ModsCode / Claude Code Mods / Ranking / Tasks & agents / Page 3 of 4

• handoffA checklist of the shell commands Claude hands you to run: captured from replies, ticked when you run them, confirmed by Claude.Dominick Giordano★ 0
• harnaisHarnais d'orchestration du dépôt : rend l'état que mesurent les scripts (suivi de vague, #2279 ; CI et train de publication en status line, #2280), sans porter de règle.MyEdO/game★ 0
• heavens-feelHeaven's Feel cast for your agents: Sakura watches over the main session, Servants answer every subagentYedidya Kfir★ 0
• high-commandSee the messages your teammates, named subagents, and other Claude Code sessions send you, grouped by peer with unread counts: a pane, a band above the prompt, and /highcommand.dot-agi★ 0
• hybrid-agentsSubagents default to Sonnet; pasting a plan path adds the hybrid rule (inline small tasks, Sonnet subagents for big ones)irfanfaraaz★ 0
  1 more in this repository

  • tool-preloadKeeps context-mode, jcodemunch, claude-mem, WebSearch, Task and Supabase tools loaded so Claude stops calling ToolSearch for themirfanfaraaz★ 0
• idea-shelfPark side-ideas mid-task with /idea, without Claude seeing them; list them with /ideas and send one later as a prompt.TR Aravindan★ 0
• jev-model-routerPicks the model and reasoning effort for each task with TypeSafe's Jev. Routes subagent models at agent.spawn and subagent and main-loop effort at turn.step, with optional main-loop model routing. Falls back to the engine's built-in classi…Dmitrii Bakhtin★ 0
• jev-model-routerCorrects the model tier of every subagent spawn (agent.spawn) with a live Jev judgment (haiku / sonnet / opus), instead of relying on /delegate's static routing table. A risky task (touches production, money, or irreversible data) is alway…tulsi★ 0
• jev-semaphoreJev Semaphore for Claude Code: Jev / Kev model routing for subagents, with a live allocation pane, agent graph and context-exchange bandPeter★ 0
• jevmateA fast decision layer for coding agents. Jev ranks files, picks the tests a change can break, sorts failures and reviews diffs by risk, so Claude reads only what matters and judges only what Jev is unsure of. Also: long output trimmed, com…Gaston Gelhorn★ 0
• kanban-statusShows your Obsidian Kanban board (BOARD.md) in the status line, with a /board pane listing every cardSajid Rahman★ 0
• kb-settings-guardDenies a delegated agent lane any write to this repo's Claude settings files.knowledge-base★ 0
• kitThe agents kit inside Claude Code: the /flow paneagents-kit★ 0
• lazarusRecords the background jobs a session starts; after a crash or restart one key resumes what died, a usage-limit stall continues by itself at the reset, and /park says whether a restart is safe.FixIt Technologies★ 0
  1 more in this repository

  • wakeWakes an idle session when a watched PR, CI run, Eve review, devbox, vitrinka task or deployik deploy reaches the state it asked for — one shared poller (vybava watch) instead of per-session sleep loops.FixIt Technologies★ 0
• lean-and-meanConcise prose and YAGNI code, installed into the project AGENTS.md. /endsession writes Rules and Next, commits, pushes, then stops.Spinlock Development★ 0
• ledgerThe record of orchestrated work: runs of units and tasks, the subagents spawned for them, each gate's verdict and the findings reviewers report, summed up in the status line while there is something to say. It can follow a superpowers plan…Kuang Tar Lim★ 0
• ledgerA per-session ledger of topics, decisions, open questions, to-dos and board state, kept by Claude through a tool and shown in a pane.gabedeluna★ 0
• ledgerA live pane of this thread's tasks, open questions and decisions, kept up to date by Haiku after every turnRob Watson★ 0
• left-undoneA sidebar listing todos Claude left undone; press a letter to flag one, then send Claude back to finish it.adammhal★ 0
• lights-outShows the background tasks this session left running and how much memory is free. Stops only what it started.Ivan Vydrin★ 0
  1 more in this repository

  • spotcheckChecks the files, line numbers and symbols a subagent cites before Claude repeats the report.Ivan Vydrin★ 0
• limitpaceLive subscription usage and pace bars, with an optional provider-neutral delegation advisor.Florian Standhartinger★ 0
• live-statusA live monitor for Claude Code: model, effort, context, 5h/7d usage limits, task progress and a subagents panel, in one responsive card.fanoisme★ 0
• long-task-notifierShows a live timer for long-running Bash commands and background tasks, then toasts, chimes and sends a desktop notification when they finish, on Linux, macOS and Windows.Josh Kerr★ 0
• loose-endsA live checklist above the prompt of the conversation's loose ends: questions left unanswered, points made in passing, caveats and deferred work it moved past, kept up to date by a small model after each turn. Needs function hooks (early a…Fernando Moraes★ 0
• mcp-dietChoose which MCP tools and subagent types Claude sees, per project. A pane lists every server and tool with the size of its description; defer or hide the ones this repo never needs and stop paying for them on every request.Mohammed Mubarak★ 0
  1 more in this repository

  • undo-agentUndo the file edits a subagent made. /rewind restores your own turns, but not a subagent's edits; this snapshots them and puts the files back with one command.Mohammed Mubarak★ 0
• mesh-liveLive Claude Agents Mesh inside Claude Code: inbox that wakes the agent, real quota reports, automatic task leases and handoff, a /mesh pane, commands, status line, live context, file locks and token masking.aciderix★ 0
• mission/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★ 0
• mission-controlYour crew, live: an animated Clawd for Claude and every subagent above the prompt, and a pane with the context and the budget.Dat Vo★ 0
• mission-paneA side pane (/ops) with this session's subagents and background jobs, live, and a sound and a toast as each one ends.simplybychris★ 0
• mod-templateTODO: one linerobertgregorywest★ 0
• model-routerHaiku sorts every subagent task into simple, standard, hard or long run and picks the model; a pane shows what each agent cost.Andy★ 0
• model-routerRuns chosen subagent types on cheaper models (Explore on Haiku by default) and adds /router to switch the main session between fast, smart and unchanged. Shows the active model beside the spinner.claudemodz★ 0
• model-routerRoutes each model request from turn.step: subagent steps to haiku, a short first prompt to low effort, and /route <model|auto> to pin the main loop. Writes every decision to PROOF-steps.log. Needs function hooks (early access).hide-sora★ 0
• model-routerRoutes prompts and subagents to a cheaper or stronger model by what they askReno Angelo Banderlipe★ 0
  2 more in this repository

  • repo-radarLive map of the repo that lights up as Claude and its subagents read, edit and fail on filesReno Angelo Banderlipe★ 0
  • swarmLive map of the session's agent tree: who spawned whom and what each is doingReno Angelo Banderlipe★ 0
• model-routerRoutes each turn and subagent to a model tier and reasoning effort using a classifier behind any server that speaks POST /v1/classify (model-router-api on Cloudflare Workers AI today), falling back to the engine's built-in classifier.SFT Inc★ 0
• monitorA control room above the prompt: background agents and shells (running, done, failed), blocked tool calls and context usage. /monitor pins it.Richard Suwandi★ 0
• multiharness-delegationRoute Agent calls with subagent_type multiharness-delegation:<harness> to an interactive external harness in tmuxfranciscocarloserra★ 0
• named-subagents-modGives every subagent a themed name in the task tree (display only; the agent is not told its name).Bobby-cell-commits★ 0
• named-subagents-modGives every subagent a themed name in the task tree, and lists the running agents under those names in a side pane: what each is doing, its tokens, its conversation a press away.Bobby-cell-commits★ 0
• 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）Tora29★ 0
• nested-agents-mdLoads nested AGENTS.md for files Claude touches through Bash, Edit or Write, where the built-in agents-md mod loads them only on Read.JStar★ 0
  1 more in this repository

  • explore-modelRuns the built-in Explore subagent on a chosen model and effort (default Haiku, medium) whenever the Agent call leaves them out. Keeps Anthropic's Explore prompt and read-only tools; a call that names its own model or effort keeps it. Need…JStar★ 0
• nightrun-pane/nightrun: pane with the newest claude-orchestrator night run's sprint states and log tail (reads only the runtime/nightrun layout; not bajzi night-run's NIGHT_DIR)bajzaa975★ 0
• no-haiku擋下明確帶 haiku 的 subagent 派工；agent 定義 pin 到 haiku 的只記一行提醒（Stan harness mod）Stan Shih★ 0
• normal-sweEngineering skills and specialist agents for Claude Code.andreimaxim★ 0
• open-pointsA live view of your project's open points or TODO markdown file: a side pane grouped by status and a one-line count above the prompt.Rajat★ 0
• openspec-governanceOpenSpec lifecycle governance for Claude Code: stage band, fail-closed edit gate, task progress and an append-only execution log.whoisclebs★ 0
• openspec-paneSide pane for OpenSpec: active change, artifact and task progress, spend per OPSX step, next-step buttonskk5190★ 0
• opsx-boardOpenSpec board: which phase you are in (propose/apply/archive), which tasks.md task is current, and every sub agent's name, model/effort, tokens and progressdavidho27941★ 0
• opum-questDrive the quest CLI: create, list, view, edit, complete, and archive tasks, drafts, milestones, and decisions in a Quest-initialized workspace instead of editing tracker state directly. Cut from the same quest-cli repository and tag as the…Opum AI★ 0
• opus-conductorOpus 5.5 conducts a mission: plans sized tasks, delegates hard labor to Sonnet 5.5 workers and narrow jobs to Haiku 5.5 scouts at the reasoning effort each task needs, and shows every agent, what it is doing and the mission's % in a live p…illa★ 0
• orchOrchestrator sessions: bind to .remember/<slug>/README.md, keep the role in the system prompt, and at a context limit ask for a handoff, then compact when the handoff_done tool signals that it is writtenchris★ 0
• orchestraA conductor agent and musician subagents for Claude Code, with a live ledger of who read and changed what, conflict and stale-read detection, and a coda built from the ledger.krzemienski★ 0
• orchestrateMarkdown-tracked task orchestration: grill a task to a spec, scout the repo into a context pack (read-only repo-scout agent), track the epic in a local git-ignored .orchestration/ markdown store (long-lived per-repo PROJECT.md, the epic as…Personal AI Setup★ 0
• orchestratorPick orchestrator settings once; only the main agent gets them, and subagent limits are enforcedkatipally★ 0
• orchestratorTurns a session into an orchestrator that delegates work to haiku and sonnet subagents, keeps its own context small, sizes each task to about 150K tokens of subagent context, and lists the running and past agents in an expandable band (/or…Rotem★ 0
• ouroborosThe dev loop that eats its own mistakes: milestone and phase workflows, long-lived specialist agents, and skills that rewrite themselves after every phase, each change proven by an eval.StupidCodeFactory★ 0
• painel-longrunPainel da execução longa: objetivo, tempo decorrido, checklist com % e as últimas linhas do progresso e do canal, atualizado sozinho (/longrun, /longrun todas)INEMA★ 0
• parkedA per-project backlog of items needing your attention, parked by you or the orchestratorKuang Tar Lim★ 0
• party-paneA side pane that shows the agents working on your requests as illustrated charactersshuletadev★ 0
• pending-youOne place for everything your AI agents are waiting on you for. When a decision is yours, Claude asks in the conversation and on a Pending You card at once, and the first answer wins.RecordPlane★ 0
• pinA short to-do list pinned above the prompt, ticked off with one click.Rostech★ 0
• plan-checklistTurns an approved plan into a todo list above the prompt; Claude checks each step off only with verification evidenceJaehyuk Han★ 0
• plan-progressLive plan progress bars above the Claude Code prompt: stages, steps, a pixel fill and soft sounds for decision, error and doneKirill Serditov★ 0
• plan-progressLive plan progress bars with stages, steps, step times and soft sounds for decision, error and done. Local fork of zycck/claude-mods plan-progress 0.3.0 (ea2c96b) that sends its rules with the first prompt instead of prompt.compose and sen…Kirill Serditov★ 0
• plan-progressLive plan progress bars above the Claude Code prompt: stages, steps, a pixel fill and soft sounds for decision, error and done (qa-mods fork: a wider title, the full title on hover, Ukrainian interface)Kirill Serditov (fork: noaod)★ 0
• plan-progressReads a phased plan into a live progress tree: phases, steps, elapsed time and an estimate of what is leftWeaponizedLego★ 0
• proc-registryRegistry of background processes and subagents: /procs command, Processes panel, counter in the status line.Chronosaur★ 0
• prompt-boosterAdds repo context to short prompts, plus one-word commands for common tasks.lakmadev★ 0
• prompt-posseThe boss and a posse of subagent creatures walk back and forth above the prompt while Claude Code worksRyan Emslie★ 0
• quicksaveA save point before compaction: the task's goal, step, branch, links, decisions, rules and next step are saved before /compact and handed back to the model after it, with a pixel-art SAVE POINT band when it is safe to compact.Pourya★ 0
  1 more in this repository

  • tripwireRules that are enforced, not remembered: deny, ask, rewrite or note on any tool call, subagents included. A pixel-art trap for every mistake you already wrote down.Pourya★ 0
• reminder-trimStop the engine's task and todo list reminders from reaching the modelMark Liu★ 0
• review-cycleAutomated multi-agent code review cycle. Spawns reviewers in parallel (plus Codex when available), applies fixes per CLAUDE.md policy, admits a commit only when a reviewer saw exactly what it records, and asks before a push, pull request, …Oak OSS★ 0
• review-lintHands Claude a cache-review checklist or test rules when an edit adds a cache or a brittle test assertionTridhatri Vallamkondu★ 0
• rpg-questBackground task notifications as returning quests: how it ended and what kind of task, ahead of the engine's summaryMonkeyBinBin★ 0
• run-boardA pane and toasts for background shells, monitors and subagents: status, elapsed time, latest output line, exit codelunatictaco★ 0
• savvy-progressProgress bar above the prompt and an agents panel (/agents-info): running, finished and planned subagents with model, progress, context, cost and time. Crabs for the claude-config scout, builder and reviewer. Copy of johnnyvizz/claude-kit …johnnyvizz★ 0
  3 more in this repository

  • workersA pane of the sessions this one orchestrates: state, branch, commits ahead, changed files, last message, who needs youBerkay Orhan★ 0
  • effort-gateDenies a subagent or background session running Opus at xhigh or max effort unless the user said soBerkay Orhan★ 0
  • route-ledgerRecords which model and effort each subagent or background session ran at and how it went, with /routing-review to tune routing rulesBerkay Orhan★ 0
• scout-routerBefore a subagent starts on Opus, a Haiku judge reads its task and moves it to Sonnet unless it needs Opus's judgment.Mohab Yasser★ 0
• serhan-progressProgress bar above the prompt for /serhan, plus an agents panel (/agents-info): running, finished and planned subagents with model, task progress, context, cost and time. Derived from johnnyvizz/claude-kit (savvy-progress).serhan★ 0
• sessionSide pane with the session's subagents, loaded skills and changed files (+/- lines)djavrell★ 0
  1 more in this repository

  • agentsSingle source of the session's agents: collects them and publishes them as state other mods readdjavrell★ 0
• session-boardDesktop mod for people who run many sessions: a task brief with criteria and authority at the start, Claude works alone and calls you only for blockers, an acceptance screen and an HTML report at the end. A free mode for brainstorming and …Ilia★ 0
• session-dashboardA side pane for the current session: prompt cache hot/cold, tool calls and errors, background commands with restart and stop, the approved plan, task list, subagents and swarm agents, and token usage for the main agent and subagentsdjmid★ 0
• session-flowA live pane that shows the session as a flow: each prompt, its phases, its subagents and its costTheBabaYaga★ 0
• session-panelA control panel for this session: an overview with a timeline, subagents with their prompt, trace and answer, shell commands with their output, and files touched; open it with /panelkpeez★ 0
  1 more in this repository

  • subagentsAn animated pane of this session's subagents: a walking Clawd per agent with its type, task and latest tool call; open it with /subagentskpeez★ 0
• session-progressProgress bar above the prompt for the current session's task: follows the todo list (TodoWrite, TaskCreate/TaskUpdate) and the plan the model reports through its progress tool.nerevar48★ 0
• session-tasksA line above the prompt counting the background tasks running in every session, and a side panel listing them (shells, subagents, monitors, workflows) read from their transcripts, even in sessions marked Completed: /alltasksR. Woeltjes★ 0
• severance-mdrMacrodata Refinement while your agents work: find the scary numbers and bin them.Magnus Widerberg★ 0
• shared-repo-guardFor repos where several AI agents (or you and an agent) work in the same folder: stops secret values from leaving your .env, pushes to public remotes, and git commands that would wipe work this session did not write.naoanao★ 0
• shepherdrSpawn, delegate to and monitor Pi agents in Herdr, with results pushed back into the sessionramtinJ95★ 0
• sherlogGroom an issue backlog: find stale, duplicate, vague, unlabeled and unprioritized issues, report them, and apply only the fixes you approve.Sherlemious★ 0
• shouldnt-you-knowAfter Claude edits code, a side look at the task and the change shows one plain-language structural note above the prompt; it never enters Claude's context.SC Wei★ 0
• sidekickPersona agents you can talk to: create a sidekick, it explains, does and fixes things in character, asks when it needs you, and speaks its replies.Meer Tarbani★ 0
• spare-cyclesA timer that brings up a small task to do while Claude works.Macdara Ó Murchú★ 0
• spatz-modRecommends Claude models and effort with spatz and can apply them to subagents and the main session.spatz★ 0
• stackStacked progress band above the prompt: tasks, subagents, rate limits and monthly costShahriar★ 0
• statusツールバー（入力欄の上）の Menu から、TODO・通知・使用率表示の設定を開くClaude Code Club★ 0
  1 more in this repository

  • todayTODO を Today・◎・○・△ の段階で管理し、ステータスバーに今日の件数を出す。一覧の画面からボタンで移動・完了できるClaude Code Club★ 0
• statusbarA session status bar for Claude Code Desktop: your 5-hour and weekly usage limits with time to reset, session and turn clocks, and running subagents, background tasks and scheduled wakeups (early access).Sergio García Mondaray★ 0
• steplineTurns a plan you approve in plan mode into a live checklist above the prompt that checks off each step as Claude completes itSaad Khan★ 0
• sticky-boardA small pane in Claude Code with your project's current phase and two to-do lists: one for Claude, one for youMagazem★ 0
• sticky-todosKeeps Claude's todo list in a side pane beside the transcript, open only while the list has items.Pawee Chinagarn★ 0
• still-modsPersonal mods above the prompt: plan progress bars and context, 5-hour and weekly usage metersstillgbx★ 0
• styxA Claude Code mod that routes the main conversation and subagents to other model providers through user-defined model aliases, on your own API keystyx contributors★ 0
• subagent-effortRun each subagent on any model (gpt-6, grok-4.7, ...) at any reasoning effort, through model and effort parameters on the Agent toolHaoYan-A★ 0
• subagent-modelsTurn subagent models on or off and set the effort subagents run at, as defaults in /config or live for one session with /subagent-models.jl-cmd★ 0
• subagent-modelsStatus line shows which model each running subagent is usingwickedhardflip★ 0
• subagent-treeSide pane showing subagents as a tree with last-tool activity, tokens and runtime per agent, click-through detail, search, and saved history of past sessionsClint Day★ 0
• subagents-panePane listing subagents with their progress and current tool callnikbrunner★ 0
• swarm-modSpawn, watch and steer a swarm of Claude Code agents from a side panedjmid★ 0
• task-board別セッションが書く tasks.json のタスク一覧を、標準のタスク一覧に似た見た目でプロンプト上に表示する(読み取り専用・エージェントに影響しない)sunagawasei★ 0
• task-eta长任务进度行：一轮跑满 3 分钟时让模型估一次剩余步骤，之后按工具调用推进状态栏里的步骤、进度条和剩余时间Bearisbug★ 0
• task-flowA side pane with Claude's plan as a task tree; quote, redirect or skip any step and Claude follows the changeChinsin★ 0
• task-lineOne clean line per task list above the prompt, filled from Claude's own todo tools, same look in the terminal and the desktop appPatrick Müller★ 0
• task-linkShows the session's SpaceHub task as a link above the prompt; /taskurl sets or replaces itDanila Andreev★ 0
• task-listTrack a project's tasks in its TASKS.md, shown in a paneamaezey★ 0
• task-progressProgress bars above the prompt for any long task that writes ~/.local/state/agent-progress/<id>.jsonAndras Gyarmati★ 0
• task-progressLive progress bars above the prompt for background shells and subagentsPiotr Korzuszek★ 0
• task-progress-hudShows done, percent and remaining tasks of the current OpenSpec change.Liam Mitchell★ 0
• task-progress-modLive TodoWrite progress bar above the prompthao li★ 0
• task-stepsShows the steps Claude plans for your task, and its progress through them, above the prompt.moonteek★ 0
• tasknotes-previewShow Obsidian TaskNotes tasks from a .base view as a board, list, agenda or dependency graph in a Claude Desktop side paneBRNCX★ 0
• taskrailA live wave board of your session's plan above the prompt: waves, tasks and their state, kept current by Claude through three tools and switched with /taskrail.Drolosoft★ 0