404 agents & automation Claude Code mods, most popular first. The most popular is ruflo-adr. Every listing shows its security level and install command.
| Name | Popularity | Security |
|---|---|---|
| ruflo-adr ADR lifecycle management — create, index, reconcile, supersede, check compliance, and link Architecture Decisi | 76.1k ★ | Low risk |
| ruflo-agntcy AGNTCY/Outshift Internet-of-Cognition runtime integration for Ruflo — SLIM secure transport for cross-host age | 76.1k ★ | Low risk |
| ruflo-autopilot Autonomous /loop-driven task completion with learning, prediction, and progress tracking — wraps 10 autopilot_ | 76.1k ★ | Low risk |
| ruflo-deepseek-harness DeepSeek model harness for ruflo — agents, commands, scripts, and skills for running and evaluating DeepSeek-b | 76.1k ★ | Low risk |
| ruflo-goals Long-horizon goal planning, deep research orchestration, and adaptive replanning using GOAP algorithms | 76.1k ★ | Review before installing |
| ruflo-protector Project Anatole: an optional, learning watchdog for unattended agents. Deterministic OWASP-mapped rules, a per | 76.1k ★ | Low risk |
| ruflo-ruos Run ruflo swarm agents on your own ruOS cloud desktops via the tenant-authenticated fleet MCP or per-tenant SS | 76.1k ★ | Low risk |
| ruflo-workflows Workflow automation across two surfaces: the 10 workflow_* MCP tools (create/run/execute/status/list/pause/res | 76.1k ★ | Low risk |
| ruflo-x-gateway Coordinate AI-agent swarms through signed federation messages, channels, and work claims. The remote Claude co | 76.1k ★ | Low risk |
| terminal-browser A browser running directly inside claude code. Preview websites, view HTML documents, and let your agent contr | 3.9k ★ | Review before installing |
| agent-radar One live line above the prompt per running subagent: time, tool count and what it's doing. /radar shows every | 268 ★ | Low risk |
| browser-lanes Shows if this session has a Playwright browser and who holds it. /browser clean closes leftover browsers. A su | 268 ★ | Review before installing |
| merge-gate Holds `gh pr merge` until CI passes and one Codex review (OpenAI's luna model) has run. A PR line above the pr | 268 ★ | Review before installing |
| mission-control /mission opens a live map of the main agent, its subagents and every tool call, plus a code map of the files t | 268 ★ | Review before installing |
| review-watch A live line above the prompt for each running code review: Codex or a review subagent, its model, what it revi | 268 ★ | Review before installing |
| agentctl Agent Control Plane for one Claude Code session: task scope, evidence, hand-over. A control and a display, not | 194 ★ | Review before installing |
| multi-core Claude Code plugin: use ChatGPT (Codex), Cursor, OpenCode Zen, and Antigravity models inside one Claude Code s | 193 ★ | Low risk |
| lane-stack Solo PM conveyor for Claude Code: orchestrator agents, lane playbooks, onboard and resume commands. | 123 ★ | Review before installing |
| flightdeck Flightdeck: a live agent dashboard for Claude Code. Main model vitals, an on-call architect, every permission | 102 ★ | Low risk |
| after A real prompt queue for Claude Code: /after runs it after the current task, without steering. See, reorder and | 91 ★ | Low risk |
| agent-board Inspect the subagents reported by the session. | 76 ★ | Low risk |
| desktop-agent-desk Filter reported agents and copy a status snapshot. | 76 ★ | Low risk |
| console-status Claude Console：跨專案 STATUS、Claude/Codex 派工、工作階段與用量總覽（含手機 Remote Control） | 75 ★ | High risk |
| ase Agentic Software Engineering (ASE) | 60 ★ | Low risk |
| fable-pin Pins every subagent to the fable model: rewrites the model on agent.spawn unless the spawn is a fork, with /fa | 42 ★ | Low risk |
| fables Claude Fables: turns what the agent is doing into little animated cartoons above the prompt, written live by S | 34 ★ | Low risk |
| workflows One loop — work — for work worth doing properly: clarify, an approved plan that is the run's only authority, d | 24 ★ | High risk |
| lemo-assistant 助手：只读子 agent（Haiku），写三行周报 · 点按钮才派；「Claude 可派助手」默认关闭，在「安全」页开启 / Assistant: a read-only subagent (Haiku) that wr | 24 ★ | Low risk |
| saas-marketing Your AI B2B SaaS marketing team: 90 specialist agents in 19 skills across content and editorial operations, SE | 24 ★ | Low risk |
| pi-agent-for-claude pi agent for claude: a `pi` subagent type whose model steps run the pi CLI, so pi subagents and agent-team tea | 23 ★ | Low risk |
| blackbox BLACK BOX RECORDER: structured per-session timeline of prompts, model steps, tool calls, subagents and denials | 22 ★ | Review before installing |
| spike-describe Spike: does a tool.describe rewrite reach the model, does agent.offer hide a type, does prompt.suggest fire? | 22 ★ | Low risk |
| agent-flow The agent flow pane: /flow opens a live tree of the session's subagents and teammates beside the transcript, f | 20 ★ | Low risk |
| model-router Route supported subagent work to Sonnet or Haiku while keeping the main conversation on its model. /router for | 20 ★ | Low risk |
| herdr Drive the herdr terminal workspace manager: panes, tabs, workspaces, and sibling coding agents | 18 ★ | Review before installing |
| codex-computer-use Route Claude's desktop computer use through Codex's computer-use engine, one Codex session per Claude session | 16 ★ | Review before installing |
| agent-narrator Watch the agent work: every step in plain English, with a live time-saved counter | 15 ★ | Low risk |
| agent-race Race Claude Code sessions on a task: live split-screen race track scoreboard | 15 ★ | Review before installing |
| swarm Mission control for subagents and agent teams: who is running, what each is doing, who spawned whom, who is ta | 15 ★ | Low risk |
| story-flow Agentic development workflow covering planning, analysis, implementation, and QA automation | 14 ★ | Low risk |
| almanac KOZMOS Almanac: what this session is made of. Slash commands run, skills invoked, subagent types spawned, MCP | 13 ★ | Low risk |
| blackbox KOZMOS Blackbox: a flight recorder above the prompt. A live Gantt of the current turn: the main loop and each | 13 ★ | Low risk |
| gearbox KOZMOS Gearbox: tool analytics for the session. Per tool its calls, errors and error rate, average, p95 and ma | 13 ★ | Low risk |
| resonance KOZMOS Resonance: a synthesized soundscape for the session. A soft tick per tool, a bonk on failures, a gong a | 13 ★ | Low risk |
| taskforge KOZMOS Taskforge: a live kanban of the session's tasks. TodoWrite lists and TaskCreate/TaskUpdate tasks fall i | 13 ★ | Low risk |
| terminus KOZMOS Terminus: the session's shell history in a sidebar. Every Bash and PowerShell call of the main loop and | 13 ★ | Low risk |
| nanoflow nanoflow by nanosite.ai: your dev workflow, live. Worktrees on their own ports, tickets, PRs/CI, checks and Pl | 13 ★ | High risk |
| flow-scenes Ambient scenes above the prompt that move with your agent's work: a fire, bubbles, surf, ski, rockets, a hot-a | 13 ★ | Low risk |
| workflow-watch Live view of a running Workflow: each stage as it starts and finishes, with what it is doing right now, in a p | 12 ★ | Low risk |
| agents-view A pane listing this session's subagents (Agent tool and workflow agents) with their status; select one to see | 12 ★ | Low risk |
| awsh awsh for Claude Code: an `aw` subagent type whose model steps are answered by a session on the local awsh harn | 11 ★ | Review before installing |
| ua-fallback After a curl or wget an automated-client filter answered 403 or 429, gives the model the browser User-Agent to | 11 ★ | Low risk |
| eklavya Learn while your agent works. Turns coding-agent generation time into adaptive, Socratic learning grounded in | 10 ★ | Review before installing |
| mods-toolbox Mods Toolbox - Function-hook mods (Claude Code 2.1.291+): Clean View, a calm checklist above the prompt for no | 10 ★ | High risk |
| agent-diet Runs search-only subagents (Explore by default) on Haiku instead of your main model; a model Claude asks for s | 10 ★ | Low risk |
| output-diet Trims long shell output, Grep results and subagent reports before Claude reads them (head, tail and error line | 10 ★ | Review before installing |
| activity Live panel of what Claude is doing: running tools with real commands and timers, what is waiting for your appr | 9 ★ | Low risk |
| notify Notification inbox + native OS notifications when a long turn ends, a subagent or background task finishes, or | 9 ★ | Review before installing |
| roadraven-hud RoadRaven pane in Claude Code: live agents on roadmap nodes, batched UAT sign-off, and a backlog you can start | 9 ★ | Review before installing |
| wolfbud WolfBud: a voice coworker (ElevenLabs agent + 3D wolf) that watches the session and can send prompts to Claude | 7 ★ | High risk |
| sysinit-output One-pass local response cleanup without agent retries | 7 ★ | Low risk |
| whats-agent-doing A small box above the prompt that always says what the agent is doing right now (reading, thinking, writing, r | 7 ★ | Low risk |
| typesafe-mod Routes decisions to TypeSafe's Jev model: ranks installed skills for each prompt, and answers the agent's own | 6 ★ | High risk |
| agent-flow A live workflow panel: the main model, the advisor and every spawned agent as cards joined by arrows | 6 ★ | Review before installing |
| aot-evals Part of AOT, the Agent Optimization Toolkit, a Mahal Systems offering. Design, build, measure and iterate the | 6 ★ | Low risk |
| agents-panel Side pane listing project, user and plugin agents with a run button each; /agents-panel toggles it. | 5 ★ | Low risk |
| prompt-queue A prompt typed while Claude is working is held in a stack above the prompt instead of landing in the running t | 4 ★ | Low risk |
| ai-skills Benjamin's collection of Claude Code skills — daily workflow, code quality, dev tools, and specialist agents. | 4 ★ | High risk |
| clocks-band A band above the prompt showing every Bash command, MCP call and subagent that has run for a while, with elaps | 4 ★ | Low risk |
| samurai-dojo A Claude samurai cuts down a Codex, Gemini, or ChatGPT foe for every tool call, and meditates, trains, and due | 4 ★ | Review before installing |
| effort-cycle Change Claude Code's effort level per agent: Ctrl+↑ and Ctrl+↓ step the main thread or the subagent in view, s | 3 ★ | Review before installing |
| crew-chief Difficulty-based routing for Claude Code. You pick the main model and effort; Claude decides what to do itself | 3 ★ | High risk |
| autoresearch Autonomous experiment loop for Claude Code: run, measure, keep or discard. A port of pi-autoresearch. | 3 ★ | High risk |
| agent-mobile-observer 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 | 3 ★ | Low risk |
| jev-router Asks TypeSafe Jev before each task which Claude model and effort fit best, then runs the turn on it | 3 ★ | Review before installing |
| dialog-timeout Ends a turn left on an open dialog (permission prompt, question) for 30 min by default and tells the agent the | 3 ★ | Low risk |
| worklist To-do sidebar next to the chat: queue tasks, even while Claude is working. When Claude is clearly done, the to | 3 ★ | Low risk |
| debugger A step debugger for the agent loop: pause at prompts, model requests, responses, tool calls and results; inspe | 3 ★ | Review before installing |
| jev-gate-router Routes the main thread's effort and each subagent's model and effort with one TypeSafe Jev assessment; on by d | 3 ★ | Review before installing |
| ricky-pixel-mod Ricky, a pixel-art cat companion for Claude Code: an animated night-sky pane with a task / subagent / activity | 3 ★ | Low risk |
| savings-meter Keeps a ledger of what output-trimmer, subagent-router and auto-effort save, shown by /savings | 3 ★ | Low risk |
| subagent-router Runs search subagents on Haiku and general-purpose ones on Sonnet, and /orchestrate splits a big task across s | 3 ★ | Low risk |
| aquarium-widget An aquarium with a fish for every running tool call and agent. | 3 ★ | Low risk |
| earpiece-widget Every running subagent with the tool it is on and its last sentence, and /whisper slips one of them a note wit | 3 ★ | Low risk |
| queue-widget A queue of prompts that run back to back while you are away, a gate command each must pass before the next sta | 3 ★ | Review before installing |
| race-widget A race track for parallel subagents: each advances one stride per tool call, with a podium as they finish. | 3 ★ | Low risk |
| agent-bridge Talk to OpenAI Codex from Claude Code: live peer messaging over a local pipe, plus headless delegation (ask_co | 3 ★ | Review before installing |
| archon-panel An Archon pane in the side panel: this project's workflow runs, their graphs and logs, and the approvals that | 3 ★ | High risk |
| whats-next A pane in the side panel listing the next steps of your dev workflow, filled by /ask-sean; click a step to see | 3 ★ | High risk |
| harness-scope Turn global skills, rules, agents and tools on or off per repo with named profiles | 3 ★ | Low risk |
| rescene RESCENE fan mod: WONI conducts while LIV, MINAMI, MAY and ZENA take the subagent and Orca worker tasks and rep | 3 ★ | High risk |
| claudetto-browser Drives a browser with `agent-browser`, or with CloakBrowser on sites with bot detection when the user chooses | 3 ★ | Review before installing |
| dcc-plugin-agents-md Loads `AGENTS.md` files where Claude Code loads `CLAUDE.md`: the user folder, each ancestor of the working dir | 3 ★ | Low risk |
| heavens-feel Heaven's Feel cast for your agents: Sakura watches over the main session, Servants answer every subagent | 3 ★ | Low risk |
| live-vibe /live: full-duplex voice (Kyutai streaming STT with semantic end of turn, or Silero and Whisper; Kokoro TTS) t | 2 ★ | High risk |
| subagent-limits Keeps subagents small: tells the main agent how to size and split work, asks a growing subagent to checkpoint, | 2 ★ | Low risk |
| agent-quick-menu A pane and prompt band for plugin commands declared in quick-menu.json, plus plugin and Claude Code settings e | 2 ★ | Review before installing |
| agent-models Each Claude subagent's model and effort in the native agent list, beside its task | 2 ★ | Low risk |
| codex OpenAI Codex as native Claude Code subagents: the Agent tool starts one and the mod drives codex app-server in | 2 ★ | Review before installing |
| codex-computer-use Claude thinks, Codex clicks: routes Claude's desktop computer use through Codex's computer-use engine (exact v | 2 ★ | High risk |