404 agents & automation Claude Code mods, most popular first. Every listing shows its security level and install command.
| Name | Popularity | Security |
|---|---|---|
| mefisto Harness opinionado de Claude Code para construir aplicaciones serverless en Azure con Event Driven Architectur | – | High risk |
| subagent-tree サブエージェントの親子関係と実行状態を枠付きペインにツリー表示する mod | – | Low risk |
| codex-board Codex 리뷰·작업 진행 상황을 우측 패널 대시보드로 표시 | – | Low risk |
| effort-gate Denies a subagent or background session running Opus at xhigh or max effort unless the user said so | – | Review before installing |
| route-ledger Records which model and effort each subagent or background session ran at and how it went, with /routing-revie | – | Low risk |
| tidepool Low tide for Claude Code: every tool, agent and background job on a timeline beside your chat, plus a themed t | – | Review before installing |
| task-progress Right-side pane that monitors any session (model vitals, tasks, agents, skills, tool activity) plus the superp | – | Low risk |
| function-hooks Shared command policies for Claude Code and Codex | – | Review before installing |
| ledger The record of orchestrated work: runs of units and tasks, the subagents spawned for them, each gate's verdict | – | Review before installing |
| parked A backlog of items needing your attention, parked by you or the orchestrator, kept per session and listed acro | – | Review before installing |
| sage-relay Hands a long Claude Code chat off to a fresh one automatically: saves a full note, clears, carries on. Optiona | – | Review before installing |
| visualize Pixel-art view of what the agent (and each subagent) is looking at and thinking about, driven by tool calls an | – | Low risk |
| escritorio-time Painel com o escritório do time em pixel art, animando o fluxo real da demanda entre os agentes. | – | Low risk |
| departure-board A Solari split-flap departure board for the agent's real work: tasks flip letter by letter in amber as they bo | – | Low risk |
| inline-tribunal A second_opinion tool and /tribunal command: your diff is reviewed by Codex and Grok side by side, read-only, | – | Review before installing |
| loop-breaker Stops the agent repeating the same failing command or undoing its own edits, and shows a stuck meter above the | – | Low risk |
| process-concierge Gives every dev server, watcher and background process the agent starts an owner, a port and a stop button, an | – | Review before installing |
| mission-control A graphical pane of the harness at work: every agent of the turn as a swimlane coloured by phase, bar height i | – | Low risk |
| zetetic-genius Grades every request before its turn starts (task class → effort rung, in one low-effort completion) and route | – | Review before installing |
| zetetic-insights The learning loop: every main turn is kept in a ledger across sessions (phase, effort, steps, failed tool call | – | Review before installing |
| proc-registry Registry of background processes and subagents: /procs command, Processes panel, counter in the status line. | – | Low risk |
| model-router Runs chosen subagent types on cheaper models (Explore on Haiku by default) and adds /router to switch the main | – | Low risk |
| vivarium Shows each subagent as a pixel Clawd in a strip above the prompt: walking while it works, asleep when it finis | – | Low risk |
| work-folder Denies a new agent working file (plan, evidence, prototype, scratch, report, probe test) outside .claude/work/ | – | Low risk |
| ext-agent Run Claude Code subagents in pi or opencode instead of a Claude model. Adds the ext-agent:worker agent type; b | – | Low risk |
| aq Pane for the per-repo aq prompt queue: pick items, batch them into the prompt box, queue drafts, and let Claud | – | High risk |
| prompt-queue Codex-style queued follow-up inputs: the queue key while a turn runs holds the prompt until the turn ends, one | – | Review before installing |
| agent-cockpit The instruments around each Claude Code session: themed status line, TTSR and layered rules, AGENTS.md and APP | – | High risk |
| agents-panel Running subagents, their latest tool call and progress bars in a side panel. | – | Low risk |
| revisor-com-prova Quando volta o resultado de um revisor (Codex, agy, council), lembra o Claude de que achado sem prova não cont | – | Low risk |
| sonnet-por-padrao Subagente e agente de script (Workflow) criados sem modelo escrito rodam no Sonnet em vez de herdar o Opus; Op | – | Review before installing |
| modder One orchestrator over every Claude Code session you have open, with Jev (TypeSafe System One) deciding which o | – | Review before installing |
| pixel-agents Animated pixel characters for running subagents, drawn under the prompt | – | Low risk |
| legion-mod Legion's order of agents inside Claude Code: thirteen named agents, threads, approvals and a shared Library, i | – | Review before installing |
| legion-mod-runner Companion to Legion Mod: starts, resumes and stops Legion's agents for it. Install both; it does nothing on it | – | Low risk |
| downrange A band, pane, and /downrange table: progress, ETA, and last output for Claude Code background shells and Monit | – | Review before installing |
| high-command See the messages your teammates, named subagents, and other Claude Code sessions send you, grouped by peer wit | – | Low risk |
| clef-gate Asks a local Clef decision model whether an expensive tool call or subagent is actually needed before Claude C | – | Review before installing |
| clef-model-router Picks the Claude model and reasoning effort for each turn with Cloudflare Clef, a fast decision model, on Work | – | High risk |
| codex-bridge Chat with OpenAI Codex CLI inside Claude Code: Codex answers in the same conversation with native tool rows, d | – | High risk |
| no-hands Hands-free voice mode for Claude Code on Apple Silicon Macs: talk any time, hear short spoken replies, interru | – | Review before installing |
| agent-watch Keeps the number of running Claude Code sessions under a limit and shows the ones waiting on you or sitting id | – | High risk |
| crew An always-on team of AI agents on your own computer: chat with them in the Crew window, and they work with you | – | Review before installing |
| clawd-park A pixel dinosaur park under the spinner: a coral T-rex acts out the agent's work, and every failing test run b | – | Low risk |
| sdd-control-plane SDD capability 10: aggregate read/delegate view, derived nextAction and configuration view. Not an orchestrati | – | Review before installing |
| agent-skills Loads skills from the cross-harness .agents/skills directories (project and ~) into Claude Code: listed for th | – | Low risk |
| pi-outliner Pi Outliner integration for Claude Code, following the outline the session folder is bound to: typed outline, | – | Review before installing |
| prompt-queue Keeps the prompts you send while Claude works in a queue, and sends them one by one once Claude has finished. | – | Low risk |
| multiharness-delegation Route Agent calls with subagent_type multiharness-delegation: to an interactive external harness in tmux | – | Low risk |
| pixel-pets An animated Claude pet above the prompt while Claude works, plus a small colored pet for each running subagent | – | Low risk |
| ghost-typist Types out the code the agent writes, live, in a side pane with keyboard sounds | – | Low risk |
| repo-sessions Pane listing the Claude Code and Codex sessions working in this repo or folder | – | Low risk |
| task-progress Live progress bars above the prompt for background shells and subagents | – | Low risk |
| wait-queue /q holds prompts until the running turn ends and sends them one per turn; a band above the prompt lists, edits | – | Low risk |
| progreso Progreso del plan sobre el prompt: fase actual, barra por fases, subagentes, tiempo transcurrido y estimación | – | Low risk |
| subagentes Obliga a Claude a elegir el modelo de cada subagente según el reparto Sonnet/Haiku/Opus/Fable | – | Low risk |
| subagent-effort Run each subagent on any model (gpt-6, grok-4.7, ...) at any reasoning effort, through model and effort parame | – | Low risk |
| mission-control Live view of what Claude is executing: every tool call with its input, output and status, subagents in their o | – | Low risk |
| agent-watch Flags risky Bash commands and writes to sensitive paths in a live sidebar pane, with a status-line tally. | – | Low risk |
| cc-sidecar See what codex, claude and gemini do when Claude Code delegates to them from Bash | – | Review before installing |
| delegator Every subagent Claude starts waits for your approval: approve, refuse, approve all for the turn, change its mo | – | Review before installing |
| supervisor-pane A side pane that lists subagent runs and chosen shell commands with their state and elapsed time. | – | Low risk |
| roteador-subagente Roteador de subagente: escolhe o modelo de cada subagente (Explore no haiku, general-purpose no sonnet...) sem | – | Low risk |
| carousel-ship After a carousel render: Caption, Queue Threads and Log ledger buttons; blocks Threads posts with a part over | – | Low risk |
| hybrid-agents Subagents default to Sonnet; pasting a plan path adds the hybrid rule (inline small tasks, Sonnet subagents fo | – | Low risk |
| agent-monitor Live steps of the subagents Claude starts (their text and grouped tool calls), in up to 3 stacked windows (the | – | Low risk |
| shell-monitor Live output of the background shells Claude starts, in up to 3 stacked windows (the rest queued) | – | Low risk |
| alvearium Alvearium (formerly session-board): one ticket board for all your Claude Code sessions and agents, terminal an | – | Review before installing |
| spotcheck Checks the files, line numbers and symbols a subagent cites before Claude repeats the report. | – | Review before installing |
| plan-board Side pane for Claude Code: the session's goal, the superpowers plan's progress, tasks and running subagents | – | Low risk |
| spec-flow [mod] [skills] Turns a feature request into a spec, one approved step at a time: clarify the request (asking y | – | Review before installing |
| session-todo A live todo pane for the session: the agent keeps it current through a tool, you read and tick it without aski | – | Low risk |
| jet-router Experimental Claude Code effort router: fake and opt-in Jev shadow | – | Review before installing |
| model-router Picks the right model for every subagent without being told: Haiku for lookups, Sonnet for building, Opus for | – | Low risk |
| 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 |
| flightdeck Flightdeck: a live agent dashboard for Claude Code. Main model vitals, an on-call architect, every permission | – | Low risk |
| agent-flow The agent flow pane: /flow opens a live tree of the session's subagents and teammates beside the transcript, f | – | Low risk |
| agentpane A side pane listing every helper agent in the session: what it does, how long it has run, and when it finishes | – | Low risk |
| codex-pet Your Codex pet in Claude Code: above the prompt and as a desktop pet that follows both Claude Code and Codex. | – | Review before installing |
| lens-view Open lens traces (J-lens, logit lens) in a terminal viewer beside the agent, in tmux | – | Low risk |
| agent-model-badge Shows which model (Sonnet 5.5, Opus 5.5, Haiku…) each subagent runs on, on its Agent row and in the agent view | – | Low risk |
| agents-pane /agents-pane opens a sidebar listing available agents in their configured colors, with a Run button each | – | Low risk |
| agent-theater A pixel theater under the prompt: the little orange guy acts out what Claude is doing, with Haiku narration in | – | Review before installing |
| swamp-watch Status line, pane and toasts for swamp workflow runs in the current repo and a swamp serve server | – | Low risk |
| 12ui A Design workspace in Claude Code: see design options for a UI as images, select one, ask for more, ask for a | – | Low risk |
| msgate-agents msgate-agents: ready-made agent types (second opinion, code review, cross-check, expert persona, delegation, a | – | Low risk |
| progress-buddy A progress band with a little coral friend for Claude Code: task and subtask lines, a gradient progress bar, s | – | Low risk |
| agent-card Styled Agent Card workflow with live lifecycle, task, worker and gate UI | – | Low risk |
| progresso Barras de progresso acima do prompt, com faixas de subagentes e comandos em background e som ao terminar, falh | – | Review before installing |
| help-offers Turns the 'How I can help' list at the end of an answer into buttons that start a subagent for each offer | – | Low risk |
| model-router 調査系のサブエージェントだけ Haiku で動かし、メインのモデルを固定する | – | Low risk |
| repo-radar A live map of your codebase that lights up where Claude is working: reads glow cyan, edits amber, errors red, | – | Low risk |
| output-folders A pane listing the folders that tools, scripts and agents wrote into this session, with what changed in each. | – | Review before installing |
| mod-installer Type /mods to preview the workflow mods, tick the ones you want and install them. | – | High risk |
| agent-model-router Picks the model each subagent runs on from a per-project table, steps up a model when a task is retried, and l | – | Low risk |
| turn-limits Counts, per agent type, the agent invocations of this session that stopped at their turn limit | – | Low risk |
| closing-time 🔔 Closes the PR loop: watches a PR until CI and agent reviews are green, and weighs review comments before act | – | Review before installing |
| allan Allan's workflow mods, built from his own session logs. Every feature has its own on/off row in /config and is | – | High risk |
| run-board A pane and toasts for background shells, monitors and subagents: status, elapsed time, latest output line, exi | – | Low risk |
| artifact-watchdog Enforces the subagent output contract: watches each Agent dispatch's artifact file, flags a 5-minute stall, wa | – | Review before installing |