flightdeck by Stephen Casella, MIT) plus routing of simple subagent tasks to cheaper models and a vault overview

• agent-decktylergraydev/cc-modsL2 Writes or runs

  Live pane of the session's subagents: status, tool calls, answers, launch and nudge, spawn caps and model rules

• agent-dietVedantAndhale/claude-pro-kitL0 Draws & remembers

  Runs search-only subagents (Explore by default) on Haiku instead of your main model; a model Claude asks for still wins, and /agent-diet picks the types and th…

• agent-dockAlyan-khattak/Claude-Code-ModsL2 Writes or runs

  Live panel showing parallel helper agents: set team size, watch cards fill in real-time

• agent-dockkorenka/claude-harnessL2 Writes or runs

  Agents side panel with run, pause, stop and open-in-tab controls, plus a context window bar with a Compact button

• agent-dockwickedhardflip/claude-code-modsL1 Reads

  /dock N tells Claude to split work across N subagents; a band shows a live card per agent.

• agent-dollsvisiblesoft-es/claude-modsL1 Reads

  Side pane with one little robot per agent (main and subagents); press one to see its conversation

• agent-firewallbaselane-sh/modsL1 Reads

  A live pane of every tool call the agent makes: green when it ran, red when it was blocked, with counters. Open it with /firewall.

• agent-fleetVladLeus/claude-modsL2 Writes or runs

  Dashboard of running Claude sessions: context, active/idle, subagents, workflows and who messages whom

• agent-flowCharlie0113-T/claude-agent-flowL0 Draws & remembers

  The agent flow pane: /flow opens a live tree of the session's subagents and teammates beside the transcript, fed by engine events, with a text fallback where n…

• agent-flowJinhaoFang/claude-modsL0 Draws & remembers

  The agent flow pane: /flow opens a live tree of the session's subagents and teammates beside the transcript, fed by engine events, with a text fallback where n…

• agent-flowdiegorv/claude-mods-diegorvL0 Draws & remembers

  A live tree of the session's subagents and teammates in a pane: status, current tool, time, calls and tokens

• agent-flowluucas42/agent-flowL2 Writes or runs

  A live workflow panel: the main model, the advisor and every spawned agent as cards joined by arrows

• agent-flowmaximemarc/Claude-modsL1 Reads

  Arbre en direct des sous-agents et de leurs outils, ouvert par /flow

• agent-flowpaulosergio-jnr/claude-code-modsL1 Reads

  Animated pane showing the orchestrator, its subagents, who is working and the messages between them

• agent-graphtheishandubey/claude-modsL1 Reads

  Pane drawing the session's running subagents: a left-to-right card graph in the desktop app, an indented tree in the terminal

• agent-groupsMark-Hickey/claude-nineL2 Writes or runs

  /agent-groups: your agents by their herdr sidebar names, with status and mesh names, in groups you can fold

• agent-hubkzarzycki/claude-modsL2 Writes or runs

  Agent hub: a pane listing this session's subagents with status, model, turns and tokens, and a box to steer a running one.

• agent-jobsnarrowstacks/claude-code-modsL2 Writes or runs

  /jobs pane: running subagents and background shells with elapsed time and Stop; a toast when background work finishes

• agent-ledgervgorla99/Condutor-Claude-SkillL1 Reads

  Shows every agent of the session, the model it ran on and its tokens; /agents opens the pane

• agent-mailboxcharanjit-singh/ClaudeVsCodeMinimalL2 Writes or runs

  Mailboxes for Claude sessions: names, cross-profile messages that wake idle sessions, and a band with your account, context, and plan limits.

• agent-mobile-observerCoolkidlab-Yin/agent-mobile-controlL3 Uses the network

  手機聊天室的觀測 mod：回合開始/結束與手機直送抵達，POST 給 :8899/api/observe；純觀測不改行為

• agent-model-badgeNew-Retr0/claude-dockL0 Draws & remembers

  Shows each spawned subagent's resolved model and effort beside its row, so a surprise model assignment is visible at a glance.

• agent-model-badgejojobird6/agent-model-badgeL1 Reads

  Shows which model (Sonnet 5.5, Opus 5.5, Haiku…) each subagent runs on, on its Agent row and in the agent viewer

• agent-model-routerlideke/agent-model-routerL2 Writes or runs

  Picks the model each subagent runs on from a per-project table, steps up a model when a task is retried, and logs every choice so an agent can tune the table.

• agent-modelsalex2481kobe/claude-modsL1 Reads

  Each Claude subagent's model and effort in the native agent list, beside its task

• agent-modelsnarrowstacks/claude-code-modsL2 Writes or runs

  Pins the model each subagent type runs on, set in /config or with /agent-models

• agent-monitorNeriakTo/claude-code-agent-monitorL2 Writes or runs

  A side pane (and a band above the prompt) tracking channel messages waiting for a reply, running and recently ended tool calls and subagents, rate-limit quota,…

• agent-monitoralwayshungry0814/claude-modsL1 Reads

  Live pane and status-line count of the agents and subagents running in this session

• agent-monitorgvart/claude-configL2 Writes or runs

  A sidebar pane for Claude Code: live progress, pause/resume, stop and messaging for subagents and workflow agents, plus session spend and plan limits

• agent-monitorisaac-pathlab/claude-monitorL1 Reads

  Live steps of the subagents Claude starts (their text and grouped tool calls), in up to 3 stacked windows (the rest queued)

• agent-monitorjaaaackieLai/claude-modsL1 Reads

  子代理監看：prompt 上方顯示子代理摘要列，/agent-monitor 開關面板，列出模型、context、token、估計費用和時間。

• agent-monitorjorgehsy/claude-modsL2 Writes or runs

  Live pane of subagents with a Clawd per agent: status, model, tokens, cost and context

• agent-monitornokiy/claude-code-modsL2 Writes or runs

  Subagent monitor: a live band above the prompt for running agents, and /sub: this session's subagent history with alerts (file conflicts, stalls, tier mismatch…

• agent-narratorOneWave-AI/claude-code-modsL2 Writes or runs

  Watch the agent work: every step in plain English, with a live time-saved counter

• agent-officeririversoza/agent-officeL2 Writes or runs

  A view-only pixel office pane showing which agents (lead, subagents, Codex, Cursor) are working, with your checklist and this branch's PR

• agent-officesaita08/my-cc-modsL1 Reads

  サブエージェントやチームの動きを、社員が働くオフィスとして pane に描く

• agent-pagerRadTech-Solutions/agent-pagerL3 Uses the network

  Pages your phone (ntfy or Telegram) when the coding agent finishes a long turn or needs you, and lets you reply from the phone.

• agent-partyytruong11201/claude-code-modsL2 Writes or runs

  Your running subagents as 16×16 pixel heroes above the prompt: their task, what they are doing, time, tokens, and a voice that tells their status

• agent-portraittesty-cool/claude-agent-portraitsL2 Writes or runs

  Animated pixel-art portrait above the Claude Code prompt that reacts to thinking, talking, tools, failures and idle time.

• agent-presetsPlagemes/claude-modsL2 Writes or runs

  Ready-made subagents for focused jobs: debugger, test writer, doc writer and migrator.

• agent-profilerYeonwooSung/my-claude-code-modsL3 Uses the network

  Execution profiler for Claude Code: model wait vs tools vs subagents, live, with OTLP export

• agent-progressnguyenngoctoan/claude-modsL2 Writes or runs

  Progress bar above the prompt for /savvy-flow or any delegated plan, plus an agents panel (/agents-info): running, finished and planned subagents with model, t…

• agent-progressredjackfred/claude-code-modsL1 Reads

  Live progress bars for running subagents above the prompt

• agent-pulseafterever/claude-modsL1 Reads

  A box above the prompt that always says what the agent is doing right now, alive with color and motion: an animated status glyph, a glowing jellyfish on the de…

• agent-quick-menuagentic-workbench/agent-quick-menuL2 Writes or runs

  A pane and prompt band for plugin commands declared in quick-menu.json, plus plugin and Claude Code settings exposed through /config.

• agent-raceOneWave-AI/claude-code-modsL2 Writes or runs

  Race Claude Code sessions on a task: live split-screen race track scoreboard

• agent-radarfbrogno/claude-modsL2 Writes or runs

  Alle Claude-Code-Sitzungen und Subagents auf einen Blick, Kaltstart-Wächter gegen teure Cache-Neuaufbauten, Modellwahl-Pflicht für Subagents, Such-Agents auf H…

• agent-radarhamzafer/claude-code-modsL1 Reads

  One live line above the prompt per running subagent: time, tool count and what it's doing. /radar shows every agent and its messages.

• agent-routerUtakataKyosui/utakata-cc-modL3 Uses the network

  サブエージェントと Workflow の agent() の依頼を LocalJev でロールに分類し、agent-routing の roles.json に従って model と effort を切り替える function hook

• agent-routeralexandernicholson/agent-routerL2 Writes or runs

  Choose a model and effort for five agent roles and for agent team teammates with /agent-models, and inspect routing and usage. Requires Claude Code Mod functio…

• agent-routermako-code/gobworksL1 Reads

  Picks the model for each subagent by its type (Explore on Haiku by default) and can cap how many run at once.

• agent-shell-watchapolenkov/agent-shell-watchL2 Writes or runs

  Always-on status line and a pane for this session's Bash calls, background tasks and Codex/Pi/Devin/OpenCodeReview runs: elapsed time, output freshness, verdic…

• agent-skillsfive82/claude-modsL2 Writes or runs

  Loads skills from the cross-harness .agents/skills directories (project and ~) into Claude Code: listed for the model and runnable as /<skill>.

• agent-skills-modslucksy/agent-skills-modsL2 Writes or runs

  See your agent-skills spec, plan and tasks inside Claude Code: a task board, a progress band above the prompt, an ETA range, sprints and a local dashboard, all…

• agent-statekleinheinczg/claude-code-agent-state-modL2 Writes or runs

  Reports what a Claude Code session is really doing (idle / working / tool / permission, plus signals and token use) from inside the session, as a JSON snapshot…

• agent-supervisorStalicJi/my-modsL2 Writes or runs

  Agent Supervisor：監控這個 session 的子代理、回報的任務與依賴、可能的阻塞與下一步建議；/supervisor 開關面板

• agent-taskszulfikar-ditya/claude-mods-agent-tasksL1 Reads

  One pane for the session's subagents and Claude's own task list

• agent-theaterafu-it/agent-theaterL2 Writes or runs

  A pixel theater above the prompt: little orange Claude acts out each tool call at a desk while a monitor shows the command and Haiku narrates it.

• agent-theaterjoydeep-pm/agent-theaterL2 Writes or runs

  A pixel theater under the prompt: the little orange guy acts out what Claude is doing, with Haiku narration in a speech bubble.

• agent-toolkitak110/dotfilesL2 Writes or runs

  Agent Plugins、Claude Code、Codex向けの品質支援プラグイン。コードと文書を扱う作業、計画やバグ調査の指針を示し、フックで入力と操作を確かめる。

• agent-trackervincentlauriat/ModsToolsL1 Reads

  A pane listing the subagents launched this session with their status and duration

• agent-treeTeodagher/teo-modsL2 Writes or runs

  Live board of your subagents: a little Claude critter per agent and one sentence on what it is doing

• agent-treeTheClaessens/thomas-claude-modsL1 Reads

  Live graph of this session's agent, its subagents and theirs: model, context, tokens, status and assignment.

• agent-treerussellpope/claude-modsL2 Writes or runs

  Pane of the herdr agents this session spawned, and theirs: status, model, context, cost, ticket. /agent-tree toggles it; a global view lists every herdr agent.

• agent-usage-guardrbartoli/agent-usage-guardL2 Writes or runs

  A Claude Code mod that holds subagent fan-out, heavy-context prompts and retry loops before they spend your usage window. It reads your plan's usage, counts ag…

• agent-warehouseshaheershoaib/agent-warehouseL2 Writes or runs

  A vector warehouse where the session's agents are little robots: they walk in when spawned, go to the web, files, desk, bench or mail station as they work, che…

• agent-watch0xGondarxyz/claude-code-modsL1 Reads

  Shows one line per running subagent above the prompt: model, task, minutes and its latest tool call

• agent-watchAndreasOA/claude-code-modsL1 Reads

  Docks a narrow pane beside the transcript that follows each running subagent live

• agent-watchTheoGegout/claude-agent-watchL2 Writes or runs

  Agent Watch: one pane for every Claude Code session on your machine and its subagents, running, waiting for you, or idle

• agent-watchestruyf/claude-agent-watch-modL2 Writes or runs

  Keeps the number of running Claude Code sessions under a limit and shows the ones waiting on you or sitting idle.

• agent-watchhereshecodes/claude-modsL1 Reads

  Flags risky Bash commands and writes to sensitive paths in a live sidebar pane, with a status-line tally.

• agent-watchice-lfernandes/claude-code-modsL1 Reads

  Subagents at a glance: tokens per agent, a toast when one stalls, and a summary naming the heaviest agent when they finish

• agent-workshopMarkMerk/markmerk-modsL2 Writes or runs

  A workshop where Claude and its subagents walk between tool stations: a pixel-art pane in the terminal, and a 3D window with a room for every session, to watch…

• agentctlmasahide/agent-kitL2 Writes or runs

  agentctl Mod: agentctl CLI (tools/agentctl) が ~/.agentctl/claude/<sessionId>/inbox/ に置いたメッセージを $.prompt.submit で Claude に届け、中断の依頼を $.turn.abort で行い、結果を acks/ に…

• agentctlsd0xdev/sd0x-harnessL2 Writes or runs

  Agent Control Plane for one Claude Code session: task scope, evidence, hand-over. A control and a display, not an isolation boundary.

• agentillehasuwini77/agentilleL2 Writes or runs

  One command for Claude Code: /agt plans, builds and reviews with the right model per step, steps aside on small tasks, and ends on one short card. Zero setup.

• agentpaneJJenglert1/claude-modsL1 Reads

  A side pane listing every helper agent in the session: what it does, how long it has run, and when it finishes.

• agentpanexuanji86/claude-agentpaneL2 Writes or runs

  A side pane for Claude Code that lists the subagents a session runs, what each is doing and what it costs in tokens, with each one's conversation a click away.

• agents-infopazimor/marketplaceL2 Writes or runs

  Agents info Mod (Claude Code 2.1.287, Mods API in early access): starting agent, timeline of agents per prompt (new, resumed, forked), resolved model and effor…

• agents-mdanthropics/claude-code, built into Claude CodeL1 Reads

  AGENTS.md as project instructions, by one option. Under claude-md-or-agents-md a project with no instruction files of its own gets its AGENTS.md files instead:…

• agents-office0xnicholasy/claude-mod-agents-rpgL2 Writes or runs

  A pane that shows the session's agents as pixel characters in an office.

• agents-panejorgik1/claude-agents-paneL2 Writes or runs

  /agents-pane opens a sidebar listing available agents in their configured colors, with a Run button each

• agents-panelBlind3y3Design/agents-panelL1 Reads

  A pane of every subagent in the session: model, effort, context, tokens, estimated cost and time, with a crab per agent role on desktop. Works with any agent t…

• agents-panelBoom-Vitt/boombignose-modsL2 Writes or runs

  Side pane listing project, user and plugin agents with a run button each; /agents-panel toggles it.

• agents-panelTLOBillyQ/claude-modsL2 Writes or runs

  A side panel listing the project's .claude/agents, each with a run button.

• agents-paneldiamondT/claude-modsL1 Reads

  Running subagents, their latest tool call and progress bars in a side panel.

• agents-panelyasirshabbirservices/claude-modsL2 Writes or runs

  A pane listing the project agents in .claude/agents, with a run button for each

• agents-sideyogeshvar/mod-claudeL0 Draws & remembers

  Shows the session's agents in a side pane: the main loop and every subagent it spawns, with tools, status, and answers.

• agents-skillsLeechael/claude-code-mod-agent-skillsUnknown access

  Discover Agent Skills under .agents/skills (project) and ~/.agents/skills (user), expose them as slash commands, list them in prompt.context, and optionally in…

• agents-viewushironoko/dotfilesL0 Draws & remembers

  A pane listing this session's subagents (Agent tool and workflow agents) with their status; select one to see its prompt, text, tool calls and results.

• agentzerojesselei1102-hue/agentzero-claude-modL2 Writes or runs

  AgentRoot for Claude Code: all of AgentRoot, plus hot set loading and a check of the operator's words.

• agmsg-inboxtsukimiya/agmsg-inboxL2 Writes or runs

  Deliver the agmsg inbox to Claude Code through a mod-owned watch.sh instead of the Monitor tool (no 30-minute re-arm)

• ahead-behindbaselane-sh/modsL2 Writes or runs

  A band above the prompt with the commits ahead and behind the upstream (↑2 ↓1), read with git status after each Bash call and file edit. Hidden when the branch…

• ai-accountsmcpysup-netizen/claude-ai-accountsL2 Writes or runs

  Claude·Codex 구독 계정별 남은 한도 띠 + 클릭 한 번 계정 전환(같은 tmux 칸에서 대화 이어가기)

• ai-dev-team111vandit111/ai-dev-teamL1 Reads

  Multi-agent build pipeline for any AI coding agent: planner, parallel builders and verifier, per-task models from your own list, knowledge-graph context, live…

• ai-sdlcSennjen/claude-sdlcL3 Uses the network

  Hook-enforced approval gates for Claude Code: intent → spec → plan → build → verify → review, with a status bar and one-click approvals.

• ai-skillsBenjaminG/ai-skillsL3 Uses the network

  Benjamin's collection of Claude Code skills: daily workflow, code quality, dev tools, and specialist agents.

• ai-usage-bandarvakme/claude-code-butlerL1 Reads

  A band above the prompt showing context fill, rate-limit windows and session cost.

• aicqashfulcra/fulcra-toolsL2 Writes or runs

  AICQ for Claude Code: your agents and friends' agents, their collaborations and what needs you. Notices messages without heartbeats, drafts or responds per you…

• aimSingh-AP/awesome-claude-modsL1 Reads

  Pin one goal for the session: it sits above the prompt with a timer, and Claude is told to stay on it and flag unrelated work instead of drifting.

• aim-widgetoMaN-Rod/claude-code-widgetsL2 Writes or runs

  Where a command lands outside this folder: the kube context, cloud profile, Terraform workspace or database it is aimed at, named in the permission dialog

• airlockBillyMRX1/airlockL2 Writes or runs

  Routes supported project edits into a Git worktree for review, accept or reject. Worktree routing is not a filesystem sandbox.

• airquotekaran-79/airquoteL2 Writes or runs

  Turns voice-mode dictation into clean, clear prompts: detects which prompts you spoke, then has Haiku remove filler, apply self-corrections and (optionally) re…

• aitoolspkkid/claude-modsUnknown access

  Subscription usage, API-equivalent cost and context bar above the prompt

• ak-cockpitthieung/claude-modsL2 Writes or runs

  AgentKit cockpit above the prompt: context fill with a handoff nudge, and the active plan's phase and checklist.

• al-syntaxabonckus/claude-code-al-syntaxL2 Writes or runs

  Tree-sitter syntax highlighting for AL (Business Central) code blocks in Claude's replies

• aleyodem/agentic-label-engineeringL2 Writes or runs

  /ale-board: a live task board for an Agentic Label Engineering (ALE) run above the prompt and in a docked pane. Reads `python3 -m ale status --json` and the ru…

• all-modsLiberty-Technical-Solutions/claude-workflow-modsUnknown access

  All 4 workflow mods in one install: status-strip, next-steps, ship-it, usage-guard.

• allanlua-erissatallan/claude-modsUnknown access

  Allan's workflow mods, built from his own session logs. Every feature has its own on/off row in /config and is switched with /mods on|off <feature>. ALLAN_MODS…

• allowlist-coachice-lfernandes/claude-code-modsL2 Writes or runs

  Counts permission dialogs per rule and, after repeated approvals, offers to add the rule to permissions.allow, asking before it writes

• almanacersinkoc/claude-modsL1 Reads

  KOZMOS Almanac: what this session is made of. Slash commands run, skills invoked, subagent types spawned, MCP servers used, models seen, plugins whose tools we…

• altshiftYossiAbutbul/altshiftL1 Reads

  Fix text typed on the wrong keyboard layout (English <-> Hebrew) and show Hebrew chat right-to-left, from a band above the prompt

• alveariumIskandeur/session-boardL3 Uses the network

  Alvearium: one ticket board for all your coding-agent sessions (Claude Code in the terminal and on claude.ai/code, and OpenAI Codex CLI) and their agents: what…

• am-context-barromnycristopher/claude-am-modsL2 Writes or runs

  A context card above the prompt with a collapsed and an expanded view: zone-coloured token count (dumb zone from 50% or 250k tokens, compact or clear from 70%…

• ambientadamentwistle/claude-code-modsL1 Reads

  An animated strip above the prompt that moves with the work, in eight styles from a request mesh to a lava lamp

• ambientbarisdemirhan/claude-ambientL3 Uses the network

  A living band above the prompt that Claude's work feeds, with sound: an aquarium, a bonsai, a skyline, constellations, weather that can follow the real sky, a…

• ambientshabier/claude-pluginsL1 Reads

  Animated 8-bit wallpapers in the docked side pane: koi pond, mountains, metropolis, neon district.

• ambient-spanish-hoverExdenta/ambient-spanishL1 Reads

  Hover a Spanish word in a reply to see its English in the band above the prompt.

• amendments-widgetoMaN-Rod/claude-code-widgetsL2 Writes or runs

  What changed in the system prompt and the built-in tool descriptions Claude Code gives Claude since the version you last ran, with the before and after one com…

• anchorpourya7/claude-code-modsL2 Writes or runs

  Pin a session to its git worktree: every Bash call runs from the anchor, and the primary checkout is guarded against stray edits and git writes.

• angry-switchertimoncool/angry-switcherL3 Uses the network

  Swear at Claude Code all you like: every prompt is cleaned before Claude reads it. Typos, translit, the wrong keyboard layout, swearing and CAPS go; the meanin…

• anime-cheera252937166/cc-modL2 Writes or runs

  Voiced pixel anime girls who roam the Claude Code transcript: they dance while Claude works and serve tea when it is done, and they do chores too: usage report…

• ankihbkse/anki-claude-modL2 Writes or runs

  Review your AnkiWeb decks above the Claude Code prompt while Claude works. Syncs straight with AnkiWeb through Anki's own Rust core; no Anki desktop or AnkiCon…

• annahmenbroening/claude-modsL2 Writes or runs

  Zeigt nach jeder Antwort die stillen Annahmen von Claude (Band ueber dem Eingabefeld); richtig/falsch markieren, falsche gehen als Korrektur an Claude. /annahm…

• annotatesagarr/claude-code-annotate-modL2 Writes or runs

  Annotate selected transcript text inline, review in a side pane, send the comments back to Claude

• anon-modeeveiljuice/claude-anonL2 Writes or runs

  claude anon: incognito mode: clean context (memory, CLAUDE.md, history unloaded), session not saved, transcript deleted at exit

• answerPeteChu/cc-answerL2 Writes or runs

  /answer: answer the questions in Claude's last reply in Claude Code's native question dialog

• answer-buttonsmutlumehmet/claude-pluginsL2 Writes or runs

  Three small buttons under Claude's last answer: Plain English, Shorter, and Plain & short

• answer-paneVedantAndhale/claude-pro-kitL2 Writes or runs

  Explain, plan and ELI5 pages drawn natively in a side pane: diagrams in place, plan decisions as buttons, Respond fills the prompt box. No model calls.

• answersrjohnt/answers-claude-modL1 Reads

  Answers-only view of the main thread: each reply filed under the prompt it answers, latest headline + open ask pinned above the prompt

• anti-cheatpourya7/claude-code-modsL2 Writes or runs

  No claims without evidence: flags "tests pass", "CI green" and "verified" claims that nothing in the turn backs up.

• aot-evalsMahalanobis-Systems/aot-evalsL0 Draws & remembers

  Part of AOT, the Agent Optimization Toolkit, a Mahal Systems offering. Design, build, measure and iterate the evals for a production agent: a repository contra…

• apercutibzejoker/claude-modsL3 Uses the network

  What Claude is building (website, mobile app, desktop client, Unity game…), live in a panel of the client (desktop, mobile in Remote Control, terminal): Claude…

• apk-fraicheurDarkSawOktay/claude-modsL2 Writes or runs

  Android APK freshness: is the APK up to date with the code, build in progress and its duration, failures and out-of-memory caught at once, size, copy to anothe…

• approma-vibe/fastdev-claude-code-modL2 Writes or runs

  A Claude Code mod.

• apple-treeJoyceGu/apple-tree-modL1 Reads

  An apple tree that grows with your weekly limit and fruits once per 5-hour window

• approval-guardUtakataKyosui/utakata-cc-modL1 Reads

  AskUserQuestion で得た承認と gh の不可逆コマンド（レビュー投稿・close・merge）の宛先を照合し、force push の確認と PR 本文の Closes キーワードの確認も行う function hook

• approvalsdbroadhurst/claude-mod-approvalsL2 Writes or runs

  A pane on the right listing the decisions Claude needs from you, each with its recommendation and Approve / Chat buttons

• approve-blockedadammhal/claude-modsL2 Writes or runs

  Retries an auto-mode-blocked call up to three times so Claude Code's own permission prompt (and Moshi) can ask you.

• appshotmareksulik/appshotL2 Writes or runs

  Press both ⌘ keys to give Claude the window you're looking at: a screenshot plus its text, including text scrolled offscreen (macOS)

• aprobar-dependenciasalexyslozada/claude-modsL1 Reads

  Pide tu aprobación antes de que Claude instale cualquier paquete y muestra el historial en una franja

• aqdaviddecorso/claude-modsL2 Writes or runs

  Pane for the per-repo aq prompt queue: pick items, batch them into the prompt box, queue drafts, and let Claude queue follow-ups

• aquarium-widgetoMaN-Rod/claude-code-widgetsL1 Reads

  An aquarium with a fish for every running tool call and agent.

• arcadeZaho92/claude-arcadeL1 Reads

  Retro games in a Claude Code pane that run while Claude works and freeze the moment it needs you.

• arcademako-code/gobworksL1 Reads

  Something to do during long turns: /snake and /2048 in a pane, with high scores and a nudge when Claude is done.

• arcademutlumehmet/claude-pluginsL3 Uses the network

  The Claude Code Arcade: pixel games above the prompt, played by your work (an invading octopus, a duck hunt, Bug Command, which you can play along with, Dario,…

• arcadeshabier/claude-pluginsL1 Reads

  Five games in the docked side pane: Rail Runner, Road Hopper, Block Drop, Flap, 2048. Hides below 110 columns.

• arcadethefotes/pane-arcadeL2 Writes or runs

  Play Snake, Minesweeper, 2048, chess (vs Stockfish) and CHIP-8 ROMs in a pane while Claude works.

• arcadetylergraydev/cc-modsL2 Writes or runs

  Tic-tac-toe, sudoku, tetris, video poker, blackjack and UNO in a side pane, playable by keyboard, mouse or an Xbox controller

• archcorearchcore-ai/archcoreL3 Uses the network

  Spec-driven development and context engineering for AI coding agents, backed by project context in Git.

• archgateaarontan-bot/Claude-modL2 Writes or runs

  Architecture map + plan gate: the AI maps modules, declares a scope, you approve it, and edits outside that scope are blocked and observed.

• architecture-treescholarly360/claude-mod-architecture-treeL0 Draws & remembers

  When a prompt uses architecture or design words, asks Claude to answer with the system architecture as a box-drawing tree.

• archon-panelseanrobertwright/claude-modsL3 Uses the network

  An Archon pane in the side panel: this project's workflow runs, their graphs and logs, and the approvals that wait on you.

• archpanefacumarcet/archpaneL2 Writes or runs

  Live architecture diagram in a side pane that Claude draws and edits while you talk

• arresterdot-agi/arresterL1 Reads

  After a hook, deny rule, or auto mode blocks a tool call, Arrester stops later calls that reach the same result another way or read or change your guards. Afte…

• arsenalafterever/claude-modsL2 Writes or runs

  A menu for the tool mods in this repo and for your own commands: a button in the footer under the prompt box opens a menu pane, docked on the right, with a Pro…

• artifact-archivevoid2610/dotfilesL0 Draws & remembers

  一時ディレクトリ (tmp/scratchpad) からの Artifact publish を拒否し ~/Documents/claude-artifacts への保存へ誘導する

• artifact-modnetgfx/claude-artifact-modL2 Writes or runs

  A side pane listing the media files and documents created in this session, with type icons, pagination, and open-with-default-app.

• artifact-watchdogm2ai-portfolio/claude-modsL2 Writes or runs

  Enforces the subagent output contract: watches each Agent dispatch's artifact file, flags a 5-minute stall, wakes an idle Claude once per stall, offers a Stop…

• ascii-flipbookwhyashthakker/awesome-claude-code-modsL1 Reads

  Play a local text animation whose frames are separated by a form feed.

• ascii-weathervincentlauriat/ModsToolsL2 Writes or runs

  Weather from wttr.in in the status line (refreshed at most once an hour); /weather shows the one-line forecast

• asd-ste100JAICHANGPARK/ASD-STE100L2 Writes or runs

  ASD-STE100 (Simplified Technical English) and 80% Karpathy Mode plugin, mod, and skill for Claude Code. Enforces clean, unambiguous technical explanations.

• aserse/aseL1 Reads

  Agentic Software Engineering (ASE)

• asideJayDoubleu/asideL2 Writes or runs

  Read-only side chat: /aside opens a pane beside the transcript where you ask about the session so far; answers come from a tool-less fork of the session's own…

• asideescapeboy/claude-code-kitL2 Writes or runs

  /aside <question>: asks a tool-less fork of the session in a pane; nothing enters the main conversation.

• asidesruthik27/claude-foundryL2 Writes or runs

  Read-only side chat: /aside opens a pane beside the transcript where you ask about the session so far; answers come from a tool-less fork of the session's own…

• asidezrdqns/claude-code-asideL2 Writes or runs

  /aside side chat for asking about the conversation without spending its context

• aside-widgetoMaN-Rod/claude-code-widgetsL2 Writes or runs

  Ask a side question about the conversation, even mid-turn, and get the answer on a card without adding a turn to the transcript

• askhyperbola-bear/claude-modsL2 Writes or runs

  A side chat in a pane that reads the main chat, scrolls and draws: /ask a question, /draw a diagram. Nothing goes back to the main chat unless you send it. Ans…

• ask-autopickKilimcininKorOglu/claude-code-modsL1 Reads

  Picks the recommended option of a question that waited unanswered for a set time, so a session you left does not stop. Off until you turn it on.

• ask-choicei-noma-ru/claude-ask-choiceL2 Writes or runs

  When a reply ends with a choice-based question written in plain text, has the model re-ask it with the AskUserQuestion picker so you can select an option inste…

• ask-firstNasrallah-Adel/claude-ask-firstL1 Reads

  Holds git commit, push, PR merge and PR creation against protected branches, and edits to .claude/settings*.json, behind a Proceed / Cancel question unless you…

• ask-jevAkeuuh/claude-modsL3 Uses the network

  ask_jev on any situation, files, a command's output and your own state, with a spend ledger

• ask-jev-fileAkeuuh/claude-modsL3 Uses the network

  Ask Jev a yes/no, a choice or a score about one file without reading it

• ask-jev-filesAkeuuh/claude-modsL3 Uses the network

  Ask Jev the same typed questions of many files in parallel, then pick the one to open first

• ask-notchsameeeeeeep/ask-notchL2 Writes or runs

  Claude's questions drop from your Mac's notch as a card. Click an option, pick with 1-4, type your own answer, or press esc to answer in Claude Code as usual.

• ask-on-auto-denytylergraydev/cc-modsL2 Writes or runs

  When auto mode's classifier blocks a tool call, asks you above the prompt and lets you allow that exact call once

• ask-threadsyyosifov/prompt-modsL2 Writes or runs

  /ask: side questions you can list, reopen, continue, and send to the main conversation

• assertion-guardianccdwyer/assertion-guardianL2 Writes or runs

  Blocks edits that weaken tests to fake a green run: removed or loosened assertions, added skips, deleted cases, swallowed errors, snapshot rewrites

• assumption-checkvumichien/claude-code-mods-kitL2 Writes or runs

  After a turn that edited files or ran commands, Haiku lists the choices Claude made that you did not state. Mark each right or wrong, add a note, and send the…

• assumption-trackerYeonwooSung/my-claude-code-modsL2 Writes or runs

  Assumption Tracker

• assumption-trackeraravindsriraj/claude-code-modsL2 Writes or runs

  Claude records each assumption it makes; review them in a side pane, mark them right or wrong, and the verdicts go back to Claude.

• astir-tuiSertelegger/astirL2 Writes or runs

  astir inside Claude Code's terminal: a footer count of agents waiting on you, a warning line when no one would be told, and /astir, a pane with a key that take…

• astrolabejonyfs/astrolabeUnknown access

  Spec Kit progress and usage governance for Claude Code: a phase rail above the prompt, the next command in the prompt hint, the current task on the spinner, a…

• at-workzhuoxingzhang/pixel-at-workL1 Reads

  A pixel-art animation above the prompt that shows what Claude is doing right now, with computer-science jokes on the spinner and holiday decorations

• atelierkys0213/kys-claude-pluginL2 Writes or runs

  통합 개발 워크플로우: spec/git/orchestrator/workflow 를 관심사 단위 skill 로 큐레이션한 단일 plugin

• ateliermesix971/mods-claudeL2 Writes or runs

  Bandeau projet (APK vs tel, git, quotas et conso en euros, conseil de modèle, tâches, sous-agents et build en pastilles) et garde-fous pour le dev Android avec…

• atelier-bellKTCrisis/flux7-modsL3 Uses the network

  Tells you when an atelier finishes: flux7-studio renders, as toasts and a line under the prompt

• ather-automataAskTinNguyen/ather-modsUnknown access

  Ather Automata: what needs you and what is next in every S2 session and web app repository (Plan, Build, Prove, Ship), a newcomer tour, autonomy windows, and g…

• ather-boardAskTinNguyen/ather-modsL2 Writes or runs

  Ather Board: the team's intents as a project board. /board shows what is stuck, every intent by owner, area or stage, the open acceptance items and each person…

• attachmentsthefuga/claude-xL2 Writes or runs

  The draft's attachments as chips above the prompt: each pasted picture, pasted text, @-mentioned file or folder and, with the issues mod, @# issue, with a glyp…

• attentionfarmattentionfarm/modL3 Uses the network

  sign up or log in, an attentionfarm band above the prompt and a scrolling status line for claude code.

• attest-ledgerramankrishna/attest-ledgerL2 Writes or runs

  Shows what actually ran next to what Claude said ran: checks, stale passes, and unbacked claims.

• attic-widgetoMaN-Rod/claude-code-widgetsL1 Reads

  Counts which tools Claude calls in this project, puts the unused ones behind ToolSearch, lists the daily ones up front, and reports how many schema tokens each…

• attributionmako-code/gobworksL0 Draws & remembers

  Your commit and pull request credit line, your way: Claude Code's default, none, or your own template with {model}.

• audit-packbaselane-sh/modsL2 Writes or runs

  Three read-only audit commands in one mod: /secret-scan, /conflicts and /licenses. They read git, project files and dependency folders. They copy results to th…

• audit-trailPlagemes/claude-modsL2 Writes or runs

  Writes every action Claude takes to an append-only JSONL audit log.

• auroraersinkoc/claude-modsL1 Reads

  KOZMOS Aurora: northern lights above the prompt while the model thinks. Shifting curtains whose intensity and speed follow the effort level (low is gentle, max…

• auth-guardDominickGiordano/claude-modsL2 Writes or runs

  Spots an expired CLI login in tool output and offers a Login button that signs in and retries.

• authorsbaselane-sh/modsL2 Writes or runs

  Adds /authors: the top 15 contributors by commit count with their last commit date, from git log. Names only, never email addresses. Read-only. Copies the resu…

• auto-approvellkhacquan/claude-modsL2 Writes or runs

  Answers permission prompts for you: regex layers allow routine tool calls and always ask on pushes to protected branches, and haiku judges the rest against you…

• auto-checksonata39-star/claude-modL2 Writes or runs

  Runs the project's linter after each edit and its type-checker before Claude stops, handing failures back to Claude

• auto-checkpointJustmalhar/awesome-claude-modsL2 Writes or runs

  Snapshots the working tree into hidden git refs at the start of every turn, with /checkpoints to list them and /undo-turn to roll back.

• auto-checkpointPlagemes/claude-modsL2 Writes or runs

  Snapshots your work tree before every editing turn and lets you /rollback to any checkpoint.

• auto-compactUtakataKyosui/utakata-cc-modL2 Writes or runs

  ターン終了時のコンテキスト使用率・ターン数、またはプロンプトキャッシュの失効を見て自動で Compaction し、要約をテキストに保存する。終了前の Issue 化・ドキュメント化を Agent に義務づけ、会話には何をやったか・何ができたか・次に何をやるかだけを残す

• auto-contextmako-code/gobworksL2 Writes or runs

  Say "this error", "the tests", "this file", "what you just did" or "the plan" and what it points at goes along with your prompt: the failing output, the test f…

• auto-contextvincentlauriat/ModsToolsL2 Writes or runs

  Adds git branch, dirty count, last commit and next TODOS to the session's system prompt

• auto-continueicedevil2001/auto-continueL2 Writes or runs

  When the 5-hour usage limit is hit, wait for the reset and send "continue" automatically.

• auto-continuemako-code/gobworksL2 Writes or runs

  Keeps work flowing: when Claude stops mid-task ("Next I'll…") or asks an obvious yes ("Shall I continue?"), a 5-second countdown you can stop sends a short con…

• auto-effortarthur-fontaine/cc-mod-auto-effortL3 Uses the network

  Picks Claude's effort level for each prompt with a System One decision model

• auto-effortjustmytwospence/claude-auto-effortL3 Uses the network

  Sets the effort for each prompt: Jev rates how much reasoning the request needs, capped at the session's own effort.

• auto-effortkzarzycki/claude-modsL1 Reads

  Auto effort: the decision model rates each prompt and the turn it starts runs at that effort.

• auto-effortnoash-xrc/claude-toolsL2 Writes or runs

  Picks low, medium or high effort for each prompt, keeping the prompt cache warm

• auto-effortpeterlimg/auto-effortL3 Uses the network

  Picks /effort per prompt: Jev (TypeSafe AI) grades how hard the task is, and the turn runs at that level.

• auto-formatPlagemes/claude-modsL2 Writes or runs

  Formats every file Claude edits with the right formatter for its language.

• auto-formatbaselane-sh/modsL2 Writes or runs

  Runs your project's own formatter on each file Claude writes or edits, only when the project has a formatter config, and tells Claude to re-read the file.

• auto-handoffAmel-DZRV/claude-code-auto-handoffL2 Writes or runs

  Shows a context bar with a red handoff mark, the prompt-cache countdown and per-request tokens. When context passes a threshold it writes a handoff summary, cl…

• auto-handoffJang-seungminn/usage-hudL2 Writes or runs

  /handoff 로 대화를 인수인계서로 정리하고 /pickup 으로 새 세션에서 이어받는다

• auto-handoffSpardutti/claude-modsL2 Writes or runs

  Hands the work to a fresh, named session when the context gets too full, using your /handoff command

• auto-handoffalexknowshtml/claude-auto-handoffL2 Writes or runs

  Hands a Claude Code session off to a fresh one before the context fills: a Haiku-written brief, /clear, and a seed that points the new session at the brief.

• auto-handoffdhrubo55/claude-modsL2 Writes or runs

  Writes a handoff by itself shortly before the prompt cache of an idle session expires, while the cache is still warm. Runs its own /auto-handoff:handoff skill…

• auto-handoffm2ai-portfolio/claude-modsL3 Uses the network

  Writes a /next handoff automatically once a 1M-token session crosses 300k tokens, so the next session can /prime from it

• auto-handoffpromptadvisers/claude-mods-starter-kitL2 Writes or runs

  Writes a cold-start handoff to handoff/ before the context fills up or compacts, and offers to resume from it in the next session.

• auto-handoverdavidho27941/cockpitL2 Writes or runs

  When context usage reaches your threshold, writes a handover note over the cached conversation prefix, compacts automatically, and hands the note to the compac…

• auto-lintbaselane-sh/modsL2 Writes or runs

  Runs your project's own linter fix (eslint, ruff or golangci-lint) on each file Claude writes or edits, only when the project has that linter's config, and tel…

• auto-modebendrucker/claudeL1 Reads

  Enhancements for Claude Code auto mode

• auto-modeld3nims/d3nim-claude-modsL2 Writes or runs

  요청마다 맞는 모델이 처리해요. 메인(Opus)은 그대로 두고 단순한 일은 Sonnet·Haiku 일꾼에게 맡겨서, 기억(프롬프트 캐시)을 안 깨고 사용료를 아껴요. 쉬고 온 뒤 압축은 Sonnet 요약, 아낀 만큼 테리 카드에 표시

• auto-panesToriwuuu/claude-modsL2 Writes or runs

  每次開 Claude Code 自動打開右側的 Diff 和 Files 面板（Source Control 用 ◨ 手動開）

• auto-pinulttla/claude-mod-repoL3 Uses the network

  Pins a new session in the desktop app's sidebar as it starts

• auto-polishmako-code/gobworksL2 Writes or runs

  Every prompt you type gets a quiet second read: without changing your words, a hidden note gives Claude the goal in one line, the likely scope, the project's c…

• auto-resumeseanrobertwright/claude-modsL2 Writes or runs

  When a turn dies on a rate limit (or an overloaded API), counts down to the reset and sends "continue" for you.

• auto-resumetartinerlabs/claude-code-modsL2 Writes or runs

  Sends "continue" once a usage limit resets, so a turn cut off by the limit picks up where it stopped.

• auto-retrymako-code/gobworksL2 Writes or runs

  Keeps long sessions going through API errors and rate limits: resubmits after a backoff when idle, waits out rate limits with a countdown, never loops, and sto…

• auto-reviewmako-code/gobworksL2 Writes or runs

  A quick second pair of eyes after edits: reviews the turn's diff in the background and offers to fix what it finds.

• auto-session-nametartinerlabs/claude-code-modsL2 Writes or runs

  Names each session from its first prompt, and again a few prompts in when that one was short, so it is easy to find in /resume.

• auto-session-titlefernandokobayashi-telus/claude-modsL3 Uses the network

  Titles the session after a few prompts and refreshes it as the work drifts; /done and /undone add or remove a checkmark in front of the title.

• auto-worktreeyut0takagi/modsL2 Writes or runs

  セッションの最初のプロンプトを送ったときに、git のワークツリーを作ってそこへ移る

• autocommitIliesseu28/claude-autocommitL2 Writes or runs

  Turns every turn Claude takes into a clean git commit: only the files that turn changed, a Conventional Commits message written by Haiku, a secret scan before…

• autodev-coredjnsty23/claude-auto-devL1 Reads

  Autonomous development workflow: brainstorm, auto, audit, review, ship, plus the prd.json sprint system.

• autonomous-loopyai333/autonomous-loopL2 Writes or runs

  A state-machine graph engine that drives a ticket through claim -> worktree -> coding -> evaluate -> review -> human approval, spawning and monitoring subagent…

• autopilotJPanna/claude-modsL2 Writes or runs

  Works through a GOALS.md goal tree turn after turn, with locked checks, its own check verdicts, lessons that carry over, safety guards and a progress band

• autopilotPlagemes/claude-modsL2 Writes or runs

  Give it a goal and success criteria; it plans, delegates, verifies and retries until the criteria pass or it needs you.

• autopilotVladLeus/claude-modsL2 Writes or runs

  Run a session autonomously for a set time with a fixed role; hand off and restart itself at a context threshold

• autopilotsayre4ux/autopilotL1 Reads

  Multi-agent orchestrator harness for Claude Code: command loop, ledger, dispatch protocol, review cycle, model-economics, and a registry-driven external-worker…

• autopilot-progressIT-Shelter-Labs/Claude-ModsUnknown access
• autoresearchbn-l/claude-autoresearch-modL3 Uses the network

  Autonomous experiment loop for Claude Code: run, measure, keep or discard. A port of pi-autoresearch.

• autoteljagreehal/autotelL3 Uses the network

  OpenTelemetry for Claude Code plugins: adds $.autotel in the engine.create fold so a plugin records spans, traces every hook dispatch with the chain beneath it…

• autotunemako-code/gobworksL3 Uses the network

  Per-prompt effort autopilot: classifies each prompt (Jev, Claude Haiku, or heuristics) and sets that turn's effort, and optionally its model, only when the swi…

• avatar7KTCrisis/flux7-modsL2 Writes or runs

  A machine face that watches tool calls and comments on them, with switchable avatars

• awarenesshatton/awarenessL3 Uses the network

  A Claude Code pane showing the model, thinking level, context, usage limits, git state, PR, running agents and your last three prompts.

• awcompactAitherium/awdkL2 Writes or runs

  Compacts a long tool result through the AitherOS decision door before the model reads it: per LINE SHAPE, learned from outcomes, never dropping a traceback or…

• aws-profilelucasleandro08/claude-modsL2 Writes or runs

  Shows each AWS profile above the prompt with whether its login still works, a one-click `aws sso login` in the app's Terminal for the expired ones, and the AWS…

• awshAitherium/awdkL3 Uses the network

  awsh for Claude Code: an `aw` subagent type whose model steps are answered by a session on the local awsh harness daemon, so any harness and any backend the da…

• ayat-of-the-daythisismairaj/ayat-of-the-dayL3 Uses the network

  Fetches a daily Quranic ayat live from api.alquran.cloud, shown in place of the spinner verb while Claude works, with a /ayat command for the full verse