ModsCode / Claude Code Mods / Ranking / Tasks & agents

• ruflo-protectorProject Anatole: an optional, learning watchdog for unattended agents. Deterministic OWASP-mapped rules, a per-project behavioural baseline, four modes (off, learn, notify, enforce), alerts you can read later.ruvnet★ 74,323
  9 more in this repository

  • ruflo-swarmAgent teams, swarm coordination, Monitor streams, and worktree isolation — wraps 4 swarm_* + 8 agent_* MCP tools (12 total) plus 6 topologies (hierarchical / mesh / hierarchical-mesh / ring / star / adaptive). With Claude Code function hoo…ruvnet★ 74,323
  • ruflo-agentAgent runtimes for ruflo — local WASM-sandboxed agents (rvagent: 10 wasm_agent_*/wasm_gallery_* MCP tools, built on @ruvector/rvagent-wasm + @ruvector/ruvllm-wasm per ADR-070) plus Anthropic Claude Managed Agents as a cloud backend (manage…ruvnet★ 74,323
  • ruflo-autopilotAutonomous /loop-driven task completion with learning, prediction, and progress tracking — wraps 10 autopilot_* MCP tools (status/enable/disable/config/reset/log/progress/learn/history/predict)ruvnet★ 74,323
  • ruflo-daaDynamic Agentic Architecture — 8 daa_* MCP tools for adaptive agents (create/adapt), cognitive patterns, workflows (create/execute), knowledge sharing, and learning/performance metrics. Feeds the JUDGE phase of the 4-step intelligence pipe…ruvnet★ 74,323
  • ruflo-deepseek-harnessDeepSeek model harness for ruflo — agents, commands, scripts, and skills for running and evaluating DeepSeek-backed workflows within the ruflo swarm.ruvnet★ 74,323
  • ruflo-federationCross-installation agent federation with zero-trust security, peer discovery, consensus-based task routing, and per-call budget circuit breaker (ADR-097)ruvnet★ 74,323
  • ruflo-goalsLong-horizon goal planning, deep research orchestration, and adaptive replanning using GOAP algorithmsruvnet★ 74,323
  • ruflo-observabilityStructured logging, distributed tracing, and metrics — correlate agent swarm activity with application telemetry. As a mod (ADR-445): a tighten-only guard on its tools, /observe-mod, and a status file the console showsruvnet★ 74,323
  • ruflo-ruosRun ruflo swarm agents on your own ruOS cloud desktops via the tenant-authenticated fleet MCP or per-tenant SSH; optional and removable (ADR-405)ruvnet★ 74,323
• moai-boardRead-only side panel for the MoAI kanban queue, factory lanes and SPEC documents. Actions: refresh, open, pick (confirmed).MoAI-ADK★ 1,230
• remctlApple Reminders in Claude Code: RemCTL's tools, plus today's tasks above the prompt in your lists' colors.Federico Viticci★ 595
• quiz-afterAfter a turn that finished a task, a forked check writes 2-3 questions about what was built and draws them above the promptDanny McAteer★ 536
• usage-dashQuota, Claude sessions and background jobs paneaqua5230★ 338
• task-orchestrator-modOpt-in Claude Code mod for MCP Task Orchestrator: live work graph, gate band, and in-process orchestration hooks (early-access function-hooks API)Jeff Picklyk★ 208
• agentctlAgent Control Plane for one Claude Code session: task scope, evidence, hand-over. A control and a display, not an isolation boundary.sd0xdev★ 192
• agent-radarOne live line above the prompt per running subagent: time, tool count and what it's doing. /radar shows every agent and its messages.Hamza Zafar★ 184
  2 more in this repository

  • mission-control/mission opens a live map of the main agent, its subagents and every tool call, plus a code map of the files they touch.Hamza Zafar★ 184
  • switchboardPicks the model for each subagent that names none, with OpenAI's Decisions API or Jev, from its short label only. One line per spawn above the prompt; /route shows each pick and what each subagent cost.Hamza Zafar★ 184
• lane-stackSolo PM conveyor for Claude Code: orchestrator agents, lane playbooks, onboard and resume commands.VKirill★ 122
• archcoreSpec-driven development and context engineering for AI coding agents, backed by project context in Git.Archcore★ 68
• savvy-progressProgress bar above the prompt for /savvy-flow, plus an agents panel (/agents-info): running, finished and planned subagents with model, task progress, context, cost and time.johnnyvizz★ 53
• drift-fuseScores each unattended turn against the task the person asked for with TypeSafe's Jev model, and after consecutive off-task turns redirects or pauses the next machine-submitted prompt.Darkroom Engineering★ 47
• think-firstAsks what you expect while a long task runs, then shows how your predictions hold uppetekp★ 47
• flight-recorderSee inside a turn: a live Gantt timeline of model requests, tool calls and subagents, with tokens and cost per lane.Prompt Advisers★ 40
  1 more in this repository

  • model-routerRoute supported subagent work to Sonnet or Haiku while keeping the main conversation on its model. /router for controls.Prompt Advisers★ 40
• fable-pinPins every subagent to the fable model: rewrites the model on agent.spawn unless the spawn is a fork, with /fable-pin on, off and status. Touches nothing but its own store. Needs function hooks (early access).Karan Bansal★ 35
• kindex-modernRepo-local Kindex memory and durable tasks for Claude function hooks (Claude Code mod, 2.1.287+)Wander★ 35
• harness-modsHarness Mod layer: heartbeat/canary, native usage, rewrite explanations, measured subagent accounting, supervisor routing, secret redaction. Modes per guard in ~/.claude/mods/mods-config.json (classic | shadow_mod | mod).Wes Sander★ 28
  3 more in this repository

  • supervisorSUBAGENT SUPERVISOR: routing-and-budget Mod. Rewrites a spawn's model onto the capability graph instead of denying it, keeps a measured per-agent-type token ledger in $.store, caps tool calls per subagent, and shows live subagents + the la…Wes Sander★ 28
  • probe3Permission override, subagent visibility, agent.spawn model rewrite, turn.step routing, prompt context injectionucsandman★ 28
  • blackboxBLACK BOX RECORDER: structured per-session timeline of prompts, model steps, tool calls, subagents and denials; /blackbox prints itucsandman★ 28
• delegation-driftCounts main-thread work since the last subagent dispatch, nudges the model to delegate at every tenth call, and refuses foreground poll loops.BioInfo★ 27
• pi-agent-for-claudepi agent for claude: a `pi` subagent type whose model steps run the pi CLI, so pi subagents and agent-team teammates live in Claude Code's own agent UI, streamed live.Fazal Ali★ 23
• thimble-termthimble's terminal-mode renderer: it draws thimble's cards, citations, labels, agents, side threads, documents and files in Claude Code. It only draws; the `thimble` command loads it in terminal mode.thimble★ 18
• agent-flowThe 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 no pane can be drawn.Charles Tao★ 16
• 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 writes a three-line report · sent only when you press its button; "Claude can send the assistant" is off by default, switch on in S…lemomo★ 16
  2 more in this repository

  • lemo-todo笔记：在面板记下笔记 · 压缩后自动摘要（Haiku）默认关闭，在「安全」页开启 / Notes: keep notes in the panel · Auto summary after compaction (Haiku) is off by default, switch on in Safetylemomo★ 16
  • lemo-voice朗读：超过 30 秒的任务完成时，朗读编号和用时 · 默认关闭，在「安全」页开启 / Speech: reads out the message number and time when a task over 30 s finishes · off by default, switch on in Safetylemomo★ 16
• routerModel and effort routing for the main conversation by task difficulty and activity, advised by a prompt classifier (Jev, Clef, Clef Flash, OpenAI or local Ollama). Subagents get one model at spawn: every agent that does not pin one.Alexei Ledenev★ 16
• ccprogressA progress bar of the current task above the spinner, in the terminal and the Desktop appamigoer★ 14
• leitstandA control room above your prompt: background agents and shells, disk space and context at a glance. Two themes, loud and quiet. /stand toggles the list.Dominik Martin★ 14
• orbitDurable tasks, sandboxed parallel runs, and PR-gated delivery for AI coding agents. Adds Orbit's MCP tools and workflow skills to Claude Code.constellation-works★ 14
• agents-viewA 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.ushironoko★ 12
• human-in-the-loopClaude assigns you the tasks only you can do. They wait in a My tasks pane, counted under the prompt, until you answer or reject them, so nothing Claude needs from you gets lost in the chat.Tzafrir Rehan★ 12
• awshawsh 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 daemon can drive runs as a native Claude Code subagent, streamed live. Also carrie…Aitherium★ 11
• paf-tasksphone-a-friend, made legible: every review as a thread of rounds with its verdict and findings, live progress while a reviewer works, and the agent sessions that need youBruno Freiberger★ 10
• hivemindKOZMOS Hivemind: the agent swarm as a live tree. The main loop at the root and every subagent beneath its parent, each with a status glyph, type and task, model and effort, elapsed time, requests, tokens, estimated spend, context fill and …KOZMOS★ 9
  3 more in this repository

  • orreryKOZMOS Orrery: subagents as planets circling a central sun above the prompt. Running agents orbit at a speed set by their tokens per second, finished ones settle into a faint outer ring, failed ones flash a red cross; a legend names up to …KOZMOS★ 9
  • questlineKOZMOS Questline: task progress above the prompt. One segmented bar for the session's todos and tasks (done green, running violet and pulsing, waiting gray), the count, what is running now and for how long. Hides itself two minutes after e…KOZMOS★ 9
  • taskforgeKOZMOS Taskforge: a live kanban of the session's tasks. TodoWrite lists and TaskCreate/TaskUpdate tasks fall into Pending, In progress and Done columns with the active form, time in the column and the owning agent, under a progress bar. /t…KOZMOS★ 9
• pinboardKeeps open decisions, the task list and links Claude creates in a sidebar pane, updated through its own toolJerad Bitner★ 9
• usage-bandShow 5h / 1w rate limits and this session's task progress above the promptluvpame★ 9
• goal-meterA progress bar for /goal built from Claude's own task plan: tasks done out of the plan, elapsed time, an ETA at the goal's own pace, and every chat's goal in /goalsNate Herk★ 8
• viberFrom idea to committed code: interview, reviewed plan, task-by-task build, project memory that grows with every build.Dariusz Lenartowicz★ 8
• bg-tasksShows the background shell tasks of the session on the status line or in the shared sidebar, with the oldest one's age, and stops one from the /bg-tasks pane.Kerem Gok★ 7
  3 more in this repository

  • subagent-ledgerShows each subagent of the session with its turns, time, model and tokens, the costliest first, yellow while it runs and green once it answered, and marks one that passed the token limit.Kerem Gok★ 7
  • effort-autoHas a small model rate how hard each prompt is and runs that turn and its subagents at the matching effort, within the levels you allow, on the models whose prompt cache survives an effort change.Kerem Gok★ 7
  • task-pokeSubmits a continue prompt while the task list has unfinished tasks, at most 99 times in a row by default, and turns the task tools on for every model unless CLAUDE_CODE_ENABLE_TODO_TOOLS is set.Kerem Gok★ 7
• command-centerOne pane for the whole session: the original intent and drift, subagents and background shells with model, tokens, idle and typical duration, files changed, and the last reply with its open questions.Justin Johnson★ 7
• taskcutCompacts when the work moves on from one sub-task to the next instead of when the context window fills, including in the middle of a long turn. Once the context is past a floor, a model judges each step, reading what you asked for and wher…Yangze Luo★ 7
• gsd-status-modA Claude Code mod for GSD projects: a live pane (roadmap, agent tree with forks, cost and context, work streams, session log, pace and fit forecast, timeline, trends, a markdown reader) plus a status band, a next-action hint and /gsd-statu…Helen Kwok★ 6
• notifyNotification inbox + native OS notifications when a long turn ends, a subagent or background task finishes, or Claude is stuck waiting for your approval.Michael Goldenberg★ 6
• roadraven-hudRoadRaven pane in Claude Code: live agents on roadmap nodes, batched UAT sign-off, and a backlog you can start or prioritiseShuffzord★ 6
• todo-barThe task list's progress in a band above the prompt, read from the todo and task tools' own calls: no tool, no prompt, no tokenshoobnn★ 6
• batonPass tasks between named Claude Code sessions: the receiver queues them, works each to a pull request, reports back and picks up the next. A band and panel show your sessions and tasks.Ashish S Kumar★ 5
• mission-controlLive coding-orchestrator cockpit: relay context zone, subagents in flight, report-card grades and the Jev decision feed.davesheffer★ 5
• roadmapRoadmaps as a dependency graph: JSON source of truth, mechanical status recompute, projected task lists, Mermaid diagrams, an HTML dashboard, the interview, review and next-task skills that drive it, and /ready, a pane that shows the ready…Jason Warren★ 5
• todosShows the repository's TODOs in a scrolling band above the prompt, newest first: TODO.md items and TODO/FIXME/HACK code comments dated with git blame, a Mine filter, issue links, picks put in the prompt for Claude, and a toast when an edit…Augustin BENGOLEA★ 5
• agent-dietRuns 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 the model.Vedant Andhale★ 4
  2 more in this repository

  • output-dietTrims long shell output, Grep results and subagent reports before Claude reads them (head, tail and error lines kept); the untrimmed text is saved to a file Claude can open.Vedant Andhale★ 4
  • peekTyping "status" while background shells or subagents run opens a pane with each task's exact elapsed time, the tail of its output and any percent it printed, instead of sending the prompt to Claude. /peek opens it too. No tokens spent.Vedant Andhale★ 4
• agentsSubagent pane and strip above the prompt: a crab per agent type with model, effort, context, tokens, requests and the latest tool call.ThisaruGuruge★ 4
  2 more in this repository

  • mission-controlA /mission-control pane showing live agents, recent tool calls and files touched this session.ThisaruGuruge★ 4
  • rabeWatch Claude Code's background work: subagents, Codex jobs, shells, monitors, cron jobs and workflows.Lorenz Hilpert★ 4
• jevThree-level decision layer on TypeSafe's Jev: picks model and effort per session and per subagent, compacts context without rewriting it, and gates code review with calibrated closed questions. Pairs with lexi: the review runs after the la…Savino Fiore★ 4
• mokkanCross-session reminders: /mokkan toggles a live pane with your TODOs, Reminders and Archived tabs, /mokkan <command> runs push, in, edit, ack, done and the rest at once, and the /mokkan:mokkan skill lets Claude do it for you.Victor Benetatos★ 4
• plan-progressPane showing what's left in .scratch/<branch>/plan.md and the live task listJeremy Winterberg★ 4
• specialists-uiTeammate-style transcript rows for Specialists in Claude Code: channel wakes, the fallback wake, and Specialists MCP tool calls under native labels. Companion to the specialists plugin, which raises those rows and therefore cannot draw the…XTRM★ 4
• straw-bossRoute work through the smallest sufficient loop: handle bounded tasks directly, fan out clear branches, or coordinate durable app-rooted Claude and Codex workrooms with provider-neutral status and git lifecycle tracking.Wei Hung★ 4
• agent-boardInspect the subagents reported by the session.Yash Thakker★ 3
  5 more in this repository

  • desktop-agent-deskFilter reported agents and copy a status snapshot.Yash Thakker★ 3
  • release-checklistKeep a persistent checklist for a release.Yash Thakker★ 3
  • stopwatchTime a task with start, pause, and lap markers.Yash Thakker★ 3
  • task-boardAdd tasks and toggle done status.Yash Thakker★ 3
  • todo-finderFind TODO, FIXME, and HACK notes in tracked files.Yash Thakker★ 3
• agent-routerChoose 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 function hooks enabled.Alexander Nicholson★ 3
  1 more in this repository

  • keepaliveA prompt cache bar for every conversation, subagent and teammate, a dashboard with /keepalive, per-conversation cache TTLs, and upkeep that keeps an idle cache warm or compacts it before it expires. Requires Claude Code Mod function hooks …Alexander Nicholson★ 3
• agent-watchSubagents at a glance: tokens per agent, a toast when one stalls, and a summary naming the heaviest agent when they finishLucas Fernandes★ 3
• agentpaneA 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.Anji Xu★ 3
• debuggerA step debugger for the agent loop: pause at prompts, model requests, responses, tool calls and results; inspect and edit them; play, step or stop.nadav-grs★ 3
• delamainRun a hub session that spawns and steers detached Claude Code and Codex agents: briefs, a shared journal, inboxes, an owner-question register, a lock board, handoffs, and the agent-top console.Ilya Kozyrev★ 3
• dotclaudeAdds a lean output style, five role agents, and a status line command. Adds hooks that ask before work on a repo with an AI policy, check edits and `git` calls, bound the context of subagents, and check Markdown line breaks and drift. Sets…xsyetopz★ 3
• jev-gateJev Gate in one plugin: the orchestration gate, the extractive compactor, the Vitest log folder, the Jev effort and model router and the jev_evidence tool. Every part is on by default; each has its own on/off option.MongLong0214★ 3
• jev-routerAsks TypeSafe Jev before each task which Claude model and effort fit best, then runs the turn on itdominicrico★ 3
• ricky-pixel-modRicky, a pixel-art cat companion for Claude Code: an animated night-sky pane with a task / subagent / activity / files board, a cat in the band above the prompt, and a purple-gold spinnermuxia23★ 3
• subagent-meterA live status line showing how much of your session's tokens go to subagents, and which agent type uses the most.Naren★ 3
• worklistTo-do sidebar next to the chat: queue tasks, even while Claude is working. When Claude is clearly done, the to-do is checked off and the next one starts; otherwise the list stops with a reason and buttons (Continue keeps the order). Runs b…Fynn Hansen★ 3
• agent-fleetDashboard of running Claude sessions: context, active/idle, subagents, workflows and who messages whomVladLeus★ 2
• agent-petsAgent Pets: live limits for the Agent Pets widget, /pets, nudges about other agents and a pixel pet above the prompt.Marczelloo★ 2
• agent-raceRace Claude Code sessions on a task: live split-screen race track scoreboardOneWave AI★ 2
  1 more in this repository

  • swarmMission control for subagents and agent teams: who is running, what each is doing, who spawned whom, who is talking to whom, and how they overlapOneWave AI★ 2
• agent-swarmMission control for your subagents: every spawned agent becomes a live, animated card above the prompt, with its phase, effort, tools, cost and a timeline you can followJeff Arese★ 2
• agent-usage-guardA 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 agents across every session, and asks in Claude Code's own dialog.Riccardo Bartoli★ 2
• agents-panelSide pane listing project, user and plugin agents with a run button each; /agents-panel toggles it.Boom-Vitt★ 2
• cf[Experimental] Contract-driven development pipeline with human-in-the-loop decision gating — agents defined by Context + Goal + Tools, not roles; a live flow-progress band above the prompt (Claude Mod; needs Claude Code 2.1.293+)Nick Huang★ 2
• concurrency-guardCaps parallel subagents and monitors; more need a stated reason and the user's approvalMichael Prömpler★ 2
• dossierEngineering workflow in one resumable DOSSIER.md: dependency-ordered tasks, invariants, drift detection, cross-repo state, a rolling status log, and scout + reviewer subagents.Mrugesh Mohapatra★ 2
• effort-cycleChange Claude Code's effort level per agent: Ctrl+↑ and Ctrl+↓ step the main thread or the subagent in view, shown as a colored meter in the footer (‹ › to click on hover) and in the tasks list's subagent rowsAner Cohen★ 2
• fleet-orchestrateclaude-fleet orchestration: /fleet-orchestrate takes the orchestrator role (take_role) in a session that holds no issue — talk a request through, then hand it to worker sessions; its state and role ride a compaction (hooks), /qd files and …verkyyi★ 2
• game-party/party: each subagent of the session with ACTIVE, CLEAR or FAIL, a bar of its tool calls and its job; opens by itself when one starts on a wide terminalReason of Moon★ 2
  1 more in this repository

  • game-quest/quest: the task list as a quest log (✓ done, ▶ in progress, · to do, the last one the BOSS), kept across /compact and into the next session in the same projectReason of Moon★ 2
• harness-scopeTurn global skills, rules, agents and tools on or off per repo with named profilesshimo4228★ 2
• human-tasksA persistent pane of actions Claude needs you to run: tick them off, pick an outcome, or reply, and Claude is toldAndrew Stephenson★ 2
• logbookKeeps a live local page for a long Claude Code task: what needs you, what was built, what was verified, and what was decided without you. Hooks record it without spending model tokens, the page follows light, dark or your system's setting,…Agulhas Labs★ 2
• mc-laneReports this Claude Code lane's tool calls (names and timings only), subagent starts, context use and cost to Mission ControlUnite-Group★ 2
  1 more in this repository

  • fleet-guardKeeps subagents and agent-team teammates on allowed models (FLEET_GUARD_MODELS) and caps concurrent teammates (FLEET_GUARD_MAX_TEAMMATES); inert when both are unsetUnite-Group★ 2
• resceneRESCENE fan mod: WONI conducts while LIV, MINAMI, MAY and ZENA take the subagent and Orca worker tasks and report back, in Korean or English. 리센느 팬 모드: 원이가 지휘하고 리브·미나미·메이·제나가 작업을 맡아 보고한다.techkwon★ 2
• sc-toolboxA toolbox pane for Claude Code: run, stop and watch the project's build tasks, scripts, Claude commands and prompts from one listSimpleCORE★ 2
  1 more in this repository

  • sc-workspaceA workspace pane for Claude Code: agents and worktrees, checkpoints, notes, changes and memory files in one tabbed paneSimpleCORE★ 2
• session-panelSession Panel: hides tool calls and shows a calm step checklist above the prompt, with a Hide/Show details button.herman925★ 2
• simple-modeSimple Mode: a plain-English checklist of what Claude is doing, one-line tool rows you can expand, and a two-line summary at the end of every reply. /simple turns it on and off.Rapple AI, from OneWave AI's agent-narrator★ 2
• streamsUntangles the interleaved work in a Claude Code session (prompts, mid-turn asides, subagents, loops) into colour-coded streams with a live navigator pane, a status bar of pills and per-stream focus.Macleod Labs★ 2
• task-bandFramed band above the prompt: running subagents, workflows, background shells and monitors, each with its own gauge; ctrl+x tab then arrows to pageMankhongGarden★ 2
• task-progressRegisters a progress tool so Claude reports multi-step work, and draws a progress bar above the input box; writes per-session progress to ~/.claude/notch/sessions/.chenyuxiaojin★ 2
  1 more in this repository

  • todo-pane/daiban side pane listing the in-progress and wrap-up items of a Markdown to-do log (NOTCH_TODO_LOG); writes ~/.claude/notch/todo.json.chenyuxiaojin★ 2
• UsageBreakdownShows what uses up your Claude limits: tokens by model, by main chat versus agents, and by project, across every chat on this MacHeuwzen★ 2
• a2a-modA2A protocol client for Claude Code: Claude hands tasks to non-Claude worker agents over Agent2Agent and picks up their results.Aliasgar Khimani★ 1
• afkswitchAFKSwitch by augbastos — Tell your agents when you're away and when you're back.Augusto Bastos★ 1
• agent-atcAir-traffic control for subagents: a live pane listing every agent, what each one is doing now, and controls to message or stop one. Open it with /atc.Matteo Hertel★ 1
• agent-bridgeTalk to OpenAI Codex from Claude Code: live peer messaging over a local pipe, plus headless delegation (ask_codex).rennerdo30★ 1
• agent-castWhile subagents and teammates run, shows each one as a character: one row per agent in a band above the prompt (face, type, task, current tool, elapsed time), and their faces at the head of the spinner line. Each agent type has its own fac…Seiya Kawamura★ 1
• agent-dollsSide pane with one little robot per agent (main and subagents); press one to see its conversationVisibleSoft★ 1
• agent-hubAgent hub: a pane listing this session's subagents with status, model, turns and tokens, and a box to steer a running one.kzarzycki★ 1
  1 more in this repository

  • self-compactCompaction at task boundaries: the model can ask to compact once its turn ends. Above a fill threshold it is asked whether to, after a turn decision-model judges a finished task, or, without decision-model, with each prompt.kzarzycki★ 1
• agent-routerPicks the model for each subagent by its type (Explore on Haiku by default) and can cap how many run at once.mako-code★ 1
  14 more in this repository

  • auto-continueKeeps 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 continue. Never for choices, missing info or risky steps.mako-code★ 1
  • best-of-nRuns 2-4 attempts at a task in parallel git worktrees, each with a different approach; compare their diffs and adopt the best.mako-code★ 1
  • context-macrosInline #tokens that attach live context to a prompt: #diff, #staged, #log:20, #tree, #todo, #errors, #file:path:10-40, #url:https://...mako-code★ 1
  • file-radarWhat Claude touched this session: reads, edits (+/− lines), searches per file, main vs subagent, with flags for blind edits and repeated reads.mako-code★ 1
  • jev-conventionsInstant repo-convention checks on every edit: CLAUDE.md, AGENTS.md, style guides and config facts compiled into atomic rules, each edit judged against all of them by Jev in a few hundred ms.mako-code★ 1
  • jev-scopeKeeps changes on task: every edit is judged by Jev against your last request (and Claude's plan) in a few hundred ms; drive-by changes go back to Claude.mako-code★ 1
  • jev-topicJev notices when a prompt starts an unrelated task and offers a fresh conversation for it, saving context and prompt cache.mako-code★ 1
  • night-shiftWorks your backlog while you are away: when idle, one worker at a time implements the next .claude/backlog.md task in its own git worktree under a strict tool policy and budget; in the morning you review, adopt or discard each branch.mako-code★ 1
  • plan-boardA live plan Claude posts and keeps current: progress above the prompt, the full checklist and its history in a pane.mako-code★ 1
  • spec-runnerWorks through a Markdown checklist item by item: one prompt per item, an optional check command, the box ticked when it passes.mako-code★ 1
  • stub-detectorNo lazy placeholders: flags TODOs, '... rest of code', NotImplemented stubs and empty bodies an edit introduces, nudges Claude to finish them, and lists what is left.mako-code★ 1
  • subagent-monitorEvery subagent, live: a /subagents pane with status, model, elapsed time, steps, tokens, last tool and answer, plus a band while any run.mako-code★ 1
  • swarmSplits a task into independent parts, runs them as parallel subagents you launch and watch live, then hands their results back for integration.mako-code★ 1
  • task-splitterOne prompt, several jobs: when a prompt you type holds independent tasks (a list, numbered steps, "do A, then B, and also C"), offers to run them one by one as their own turns, stopping at the first that fails or asks you something.mako-code★ 1
• agent-skills-kitWorkflow skills, routing hooks, and read-only review subagents for Claude Code. Also portable to GitHub Copilot, Codex, OpenCode, and dsh.Mark Bovee★ 1
• agents-syncLinks the shared skills from ~/.agents/skills into ~/.claude/skills at session startturanmahmudov★ 1
• autopilotMulti-agent orchestrator harness for Claude Code: command loop, ledger, dispatch protocol, review cycle, model-economics, and a registry-driven external-worker layer.Autopilot Contributors★ 1
• breadcrumbsAn always-on pane with what this session is about: the task, your last prompt, what Claude is doing and last said, and the explanations it wrote, saved as notes you can preview.crockalet★ 1
• clean-viewCalm, non-technical view: hides tool rows and shows one plain-English checklist above the prompt.schmas★ 1
• cockpitA quiet band above the prompt: model, effort, context %, cost, current task and live subagentsFredj Hammami★ 1
• codexOpenAI Codex as native Claude Code subagents: the Agent tool starts one and the mod drives codex app-server in its place, no model in betweenalex2481kobe★ 1
  1 more in this repository

  • agent-modelsEach Claude subagent's model and effort in the native agent list, beside its taskalex2481kobe★ 1
• coding-standardsPersonal coding standards: skills, hooks, and agents reusable across projectsRipta Pasay★ 1
• compoundChecks for existing work before a substantial task, and has the lesson written down after a problem is solved.Jeremy Manning★ 1
• creator-bandThe creator band in one row above the prompt: turn timer, count of TODO, FIXME and HACK lines (read with git), and the daily streak flame.Baselane★ 1
  7 more in this repository

  • focus-packThree quiet nudges in one mod: commit after 8 edits, TODO/FIXME/HACK lines added, and debug prints added.Baselane★ 1
  • todo-countA band above the prompt with how many lines in tracked files hold TODO, FIXME or HACK (todo 12), counted with git after edits. Hidden when there are none.Baselane★ 1
  • todo-nudgeAt turn end, one toast with the count of TODO, FIXME and HACK lines your edits added this turn. Quiet when none were added.Baselane★ 1
  • todo-paneA live side pane of the TODO, FIXME and HACK lines in tracked files (git grep), grouped by file and capped at 30. It refreshes after file edits while open. Open it with /todo-pane.Baselane★ 1
  • repo-packFive read-only repo commands in one mod: /todos, /loc, /hotspots, /commit-msg and /branches. They read git. They copy results to the clipboard.Baselane★ 1
  • scriptsAdds /scripts: runnable tasks from package.json scripts, Makefile targets, justfile recipes and pyproject scripts at the git repo root. Read-only. Copies the result to your clipboard.Baselane★ 1
  • todosAdds /todos: TODO, FIXME and HACK lines in tracked files, found with git grep, grouped by file (50 lines at most). Read-only. Copies the result to your clipboard.Baselane★ 1
• deskbarA desk for the Claude Code prompt: context weather, Gmail, calendar, tasks across sessions, notes, a music deck and a billable-hours timer0NE-C0DEMAN★ 1
• done-gateNotices when Claude marks a task done while code it changed has not been tested since, and tells Claude and you; a band shows the last test run. It warns, it never blocks. Starts off: /done-gate on turns it onChien Vu Minh★ 1
• earpiece-widgetEvery running subagent with the tool it is on and its last sentence, and /whisper slips one of them a note without stopping the turnoMaN-Rod★ 1
  3 more in this repository

  • race-widgetA race track for parallel subagents: each advances one stride per tool call, with a podium as they finish.oMaN-Rod★ 1
  • tasks-widgetThe session's task list with a progress bar.oMaN-Rod★ 1
  • todos-widgetThe TODO, FIXME, HACK and XXX comments in the repository, counted and listed.oMaN-Rod★ 1
• etaTime left on the working turn, on the spinner line: from the task list's pace, else from how long your turns run. No model calls, no tokens. /eta turns it on or off.Hamza Siddiq★ 1
• explore-modelPins the model that background recon subagents run on. An agent.spawn hook sets the Explore subagent's model to haiku, so a session driven by an expensive model stops billing its codebase searches at that tier, without shadowing the built-…Rex Lorenzo★ 1
• fleet-core-c7Lead-side teammate lifecycle: tracks teammates, blocks one Stop while idle teammates are resident, exports the roster.mods-research★ 1
  1 more in this repository

  • spawn-governorRefuses subagent/teammate spawns the lead's context cannot absorb, caps oversized Agent returns to a file, and enforces spawn depth from exact parentAgentId.fleet-core★ 1
• floateeYour Floatee backlog inside Claude Code: the open todos above the prompt (or in a side pane), one button to process each, and guards that keep your API token out of the conversationBleh★ 1
• foremanLive view of a foreman program: lanes, agents, stalls, what needs you, and memoryStella Inwood★ 1
• graceful-stopWinds agents down cleanly as the session's credit runs out and has the orchestrator write a resume memo.Renaud Couttet★ 1
• grillWhile Claude works on your task, a sharp partner asks the questions that change the result. Answers reach Claude mid-turn. Brainstorm and side chat modes too.Atchyut★ 1
• jev-model-routerPicks the model and the reasoning effort for each task with TypeSafe's Jev, a System One decision model reached either through TypeSafe's own API or the Vercel AI Gateway. Routes subagent models at agent.spawn and the main loop's effort an…claude-code-templates★ 1
• limit-guardWarns when the prompt cache is invalidated; near the 5h cap blocks subagents and wide scans and asks Claude for short answers.Talap-creator★ 1
• mascotA desktop mascot overlay that reacts to turns, tool calls and subagentsdesuqcafe★ 1