404 agents & automation Claude Code mods, most popular first. Every listing shows its security level and install command.
| Name | Popularity | Security |
|---|---|---|
| agent-colours Colours subagent and skill names in Claude Code by their own color: field. An agent's name sits on a coloured | – | Low risk |
| agent-delegation The delegation mode, subagent cap and model routing. | – | Low risk |
| codex-pane Follow your Codex CLI session live in a Claude Code pane; relay the current exchange to Claude, or Claude's an | – | Low risk |
| agent-workshop A workshop where Claude and its subagents walk between tool stations: a pixel-art pane in the terminal, and a | – | Review before installing |
| crab-crew A crew panel for standard subagents (/crew): each agent type is a crab character with its own role, look and l | – | Low risk |
| agentctl agentctl Mod: agentctl CLI (tools/agentctl) が ~/.agentctl/claude//inbox/ に置いたメッセージを $.prompt.submit で Claude に | – | High risk |
| agent-flow Arbre en direct des sous-agents et de leurs outils, ouvert par /flow | – | Low risk |
| linear-tree A Claude Code mod: a Linear project as a tree and a flowchart in a side pane, with progress, search, filters, | – | Review before installing |
| mcp-diet Choose which MCP tools and subagent types Claude sees, per project. A pane lists every server and tool with th | – | Low risk |
| undo-agent Undo the file edits a subagent made. /rewind restores your own turns, but not a subagent's edits; this snapsho | – | Review before installing |
| buffer-pane A pane beside the transcript that holds the next things to tell the agent: write blocks of text while a turn r | – | Low risk |
| dash-it /dash-it opens a widget dashboard of background shells, subagents, monitors and schedules the session runs out | – | Low risk |
| glimt A quiet side pane: what this session is doing now, its plan, its agents as a tree, and every other Claude Code | – | Review before installing |
| scout-router Before a subagent starts on Opus, a Haiku judge reads its task and moves it to Sonnet unless it needs Opus's j | – | Low risk |
| time-agentes Modelo por tipo de subagente e painel /agentes com status e barra de consumo de cada agente e do total. | – | Low risk |
| effort-router Keep the model fixed and pick the reasoning effort per turn by classifying the prompt with $.model.classify | – | Low risk |
| model-router Route each turn to Haiku / Sonnet / Opus with TypeSafe Jev (default: Sonnet) | – | Review before installing |
| terminal-tab-title Names the terminal tab your coding agent runs in from your first prompt: Claude Code, Codex, Cursor, Gemini CL | – | Review before installing |
| model-router Jev (TypeSafe) picks the model and effort per task type; ported from jev-model-router with main-loop model swi | – | Review before installing |
| agent-jobs /jobs pane: running subagents and background shells with elapsed time and Stop; a toast when background work f | – | Review before installing |
| agent-models Pins the model each subagent type runs on, set in /config or with /agent-models | – | Low risk |
| live-spinner Spinner says what is actually running: the Bash command, the file being read or edited, the search, the subage | – | Low risk |
| pre-merge-cross-review merge 前の codex review を必須化する | – | Low risk |
| code-buddy Comment on your dev app in the browser; one background agent per comment makes the change and answers in the t | – | High risk |
| swarm-mod Spawn, watch and steer a swarm of Claude Code agents from a side pane | – | Review before installing |
| agent-model-badge Shows each spawned subagent's resolved model and effort beside its row, so a surprise model assignment is visi | – | Low risk |
| control-tower Control Tower: Flightdeck's live agent dashboard on top, savvy-progress's savvy-flow agents panel below, plus | – | Low risk |
| temper-pr-queue A review queue for the open temperlang/temper PRs from one author: grouped, sized, overlap-aware, with a guide | – | Low risk |
| opus-conductor Opus 5.5 conducts a mission: plans sized tasks, delegates hard labor to Sonnet 5.5 workers and narrow jobs to | – | Low risk |
| colony Side pane showing agents as pixel creatures | – | Review before installing |
| bruh Coordinate Claude Code sessions across projects and machines: bigm, clankers, clerks, and workflows. | – | Review before installing |
| agent-flow Animated pane showing the orchestrator, its subagents, who is working and the messages between them | – | Low risk |
| honest-exit Make silent shell failures loud: a glob that matched nothing, a command missing from the agent's shell, or a p | – | Low risk |
| clean-code Setzt Clean-Code-Regeln als Hooks um: Lint-Hinweis nach Code-Änderungen, Referenzordner mit Quellcode der Bibl | – | Review before installing |
| prompt-boost Analysiert und optimiert Prompts und Agenten-Aufträge passend zum aktiven Modell und macht Subagenten sparsam: | – | Review before installing |
| prompt-queue Queue prompts in a card grid above the input and send each later with a button, or auto-send them after each r | – | Low risk |
| model-router Routes prompts and subagents to a cheaper or stronger model by what they ask | – | Low risk |
| repo-radar Live map of the repo that lights up as Claude and its subagents read, edit and fail on files | – | Low risk |
| swarm Live map of the session's agent tree: who spawned whom and what each is doing | – | Low risk |
| agent-pager Pages your phone (ntfy or Telegram) when the coding agent finishes a long turn or needs you, and lets you repl | – | Low risk |
| squishys A companion mod for Claude Code's agents: every agent gets its own tiny pixel-art squishy you can watch, stop, | – | Review before installing |
| raily-matches Raily is a personal AI agent that finds people worth meeting for you (friends, dates, business contacts) and h | – | Review before installing |
| agent-dash Sessions, subagents and agent teams in one terminal pane (/dash) | – | Low risk |
| office-space Subagents as 16-bit office workers above the prompt, plus external workers from a watched folder. Toggle with | – | High risk |
| cdx Run OpenAI Codex and Google Antigravity execution lanes from Claude Code with background event delivery, statu | – | High risk |
| agent-progress Live progress bars for running subagents above the prompt | – | Low risk |
| model-router Runs Explore subagents on haiku and general-purpose ones on sonnet unless a model was asked for | – | Review before installing |
| claude-dj Control YouTube Music, Spotify or anything else playing from Claude Code: a now-playing band, a /music pane wi | – | High risk |
| session-tasks A line above the prompt counting the background tasks running in every session, and a side panel listing them | – | Review before installing |
| prompt-posse The boss and a posse of subagent creatures walk back and forth above the prompt while Claude Code works | – | Low risk |
| agent-office 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 | – | Low risk |
| ticket-board A live board of an implement-spec run: each ticket's status, blockers and agents, with corrections sent straig | – | Low risk |
| linear-workflow Linear workflow for Claude Code: issue-next, issue-start, issue-review, issue-ship and issue-plan-cycle skills | – | High risk |
| sbs-deck SecureBine console styling for Claude Code: labelled prompt boxes, queued-message colors, quiet tool rows, col | – | Review before installing |
| model-router Routes each turn and subagent to a model tier and reasoning effort using a classifier behind any server that s | – | High risk |
| party-pane A side pane that shows the agents working on your requests as illustrated characters | – | Low risk |
| lean-and-mean Concise prose and YAGNI code, installed into the project AGENTS.md. /endsession writes Rules and Next, commits | – | Low risk |
| workstreams-board A live pane for a workstreams round: each stack layer's place in the review loop, its CI, threads, agents and | – | Low risk |
| stworkflow Runs a feature from idea to merged PR through a 15-step workflow, shown as a one-line rail above the prompt | – | Review before installing |
| agent-supervisor 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 | – | Review before installing |
| task-board Side panel listing every todo, task and subagent with live status | – | Low risk |
| focus-lock Start a timed sprint on one task with /sprint. Prompts about anything else are held until the timer ends. | – | Low risk |
| agent-tree Live board of your subagents: a little Claude critter per agent and one sentence on what it is doing | – | Low risk |
| agent-portrait Animated pixel-art portrait above the Claude Code prompt that reacts to thinking, talking, tools, failures and | – | Review before installing |
| roadmap Panel con el roadmap del plan de superpowers activo y las tasks y subagentes de la sesión | – | Low risk |
| agent-graph Pane drawing the session's running subagents: a left-to-right card graph in the desktop app, an indented tree | – | Low risk |
| meter Session meters: a band above the prompt on desktop, a status line under the prompt on the terminal, and a suba | – | Review before installing |
| agents-panel A side panel listing the project's .claude/agents, each with a run button. | – | Low risk |
| jev-model-router Corrects the model tier of every subagent spawn (agent.spawn) with a live Jev judgment (haiku / sonnet / opus) | – | Review before installing |
| neko-agents 起動中のエージェントを猫にして書き出す（見るのは neko-room ビューア） | – | High risk |
| effort-router Picks the reasoning effort for each turn of the main conversation with a System One classifier (hosted Jev or | – | High risk |
| homedot-panel Shows your homedot agents in Claude Code's status line (running, resting, stopped), with the 5-hour limit and | – | Low risk |
| agent-deck Live pane of the session's subagents: status, tool calls, answers, launch and nudge, spawn caps and model rule | – | Low risk |
| inbox The repo's inbox/ work queue as a pane: todo items at the root, then processing/, review/, done/ and blocked/. | – | High risk |
| sound-board Plays a distinct sound for subagent spawn/finish/failure, permission asks, auto-mode denials, finished turns a | – | Review before installing |
| timeline Vertical orchestration timeline: talk on the left, work milestones with progress and live subagent cards on th | – | High risk |
| ziel-graph Der Plan eines Repos in zwei Ansichten, mit GOAL.md als Anker: /graph zeigt schmal die laufenden Chats und den | – | High risk |
| ultracode-gpt GPT mode for ultracode: Workflow agent() calls run on GPT through pi instead of Claude subagents. | – | Review before installing |
| unpaged Renders Claude Code plans as whiteboards on Unpaged. /unpaged:visual-plan turns the plan in your conversation | – | Review before installing |
| agent-router 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 func | – | Review before installing |
| change-review 実装後の差分を、実装者とは別の読み取り専用レビュアー SubAgent に点検させるMod。指摘の形式検証、再レビュー回数の上限、未実施・未解決の明示を行う。任意で、ローカルLLMによる差分の一次点検 (参考データ) も | – | Review before installing |
| goal-orchestrator /goal の内容をタスク分解・TODO化・実行順序付けし、各タスクを SubAgent に委譲させる | – | Low risk |
| subagent-router SubAgent の起動時に、タスクに合う model と effort を ollama の決定モデル (tev1:4b、不調なら nimble) に判断させて振り分ける | – | Low risk |
| agent-tracker A pane listing the subagents launched this session with their status and duration | – | Low risk |
| done-sound Plays a short chime when a long main-agent turn completes; /done-sound off|on|test | – | Low risk |
| tool-heatmap A pane counting tool calls and failures per tool, main conversation and subagents together | – | Low risk |
| vkazas-side A side pane (/side) where you talk directly to a subagent forked from the main conversation, while the main co | – | Low risk |
| babysitter Watches your background agents, corrects the ones that loop, stall or error out, and reports when they are don | – | Review before installing |
| code-kit Keeps AI coding agents inside your project's rules, from idea to merged code: spec design, lanes, layer rules, | – | Review before installing |
| agent-dock /dock N tells Claude to split work across N subagents; a band shows a live card per agent. | – | Low risk |
| run-breakdown Band above the prompt: after a long run, which model and effort the main session, each subagent, Gemini and Ol | – | Low risk |
| subagent-models Status line shows which model each running subagent is using | – | Low risk |
| codex-lane Run worker jobs on Codex in the background, with completion notifications and a jobs pane | – | High risk |
| agent-crew A live pane of your subagents as a little pixel crew: who is working, on what, and how far along | – | Low risk |
| jev-router Per-turn model routing: TypeSafe Jev picks Haiku, Sonnet or Opus for each prompt (port of gargpratyush/jev-rou | – | Review before installing |
| agents-panel A pane listing the project agents in .claude/agents, with a run button for each | – | Low risk |
| model-router Classifies each turn as mechanical, ordinary or hard and sets the model and reasoning effort to match, logging | – | Low risk |
| ale /ale-board: a live task board for an Agentic Label Engineering (ALE) run above the prompt and in a docked pane | – | Review before installing |
| agents-side Shows the session's agents in a side pane: the main loop and every subagent it spawns, with tools, status, and | – | Low risk |
| scopus-mod-for-dobby A /scopus-mod side pane for browsing the scopus-for-dobby library and attaching papers to the chat, with tools | – | Review before installing |