1,035 cost & usage Claude Code mods, most popular first. Every listing shows its security level and install command.
| Name | Popularity | Security |
|---|---|---|
| cc-contextbar Battery-style context bar for Claude Code, drawn as a live band above the prompt: real context %, session cost | 1 ★ | Low risk |
| usage-meter Shows plan rate-limit usage, session cost, context fill and a per-task token estimate above the prompt | 1 ★ | Low risk |
| neon-hud A live HUD above the prompt: turn timer, active skill, subagent tree, git state, rtk token savings and one-cli | 1 ★ | Review before installing |
| logstrip-gain LogStrip global token savings in a status line and statistics report card. | 1 ★ | Review before installing |
| rtk-gain RTK token savings in the status line, and /rtk-gain draws the full rtk gain report as a card. | 1 ★ | Review before installing |
| tools-usage Side pane listing the tools used in the session (built-in, MCP, skill, agent, plugin, hook) with calls and tok | 1 ★ | Low risk |
| things-you-should-know Course example mod: a band above the prompt with the session facts you tend to forget (files edited since the | 1 ★ | Review before installing |
| pet Maid mascot in the prompt band: reacts to Claude state, shows CTX/5H/7D usage, keeps an affection counter. | 1 ★ | Low risk |
| token-panel A pane listing each prompt's token usage and its cost at standard API (Enterprise usage) rates; /token-panel t | 1 ★ | Low risk |
| usage-meter Plan usage under the prompt: 5-hour, weekly and Fable limits with reset times, plus prompt-cache expiry | 1 ★ | Review before installing |
| pixel-crew Routes every message to the cheapest model that can do it (Haiku, Sonnet or Opus) and shows three pixel worker | 1 ★ | Low risk |
| ctx-cache-band Band above the prompt: context window used/max and prompt-cache TTL countdown + hit rate; optional auto-compac | 1 ★ | Low risk |
| idlecrash Crash with fake tokens against other people who are also waiting for Claude: in a pane, in a terminal and in t | 1 ★ | Low risk |
| eta Time left on the working turn, on the spinner line: from the task list's pace, else from how long your turns r | 1 ★ | Low risk |
| token-weather A live forecast of the context window, in the band above the prompt. /token-weather turns it on or off. | 1 ★ | Low risk |
| jev-router Asks Jev before each prompt what the task is and how hard it is, then picks the Claude model (and optionally e | 1 ★ | High risk |
| clawd-crew Every running Claude Code session and subagent as a little animated Clawd, with its model, time working and to | 1 ★ | Review before installing |
| usage-band Mod: a slim retro line above the prompt showing your plan's 5-hour and weekly usage limits. | 1 ★ | Low risk |
| modal-meter Watches your Modal apps from the CLI, in projects that use Modal: running apps and containers on the status li | 1 ★ | Review before installing |
| pr-autopilot Watches your open pull requests: CI pass/fail toasts for the PRs you open here, failing-check logs attached wh | 1 ★ | Review before installing |
| recall Makes past sessions recallable: indexes Claude Code and Codex transcripts, subagent runs, memory files, standi | 1 ★ | High risk |
| second-opinion /second-opinion asks Fable (or the model you set) for a candid senior review of your recent commits, branch, u | 1 ★ | High risk |
| stall-alarm Raises the alarm when a long-running session stalls while you are away: a permission dialog or a question that | 1 ★ | Review before installing |
| usage-meter A machine-wide meter of the plan's rolling 5-hour usage: every session's turns summed as effective tokens, the | 1 ★ | Review before installing |
| astrolabe Spec Kit progress and usage governance for Claude Code: a phase rail above the prompt, the next command in the | 1 ★ | High risk |
| cost-bar A one-row band above the prompt with session cost, 5h/7d plan limits and an optional budget bar. | 1 ★ | Low risk |
| context-bar Context window bar and a live prompt-cache countdown under the prompt | 1 ★ | Review before installing |
| clawd-bar Clawd, Claude Code's crab, lives in a band above your prompt: he acts out the session, shows what's running, y | 1 ★ | High risk |
| usage-limits Consumo de tokens, custo, previsão dos limites de 5h e semanal e recomendação de modelo | 1 ★ | High risk |
| usage-meter Minimal band: model, context tokens and estimated session cost, coloured by context fill | 1 ★ | Low risk |
| better-compact Steers every compaction, including automatic ones, with a brief that keeps goal, next step, files, decisions a | 1 ★ | Low risk |
| context-view The context window as one row above the prompt, drawn the way Claude Code draws its own meters: the context's | 1 ★ | Review before installing |
| usage-bell Rings when the session nears a limit: context fill, rate-limit windows, the auto-memory index | 1 ★ | Low risk |
| calm-recap Calm Recap: a Welcome back card when you return to the keyboard, and the prompt cache's hit rate and time left | 1 ★ | High risk |
| agent-hub Agent hub: a pane listing this session's subagents with status, model, turns and tokens, and a box to steer a | 1 ★ | Low risk |
| clawd-gotchi Bottom-left retro RPG companion: a pet fed by cache hits and commits, failing test suites as bosses. | 1 ★ | Low risk |
| context-cache Bottom-grid row: context fill and prompt cache (hit rate, countdown from the TTL the API reports). Toasts when | 1 ★ | Low risk |
| llm-speed Band showing avg time to first token and output tokens/s | 1 ★ | Low risk |
| rtk-quota Band showing rtk gain: tokens saved and quota preserved | 1 ★ | Low risk |
| usage-tracker Bottom-grid row: plan and session/week usage. Toasts when limits near. | 1 ★ | Low risk |
| session-hud 把上下文、token、缓存命中、TPS、费用、增删行数、耗时写给原生 statusLine 显示 | 1 ★ | Review before installing |
| ctx-relay A band above the prompt with context size, per-turn cost and the prompt-cache countdown. Past the handoff line | 1 ★ | High risk |
| otto-hud Otto, a blue octopus, forecasts your context window on one line above the prompt, in the Claude Code desktop a | 1 ★ | Low risk |
| companion A Claude Code companion: a Markdown kanban board pane (/board), a "please look" queue, a mood sprite, and rate | 1 ★ | High risk |
| pedidos /pedidos: panel con los pedidos de hoy de tu Tiendanube y cuánto vendiste, sin gastar tokens | 1 ★ | Low risk |
| tablero /tablero: ventas de Tiendanube + tráfico de Google Analytics + Meta Ads en un panel, con MER y conversión, sin | 1 ★ | Low risk |
| grimoire A spellbook of agent skills for AI. Cast wisely. Four skills: eagle-eye, which lays coupled decisions out as a | 1 ★ | High risk |
| clear-view Live session dashboard: what Claude is doing now, turn timing, tool stats, files touched, errors and token usa | 1 ★ | Low risk |
| gear Routes each turn's reasoning effort with TypeSafe's Jev decision model, keeping the prompt cache (Claude Code | 1 ★ | Review before installing |
| statusbar Status rows under the Claude Code prompt: model and effort pills, and context, 5-hour, 7-day and Fable usage b | 1 ★ | Low risk |
| usage-meter Shows what each request and each session took of your Claude plan's 5-hour and weekly limits | 1 ★ | Review before installing |
| cache-warm Keeps the prompt cache warm on idle chats with a capped fork ping, and tracks cache hits and misses | 1 ★ | Low risk |
| slick-bar One-line session bar above the prompt: model, effort, repo, branch, context gauge, prompt cache health, rate l | 1 ★ | Review before installing |
| prompt-cache-control Prompt-cache meter above the Claude Code prompt: how many tokens each request read from, wrote to and sent pas | 1 ★ | Low risk |
| burnrate Live quota and prompt-cache monitor for Claude Code: how fast your plan windows are filling and when they run | 1 ★ | Low risk |
| token-watch Plan usage (5-hour, weekly and any model window) and the context window as thin bars above the prompt. Right-c | 1 ★ | Review before installing |
| token-meter Shows live tokens per second, per minute and per hour in the status line | 1 ★ | Low risk |
| pastiche Ambient language learning. Hooks weave vocabulary into ordinary Claude Code sessions — stale items you are for | 1 ★ | Review before installing |
| agent-board A row above the prompt for the subagents Claude starts: running and done per model, a token bar, and a working | 1 ★ | Low risk |
| usage-ring A band above the prompt for your limits, this chat's context, prompt cache and todos, and its token total and | 1 ★ | Review before installing |
| agents-info Agents info Mod (Claude Code 2.1.287, Mods API in early access): starting agent, timeline of agents per prompt | 1 ★ | Low risk |
| token-weather-usage Demo: colored pills above the prompt: context tokens with weather, 5h/7d limits vs time elapsed, prompt cache | 1 ★ | Low risk |
| usage-bars Your Claude Code 5-hour and 7-day usage limits as animated bars under the prompt: percent, reset countdown, pa | 1 ★ | Low risk |
| tokenmunim Cost control for AI agents: a budget per task, a live ledger of every step, and a circuit breaker that stops l | 1 ★ | Review before installing |
| aitools Subscription usage, API-equivalent cost and context bar above the prompt | 1 ★ | High risk |
| cache-hit-meter Shows what share of input tokens came from the prompt cache. | 1 ★ | Low risk |
| cloud-cost-warn Warns before commands that create expensive cloud resources like GPU instances or large databases. | 1 ★ | Low risk |
| context-optimizer Keeps the context lean automatically: trims noise, picks the right moment to compact and shows the tokens it s | 1 ★ | Low risk |
| cost-meter Live session cost estimate in the status line, from real token usage. | 1 ★ | Low risk |
| daily-spend Tracks spend per day and week across sessions with a /spend report. | 1 ★ | Low risk |
| jwt-decode /jwt decodes a JSON Web Token locally — header, claims, expiry — without sending it anywhere. | 1 ★ | Low risk |
| mission-control One dashboard for every Claude session on your machine: what each is doing, cost, blockers, with pause and pri | 1 ★ | High risk |
| session-stats /session-stats shows a dashboard of turns, tools, tokens, cost, duration and files. | 1 ★ | Low risk |
| team-hub A shared panel of team conventions, recommended mods, budgets and rules, synced through the repo. | 1 ★ | Review before installing |
| token-budget Set a token or dollar budget per session; get warned at 80% and stopped at 100%. | 1 ★ | Low risk |
| token-sparkline A sparkline of tokens per turn right above the prompt. | 1 ★ | Low risk |
| clawd-buddy A small Claude Code mascot above the prompt, with usage, context, cache, directory and git status | 1 ★ | Low risk |
| leo-mods Leo's Claude Code mods: usage bars, limits, cost, prompt cache countdown, active time and running agents | 1 ★ | Review before installing |
| monitor A control room above the prompt: background agents and shells (running, done, failed), blocked tool calls and | 1 ★ | Low risk |
| usage-bar Usage bars (context, 5h, 7d, cost) above the prompt plus an auto-compact nudge; toggle with /usage-bar | 1 ★ | Low risk |
| explore-model Pins the model that background recon subagents run on. An agent.spawn hook sets the Explore subagent's model t | 1 ★ | Low risk |
| review-gate The review gate as a tool.check function hook. Every shell call is decided in process, so the non-commit calls | 1 ★ | Review before installing |
| cache-timer A countdown in the prompt footer: under the hint line on the terminal, left of the model picker on the desktop | 1 ★ | Review before installing |
| cache-meter Status line with prompt-cache hit rate, context size and TTL countdown; toasts and prices every cache rebuild | 1 ★ | Low risk |
| usage-bar Interactive band above the prompt: context fill, 5-hour and 7-day plan limits with resets, session cost, and a | 1 ★ | Low risk |
| chai-meter A taxi meter for the session's cost in the status line, in dollars and cups of chai. | 1 ★ | Low risk |
| usage-panel A /meter pane with your spend, pace, token mix, forecast, and plan week, plus /meter web: a full report that r | 1 ★ | Low risk |
| usage-tracker Shows 5-hour and weekly plan usage and the context window above the prompt | 1 ★ | Low risk |
| ctk Token-light team companion: capped agent teams, risk-based review, disciplined debugging. | 1 ★ | Review before installing |
| mize-coworker Claude as a small coworker in the terminal: an orange pixel-art Claude, two rows tall, in 132 frames. While a | 1 ★ | Review before installing |
| prompt-forge Spends your Claude Code tokens where they count: moves a new task into a fresh session (a new terminal window, | 1 ★ | Review before installing |
| token-weather A live forecast of the context window and the 5-hour and weekly quota, drawn above the prompt. | 1 ★ | Low risk |
| composio-pulse Times every composio CLI call into a status-line sparkline against a latency budget, and blocks re-linking a c | 1 ★ | Review before installing |
| review-lint Hands Claude a cache-review checklist or test rules when an edit adds a cache or a brittle test assertion | 1 ★ | Low risk |
| overalls Status band above the prompt: context weather, usage limits, and the Ponytail and Caveman levels | 1 ★ | High risk |
| burn-rate A terminal cost dashboard (/burn): spend by day, project, model, activity, tools, shell commands and MCP serve | 1 ★ | Review before installing |
| limits Claude Code mod: your 5h/7d quota, context window, prompt-cache time left and session cost on one line above t | 1 ★ | Review before installing |
| token-hamster Claude Code mod that shows token usage, 5-hour and weekly limits, reset countdown and cost per turn as an anim | 1 ★ | Low risk |
| context-meter Always-on context window meter above the prompt, with usage limits (terminal and desktop app) | 1 ★ | Low risk |
| claudebar-mod claudebar as a mod: an interactive band with git, model, effort, context, rate limits, cache, tools and agents | 1 ★ | Review before installing |