1,035 cost & usage Claude Code mods, most popular first. Every listing shows its security level and install command.
| Name | Popularity | Security |
|---|---|---|
| cache-maxxer Shows the prompt cache's countdown and hit rate above the input box, explains every cache break and cache expi | 8 ★ | Review before installing |
| agent-router Choose a model and effort for five agent roles and for agent team teammates with /agent-models, and inspect ro | 7 ★ | Review before installing |
| keepalive A prompt cache bar for every conversation, subagent and teammate, a dashboard with /keepalive, per-conversatio | 7 ★ | High risk |
| hud claude-hud 0.10.0 as a mod: model, project, git, context, usage, tools, agents and todos, plus alerts, budget, | 7 ★ | Review before installing |
| receipt What each turn did, in a band above the prompt once it ends (files changed with lines, commands and failures, | 7 ★ | Review before installing |
| todo-bar The task list's progress in a band above the prompt, read from the todo and task tools' own calls: no tool, no | 7 ★ | Review before installing |
| agent-watch Subagents at a glance: tokens per agent, a toast when one stalls, and a summary naming the heaviest agent when | 7 ★ | Low risk |
| limits-meter Plan limits and context above the prompt: model and effort, 5-hour and weekly windows with reset times, contex | 7 ★ | Low risk |
| mod-usage Shows Claude context, 5-hour and 7-day usage as gradient progress bars above the prompt (Claude Code Desktop / | 7 ★ | Review before installing |
| paneline Claude Code mod (plugin) that adds a side pane with Activity, Files, Agents, Context, MCP, Skills and Spend ta | 7 ★ | Review before installing |
| pixel-cat A little pixel cat that wanders above the Claude Code prompt, watches your usage limits and announces when wor | 7 ★ | Low risk |
| usage-hud 输入框下方是三列对齐的模型/用量/状态面板，上方是一只会按工具做动作、带着子代理小螃蟹来回走的像素螃蟹（终端；Windows / macOS / Linux）；配速预警和螃蟹情绪、每轮收据、一键压缩、额度恢复提醒、子代理 | 7 ★ | Review before installing |
| taskcut Compacts when the work moves on from one sub-task to the next instead of when the context window fills, includ | 7 ★ | Low risk |
| cache-keep-warm Shows how long your session's prompt cache stays warm, and can keep it warm in the background while you are aw | 6 ★ | Low risk |
| cache-timer Counts down to when the prompt cache expires, so you can send the next message before the whole conversation h | 6 ★ | Low risk |
| session-meter Shows a live session pane (/ctx): context breakdown, usage limits with pace, tool calls and model requests; se | 6 ★ | Review before installing |
| turn-footer Turns the line under each answer into a turn summary (tools, requests, tokens, cache hit) and shows the runnin | 6 ★ | Low risk |
| agent-crew Shows your subagents above the prompt as pixel-art Claude crew members: what each one is doing, how far along | 6 ★ | Low risk |
| cache-panel Passive 50-minute prompt-cache reminder with a keyboard/mouse panel: keep warm, ping once, or compact, with li | 6 ★ | Review before installing |
| gsd-status-mod A Claude Code mod for GSD projects: a live pane (roadmap, agent tree with forks, cost and context, work stream | 6 ★ | Low risk |
| commander-hud Commander HUD: Fable state, running agents, tool-call budget and update pill above the prompt | 6 ★ | Low risk |
| laya-router Auto-route each Claude Code session to Haiku, Sonnet, Opus or Fable from its first prompt. Classified locally, | 6 ★ | Review before installing |
| context-card Context window breakdown and plan usage, in the band above the prompt. | 6 ★ | High risk |
| session-hud Session Tracker above the prompt box: context window with a /compact recommendation, 5-hour plan limit, prompt | 6 ★ | Low risk |
| usage-band Status line: model, context window, 5-hour and weekly limits with reset times, warning past 90%. Hungarian or | 6 ★ | Low risk |
| usage-header Band above the prompt: context window broken down by category in colours, plus the 5-hour and weekly limits. H | 6 ★ | Low risk |
| context-band Band above the prompt: context %, tokens, model, cost, prompt-cache size/share/TTL countdown, 5h and weekly us | 6 ★ | Review before installing |
| spawn-ledger Spawn log (spawn_start/launched/end + cost, native agentId lineage), artifact check and in-session RESPAWN_REQ | 6 ★ | Review before installing |
| voice-compact Startup token diet: rewrites the long CAVEMAN / PONYTAIL MODE ACTIVE hook-context injections into ~150-token c | 6 ★ | Low risk |
| rich-terminal Mermaid diagrams drawn inside Claude Code replies, and a truecolor status line under the prompt with a Token W | 6 ★ | Review before installing |
| context-bar Context window breakdown and prompt-cache countdown above the prompt; /context-bar toggles it. | 5 ★ | Low risk |
| keepwarm Keeps an idle interactive session's prompt cache warm with one tool-less fork just before the 1-hour cache lap | 5 ★ | Review before installing |
| usage-hud A pixel Clawd above your prompt whose mood follows your context, session and weekly usage | 5 ★ | Review before installing |
| usage-pet A usage band above the prompt — context, 5-hour limit, weekly limit, cache hit rate — with Clawd, an animated | 5 ★ | Review before installing |
| vitals A light, framed live dashboard above the prompt, in the terminal and in the desktop app: model and effort, con | 5 ★ | Review before installing |
| token-monster A pixel-art monster in a side pane that eats tokens and shows context, limits and activity at a glance | 5 ★ | Review before installing |
| wavy-usage Liquid-filled rings above the Claude Code prompt for the 5-hour and 7-day limit windows, context fill and prom | 4 ★ | Low risk |
| ccbar ccbar — a quiet status band above the prompt, drawn natively by Claude Code's function hooks: the model and it | 4 ★ | Review before installing |
| session-usage-band See what your next message costs: a live band above the prompt with the prompt-cache countdown, the re-warm pr | 4 ★ | Review before installing |
| local-answer-router Answers trivial questions (what branch, what changed, did the last test pass) from git and the last test run o | 4 ★ | Review before installing |
| subagent-meter A live status line showing how much of your session's tokens go to subagents, and which agent type uses the mo | 4 ★ | Low risk |
| clawd-spinner Clawd acts out the spinner's word above it while Claude works: cooking for Sautéing, dancing for Vibing, pacin | 4 ★ | Low risk |
| lexi Test-first workflow for coding agents, without the spec ceremony. A PreToolUse hook keeps source edits behind | 4 ★ | Review before installing |
| crab-cam A crab above the prompt acts out what Claude is doing: reading, writing code, thinking, searching and more. A | 4 ★ | Low risk |
| noctis Runs long Claude Code jobs overnight within your usage limits: pauses just before the 5-hour or weekly limit, | 4 ★ | Review before installing |
| idle-compact Compacts the main conversation once it has sat idle for idleMinutes, while the prompt cache is still warm, and | 4 ★ | Low risk |
| usage-bar See your Claude Code session at a glance: context left, cost and today's spend, rate limits, git diff and PR s | 3 ★ | Review before installing |
| clubhouse Claude Clubhouse: a toolbar above the prompt, rooms for usage, agents, commands, tool rules and colors, and wh | 3 ★ | High risk |
| miod Generative music for Claude Code. Every task gets its own tune, and the mood follows what the agent is doing a | 3 ★ | Low risk |
| mission-control A live sidebar: project, context and quota, tasks, subagents with ETA, and a running recap | 3 ★ | Low risk |
| cache-meter Prompt cache status above the prompt: how long the cache stays warm, what a re-cache would cost, plan limits n | 3 ★ | Low risk |
| handoff-relay A Handoff button above the prompt: runs /handoff and lights up from 180k tokens of context (the threshold opti | 3 ★ | Low risk |
| sidebar Shows the model's real output speed, token and prompt-cache stats in a docked sidebar beside the transcript. | 3 ★ | Review before installing |
| cache-keepalive Keeps an idle session's prompt cache warm with a short prompt 2 min before it expires; capped per model, the l | 3 ★ | Review before installing |
| cost-ledger Cost ledger across all chats: after every answer it records the chat cost (as /cost), tokens per model and mod | 3 ★ | Low risk |
| observe An /observe pane with a tab per provider: Docker and Modal containers with each one's live logs and GPU, CPU a | 3 ★ | Review before installing |
| statusbar Colored two-row status line below the prompt: model, folder, git branch and changes, context fill, 5h and 7d q | 3 ★ | Review before installing |
| ultracompress Deterministic local compaction for Claude Code: replaces the stock compaction summarizer with the local UltraC | 3 ★ | Review before installing |
| effort-router Picks low/medium/high/xhigh effort per prompt for Opus/Sonnet/Haiku 5.5+ and Fable/Mythos 5.1+ by how uncertai | 3 ★ | Low risk |
| ClauDiscobombulating Console: limits, cache timer + alert, model/effort pickers, side pane. Desktop: limits and cache timer under t | 3 ★ | High risk |
| auto-effort Picks low, medium or high effort for each prompt, keeping the prompt cache warm | 3 ★ | Low risk |
| context-meter Band above the prompt with model, effort, context fill, rate-limit windows and session cost, cache state | 3 ★ | Review before installing |
| idle-compact Compacts an idle session with a large context just before its prompt cache expires, while the summary still re | 3 ★ | Review before installing |
| sessclone Sends Claude Code usage to a SessClone deployment. | 3 ★ | Low risk |
| cache-refresher Shows when your prompt cache expires and what rebuilding it would cost. Optional auto-refresh, off by default, | 3 ★ | Low risk |
| attic-widget Counts which tools Claude calls in this project, puts the unused ones behind ToolSearch, lists the daily ones | 3 ★ | Low risk |
| ledger-widget What a project has cost across every session, from any folder or worktree in it: measured as each turn ends, a | 3 ★ | Review before installing |
| sieve-widget A compaction that keeps every word you and Claude said and folds only the old tool traffic, with no summary an | 3 ★ | Low risk |
| stream-widget A live gauge of how fast Claude is writing, in tokens per second, with a sparkline. | 3 ★ | Low risk |
| usage-widget A bar per rate-limit window with time to reset and session cost. | 3 ★ | Low risk |
| weather-widget Context usage drawn as weather, from clear skies to a storm near compaction. | 3 ★ | Low risk |
| clawd-dash Session dashboard under the prompt: usage limits, context, cost, model, effort, session stats, git status, fil | 3 ★ | Low risk |
| am-context-bar A context card above the prompt with a collapsed and an expanded view: zone-coloured token count (dumb zone fr | 3 ★ | Review before installing |
| reminder-log Tallies the reminders Claude Code injects for the model, per session; drops the token counter and repeated att | 3 ★ | Low risk |
| tamagoxtix A little pixel monster in place of the spinner: animated by what Claude is doing, with a visual timer, a stack | 3 ★ | High risk |
| usage-percent A row under the prompt: context, 5-hour, weekly and model-scoped weekly usage; in Nx repos also memory, the se | 3 ★ | Review before installing |
| auto-resume When a turn dies on a rate limit (or an overloaded API), counts down to the reset and sends "continue" for you | 3 ★ | Review before installing |
| hud Two coloured, animated lines under the prompt, every figure named: model, effort, context window, rate limits, | 3 ★ | Low risk |
| cost-meter Always know what a session costs: live $ / context / rate-limit status line, the cost of every turn, context w | 3 ★ | Low risk |
| clawd-hud-spike Spike da HUD RPG: sondas no app real para os itens A VALIDAR (sem gastar tokens) | 3 ★ | Low risk |
| effort-router Make your Claude Code usage go up to twice as far. Picks the right reasoning effort for every prompt and every | 3 ★ | Review before installing |
| claudetto-sessions Measures the start of a Claude Code session by source, and the usage of each run: model calls, context that ea | 3 ★ | Low risk |
| deploy-verify After a deploy command succeeds, curls the live URL with cache-busting and puts the verdict in the model's con | 3 ★ | Review before installing |
| money-band A line above the prompt with liquid assets, CPF, debt and month-to-date spend, read from a pair of SQLite data | 3 ★ | Review before installing |
| usage-band A line above the prompt with the five-hour and seven-day limit windows, this session's context fill and cost, | 3 ★ | Low risk |
| usage-band 入力欄の上に使用量メーター（ctx・5h・7d・モデル別の週枠）と effort の切り替えを出す | 3 ★ | High risk |
| usage-limits Progress bars for the session (5h) and week (7d) rate limits in the prompt footer | 2 ★ | Low risk |
| usage-limits Keeps the 5-hour and weekly limit windows, their burn rate, a run-out projection, context fill, session cost a | 2 ★ | Low risk |
| tokensaver Token-efficient delegation: routes sub-agents to the cheapest capable model tier, escalates on failure, learns | 2 ★ | Review before installing |
| logbook Keeps a live local page for a long Claude Code task: what needs you, what was built, what was verified, and wh | 2 ★ | Review before installing |
| usage-meter Directory, branch, worktree, model and effort, with 5h and weekly limits (subscription) or cost (pay-per-token | 2 ★ | Low risk |
| ask-jev ask_jev on any situation, files, a command's output and your own state, with a spend ledger | 2 ★ | Review before installing |
| jev-hud A band above the prompt that shows Jev at work: a spinner while it thinks, each intervention in colour, calls, | 2 ★ | Low risk |
| dispatch-pilot Dispatch Pilot：一个在 Claude 之外的决策模型（默认 Perplexity 的 pplx，没有 Perplexity key 时退回 TypeSafe 的 Jev，也可以固定用 Jev）在你每次发消息 | 2 ★ | High risk |
| contador-tokens Muestra los tokens del contexto y el costo de la API en la barra de estado, y un toast con lo que sumó cada re | 2 ★ | Low risk |
| usage-tally Your Claude plan usage inside Claude Code: session (5h) and weekly limits with reset countdowns in the status | 2 ★ | Low risk |
| token-watch Shows token use, plan limits and cache temperature of the sessions on this Mac | 2 ★ | Low risk |
| pace Shows when a session gets heavy or its prompt cache is about to go cold, and parks a session so the next one c | 2 ★ | High risk |
| cache-timer Status line: minutes left until the main thread's prompt cache goes cold (assumes a 60-minute cache; it is 5 m | 2 ★ | Low risk |
| cost-ledger Tracks what Claude Code costs — session, calendar-week and calendar-month totals with the month's pace and wee | 2 ★ | High risk |