404 agents & automation Claude Code mods, most popular first. Every listing shows its security level and install command.
| Name | Popularity | Security |
|---|---|---|
| nightrun-pane Live night-run status pane (`/nightrun`) that reads an external orchestrator's `runtime/nightrun` layout. | 2 ★ | Low risk |
| eunuch-mode-court A Claude Code mod for Eunuch Mode: while the skill is on, the palace adviser stands above the prompt in pixel | 2 ★ | Review before installing |
| council Second opinions inside Claude Code: GPT as fresh eyes when you go in circles, Codex acceptance of every handov | 2 ★ | High risk |
| mascot A desktop mascot overlay that reacts to turns, tool calls and subagents | 2 ★ | High risk |
| magic-router Routes each session to Sonnet 5.5 or Opus 5.5 and each prompt to an effort level, using a local GLiNER2.5 clas | 2 ★ | High risk |
| nightshift Codex inside Claude Code: it picks up the chat when your Claude limit runs out, talks with you through Codex's | 2 ★ | High risk |
| team-orchestrator Team Orchestrator: welcome screen, quick starts (Squad, All-Purpose Team, Tech Team), a table-style team form, | 2 ★ | High risk |
| graphos-agent-mods Experimental Claude Code mods for GraphOS Agent Services. GraphOS Inspector explains each execute call in a do | 2 ★ | High risk |
| tool-elapsed 長く走っている tool 呼び出し (codex exec / swift test / make test …) の経過時間をプロンプトの上の帯に出し、5 分ごとに toast で知らせる | 2 ★ | Low risk |
| 12ui-design A Design workspace in Claude Code: see design options for a UI as images, select one, ask for more, ask for a | 2 ★ | Low risk |
| subagent-tuner Picks the model and reasoning effort of every subagent: a recommendation by task kind, a band above the prompt | 2 ★ | Review before installing |
| rabe Watch Claude Code's background work: subagents, Codex jobs, shells, monitors, cron jobs and workflows. | 2 ★ | Review before installing |
| streams Untangles the interleaved work in a Claude Code session (prompts, mid-turn asides, subagents, loops) into colo | 2 ★ | High risk |
| swarm Splits a task into independent parts, runs them as parallel subagents you launch and watch live, then hands th | 2 ★ | Low risk |
| queue A prompt queue that runs itself: line up prompts with /queue and they run one after another, pausing when Clau | 2 ★ | Low risk |
| jev-conventions Instant repo-convention checks on every edit: CLAUDE.md, AGENTS.md, style guides and config facts compiled int | 2 ★ | High risk |
| file-radar What Claude touched this session: reads, edits (+/− lines), searches per file, main vs subagent, with flags fo | 2 ★ | Low risk |
| agent-router Picks the model for each subagent by its type (Explore on Haiku by default) and can cap how many run at once. | 2 ★ | Low risk |
| task-band Framed band above the prompt: running subagents, workflows, background shells and monitors, each with its own | 2 ★ | Low risk |
| pixel-pals [k-mods] Claude가 일하는 동안 입력창 위에 냥캣·Clawd·썬더 같은 픽셀 친구들이 지나가고, 턴마다 자라는 펫을 키워요. 엄선한 6가지 장면에 clawd-tales의 Clawd 이야기 | 2 ★ | Review before installing |
| pixel-crew Pixel-art progress bar with the Claude mascot and a side panel that turns your subagents into a crew of charac | 2 ★ | Review before installing |
| vibeship Vibeship: a 3D spaceship where your Claude Code agents work in crew uniforms. Pick the deck, furnish the stati | 2 ★ | High risk |
| litclaude Claude Code-native workflow plugin with a bounded-authority start-work lifecycle. | 2 ★ | Low risk |
| factory Run herdr software factories through this session: it ticks every run, runs a hidden patrol subagent as its ma | 2 ★ | High risk |
| clef-model-router Picks the Claude model and reasoning effort for each turn with Cloudflare Clef, a fast decision model on Worke | 1 ★ | High risk |
| subagent-models Shows each running subagent's model and effort on the hint line above the agent list | 1 ★ | Low risk |
| headway Goal, task and agent progress above the Claude Code prompt — zero setup | 1 ★ | Review before installing |
| afkswitch AFKSwitch by augbastos — Tell your agents when you're away and when you're back. | 1 ★ | Review before installing |
| agent-firewall A live pane of every tool call the agent makes: green when it ran, red when it was blocked, with counters. Ope | 1 ★ | Low risk |
| tristens-tools Tools menu for Claude Code: Clean View, Prompt Upgrade, model/effort control panel, Agent Dock, Roadtrip minig | 1 ★ | Review before installing |
| classify-hint Classifies the user's prompt with Haiku against a few yes/no questions in one call and attaches a rough, non-b | 1 ★ | Low risk |
| verify-reports Attaches a verification reminder to every delivery from another agent: a subagent's hand-back, a background ta | 1 ★ | Low risk |
| breadcrumbs-launcher Starts breadcrumbs' manual-test testers the moment you press Start, without going through the main agent. | 1 ★ | High risk |
| jev-model-router Picks the model and reasoning effort for each task with TypeSafe's Jev. Routes subagent models at agent.spawn | 1 ★ | High risk |
| codex-flow /flow 面板查看和停止本会话派出的 Codex 任务，任务跑满 15 分钟时提醒主 Agent 排查 | 1 ★ | High risk |
| progress-board A pane showing every task and subagent as a colored progress bar with percentage and estimated time left | 1 ★ | Low risk |
| collapse-work Folds a finished turn's work under a "Worked for" row, leaving the final answer, like Codex | 1 ★ | Low risk |
| queue Queues messages sent while Claude is working and sends them one per turn, like Codex | 1 ★ | Low risk |
| stepwarden Every tool call your agent makes, checked before it runs. Verifies each pending tool call against the session' | 1 ★ | High risk |
| task-planner Recomienda modelo, effort y subagentes al empezar una tarea nueva y aplica la eleccion en silencio. | 1 ★ | Low risk |
| agentille One command for Claude Code: /agt plans, builds and reviews with the right model per step, steps aside on smal | 1 ★ | High risk |
| dag-workflow Dependency-ordered DAG workflows of Claude Code subagents, with a live DAG pane | 1 ★ | Review before installing |
| better-tasks Plan and track tasks inside Claude Code, kept as plain Markdown files in your project, with weekly sprints, a | 1 ★ | High risk |
| agentzero AgentRoot for Claude Code: all of AgentRoot, plus hot set loading and a check of the operator's words. | 1 ★ | Review before installing |
| model-router Uses Haiku to pick Opus, Sonnet or Haiku for each sub-agent | 1 ★ | Low risk |
| eval-kernel A persistent JavaScript kernel the model drives with one `eval` tool: state survives between cells, and cells | 1 ★ | Review before installing |
| puzzle Tile puzzles of Obol's shades art while your agents work: swap the pieces until the picture is whole. | 1 ★ | Low risk |
| severance-mdr Macrodata Refinement while your agents work: find the scary numbers and bin them. | 1 ★ | Low risk |
| watchdog Watchdog agents review each update of the agent you work with and push short notes to it. It spawns review sub | 1 ★ | Review before installing |
| workflow-map Live workflow map: one row above the prompt (what is running, what is next, segmented progress) that expands i | 1 ★ | Review before installing |
| otomatik-devir Bağlam doluluğunu durum satırında gösterir; eşik aşılınca işi güvenli bir noktada bitirtir, çalışan subagent'l | 1 ★ | Low risk |
| a2a-mod A2A protocol client for Claude Code: Claude hands tasks to non-Claude worker agents over Agent2Agent and picks | 1 ★ | Review before installing |
| agent-presets Ready-made subagents for focused jobs: debugger, test writer, doc writer and migrator. | 1 ★ | Low risk |
| night-shift Runs your queued tasks at a scheduled time, like overnight, and leaves you a report. | 1 ★ | Review before installing |
| parallel-explore /explore sends three subagents to investigate different parts of the codebase and merges their findings. | 1 ★ | Low risk |
| review-agent Adds a dedicated code-reviewer subagent and a /review command. | 1 ★ | Low risk |
| smart-router Routes every subagent to the right model for the task's difficulty, runs independent work in parallel and star | 1 ★ | Review before installing |
| subagent-cap Caps how many subagents can run at the same time. | 1 ★ | Low risk |
| subagent-monitor Watch running subagents live: type, status, duration and last activity. | 1 ★ | Low risk |
| task-queue /queue lines up prompts that run one after another whenever Claude is free. | 1 ★ | Low risk |
| graceful-stop Winds agents down cleanly as the session's credit runs out and has the orchestrator write a resume memo. | 1 ★ | Review before installing |
| task-list Opt-in persistent task checklist: the agent asks to use it, the user approves, checks items off and alone can | 1 ★ | Review before installing |
| tool-visibility-controller Claude Code plugin for per-agent tool visibility — hide and refuse subagents, skills, MCP and built-in tools p | 1 ★ | Review before installing |
| imagine Generate images with your ChatGPT login (through OpenAI's Codex CLI) and add them to your project | 1 ★ | Review before installing |
| autopilot Multi-agent orchestrator harness for Claude Code: command loop, ledger, dispatch protocol, review cycle, model | 1 ★ | Low risk |
| astir-tui astir inside Claude Code's terminal: a footer count of agents waiting on you, a warning line when no one would | 1 ★ | Low risk |
| agent-warehouse A vector warehouse where the session's agents are little robots: they walk in when spawned, go to the web, fil | 1 ★ | Low risk |
| codex-pet Your Codex pet, living above the Claude Code prompt: it works while Claude works, waits when you are needed, a | 1 ★ | Review before installing |
| chiikawa Chiikawa mode: Hachiware conducts, and the friends from Chiikawa appear as text drawings to take on tasks and | 1 ★ | Review before installing |
| agent-watch Agent Watch: one pane for every Claude Code session on your machine and its subagents, running, waiting for yo | 1 ★ | Review before installing |
| composio-daily Standup pane, seen-this-before error lookup and agent-busy Slack status, through the Composio CLI | 1 ★ | Review before installing |
| model-router Routes each turn to the cheapest model + effort that fits the task (Haiku 5.5 → Sonnet 5.5 → Opus 5.5 → Fable | 1 ★ | Low risk |
| agent-dolls Side pane with one little robot per agent (main and subagents); press one to see its conversation | 1 ★ | Low risk |
| agent-watch Shows one line per running subagent above the prompt: model, task, minutes and its latest tool call | – | Low risk |
| agents-office A pane that shows the session's agents as pixel characters in an office. | – | Review before installing |
| herdr-fleet Pane: every herdr agent, its status and last words, with this pane marked | – | Review before installing |
| agent-pulse A box above the prompt that always says what the agent is doing right now, alive with color and motion: an ani | – | Low risk |
| waypoints A route for /goal and any multi-step work, built from Claude's own task plan: the plan drawn as a line of node | – | High risk |
| agent-theater A pixel theater above the prompt: little orange Claude acts out each tool call at a desk while a monitor shows | – | Low risk |
| agent-chat A side pane with the conversation between Claude and its subagents: what each was asked and what it sent back | – | Low risk |
| agent-toolkit 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。 | – | Review before installing |
| code-modernization Modernizzazione guidata per qualsiasi codebase legacy: parti da /modernize, ottieni una valutazione, una mappa | – | Review before installing |
| workflow-radar Live view of what the model is doing: thinking, writing, tool calls and subagents | – | Low risk |
| coding-agents A coder subagent the main session delegates focused coding tasks to | – | Low risk |
| mod-monitor A pane showing what each mod is doing, the agents they start and the messages passing between them | – | Low risk |
| model-router Rates each coding task with Haiku and runs it on Haiku, Sonnet or Opus | – | Low risk |
| task-planner Plan work with an Opus planner agent and track the steps in a pane | – | Low risk |
| agent-monitor Live pane and status-line count of the agents and subagents running in this session | – | Low risk |
| agent-dock Live panel showing parallel helper agents — set team size, watch cards fill in real-time | – | High risk |
| codex-computer-use Control native Mac apps through Codex, with per-app approval and /codex-cu on|off. | – | Review before installing |
| spider-team Read-only analyst, planner and reviewer subagents; Jev picks each one's model and effort from the task. | – | Review before installing |
| subagent-effort Sets the reasoning effort of every native subagent call from Jev's rating of its task, leaving the model as it | – | Review before installing |
| task-progress Progress bars above the prompt for any long task that writes ~/.local/state/agent-progress/.json | – | Review before installing |
| agent-watch Docks a narrow pane beside the transcript that follows each running subagent live | – | Low risk |
| agent-cats A dashboard of the session's agents as coloured cats: their tasks, skills and run time, their questions answer | – | Review before installing |
| agent-autopilot Answers AskUserQuestion polls for you only when the assistant marked one option (Recommended) and nothing look | – | Low risk |
| agent-shell-watch Always-on status line and a pane for this session's Bash calls, background tasks and Codex/Pi/Devin/OpenCodeRe | – | Review before installing |
| crew Crew: predicts the next step after each answer and suggests the 5 session agents that fit it, drafts a task pr | – | High risk |
| cmdc-worker Claude orchestrates, Command Code (cmdc) implements: a tool that hands a task to cmdc and returns its diff for | – | Low risk |
| week-calendar Weekly calendar and agent-effectiveness report of Claude Code sessions: PRs merged and productive agent time p | – | Review before installing |