1,035 cost & usage Claude Code mods, most popular first. The most popular is ruflo-docs. Every listing shows its security level and install command.
| Name | Popularity | Security |
|---|---|---|
| ruflo-docs Documentation generation, API docs (JSDoc/TSDoc/OpenAPI), and drift detection — drives the `document` backgrou | 76.1k ★ | Low risk |
| ruflo-swarm Agent teams, swarm coordination, Monitor streams, and worktree isolation — wraps 4 swarm_* + 8 agent_* MCP too | 76.1k ★ | Review before installing |
| token-optimizer The Token Optimizer status bar on its own, for its tests. It ships inside the token-optimizer plugin. | 2.6k ★ | High risk |
| shunt A Claude Mod for the shunt gateway: a band above the prompt shows how much of each window is used and the time | 302 ★ | Review before installing |
| cache-clock A prompt-cache line under your status line, from Claude Code's own cache figures: time left while warm, hit ra | 268 ★ | Review before installing |
| context-bar Your context window as a stacked bar above the prompt, a color per category, with token counts and the compact | 268 ★ | Low risk |
| openai-balance Your OpenAI API credit above the prompt: an estimated balance with a gauge, today's spend, where the money mos | 268 ★ | Review before installing |
| openrouter-balance Your OpenRouter credit above the prompt: the balance with a gauge, today's spend and where the money mostly we | 268 ★ | Review before installing |
| switchboard Picks the model for each subagent that names none, with OpenAI's Decisions API or Jev, from its short label on | 268 ★ | Review before installing |
| token-weather A live forecast of the context window, with a prompt-cache countdown, drawn above the prompt. | 268 ★ | Review before installing |
| usage-meter Your plan's 5-hour and 7-day usage as small bars above the prompt, with the reset countdown and the session's | 268 ★ | Low risk |
| effortless Sets the reasoning effort for every prompt automatically, shows it under the prompt box, and counts down how l | 232 ★ | High risk |
| savvy-progress Progress bar above the prompt for /savvy-flow, plus an agents panel (/agents-info): running, finished and plan | 216 ★ | Low risk |
| session-band Band above the prompt: turn number, output speed, turn and session cost, prompt cache countdown and context fi | 216 ★ | Review before installing |
| cache-tax A Claude Code mod that keeps the one-hour prompt cache warm during breaks and stops a cold send once with its | 204 ★ | Review before installing |
| skins Skins for Claude Code: tool rows that open onto their input and answer, highlighted code, diff, table, math, M | 158 ★ | Review before installing |
| ctx-handoff Turns what you teach Claude into project notes, catches its usual slips, keeps the cache warm while you're awa | 111 ★ | High risk |
| great-cto You already have the agent. This is everything around it. great_cto runs Claude Code as a pipeline of 72 speci | 103 ★ | Review before installing |
| ci-watch /ci-watch : polls gh pr checks every minute in the status line, no tokens. | 93 ★ | Low risk |
| company-hq Back office for the /company skill: every /company run is its own company (state file per company, several ope | 93 ★ | High risk |
| context-meter Band above the prompt: context fill, cache read, cost, plan limits; warns at 50%/70%; Handoff button and /hand | 93 ★ | Low risk |
| spend-ledger Per-project token and cost ledger per machine; /spend; monthly note in Svod, with other machines pulled over s | 93 ★ | High risk |
| sub-meter Your subscription usage at the bottom right of Claude Code: the 5-hour and weekly windows, as a bar that takes | 91 ★ | Low risk |
| token-meter Each turn's tokens and the session's running total, in color at the end of the hint line under the prompt. | 91 ★ | Low risk |
| save-token-jev Jev-guided, verbatim context compaction for Claude Code. | 81 ★ | Review before installing |
| cache-inspector Track API cache reads, writes, and uncached input by request. | 76 ★ | Low risk |
| context-meter See the current context window fill and remaining tokens. | 76 ★ | Low risk |
| desktop-cost-watch Set a local budget reminder against reported session USD. | 76 ★ | Low risk |
| desktop-quota-clock Chart reported plan windows with live reset countdowns. | 76 ★ | Low risk |
| desktop-token-flow Chart uncached input, output, cache reads, and cache writes. | 76 ★ | Low risk |
| desktop-usage-strip Show quota, reset countdowns, tokens, and cost in a composer strip. | 76 ★ | Low risk |
| desktop-workspace-home Show the current workspace, Git state, and session usage together. | 76 ★ | Low risk |
| quota-watch Inspect reported plan windows and their reset times. | 76 ★ | Low risk |
| turn-timeline Show duration, token totals, and interruption state per turn. | 76 ★ | Low risk |
| cache-clock A one-line band above the prompt: context used, and a countdown until the prompt cache goes cold | 72 ★ | Review before installing |
| hyday-pet A virtual pet that lives above your Claude Code prompt and grows from the work Claude does: it evolves by what | 72 ★ | Low risk |
| tw-stock-mod Watchlist band above the Claude Code prompt: Taiwan hours show the Taiwan list (紅漲綠跌), US hours show the US li | 66 ★ | High risk |
| compaction-trigger Requests a session compaction when the live context passes a token threshold, so verbatim compaction plugins r | 51 ★ | Review before installing |
| jev-compact-gate Jev decides when the session compacts, inside a 280k–400k token band; Claude's own summary does the compacting | 41 ★ | Review before installing |
| cache-keeper Keeps a big chat's prompt cache warm, warns before an expensive cold restart, shows every local chat on one bo | 37 ★ | Review before installing |
| optim-jev Jev based token-usage optimization tools for Claude Code workflows. | 36 ★ | High risk |
| ccswap ccswap inside Claude Code: /ccswap to list and switch accounts, an accounts pane, a switch toast, and a quota | 33 ★ | Low risk |
| contextsaver Diagnoses wrong processes, workflows and habits in Claude Code sessions: fires on plan acceptance, workflow la | 28 ★ | Review before installing |
| usage-quota Know your Claude limits before they hit you (Live band above the Claude Code prompt): 5 Hour and Weekly usage | 24 ★ | Review before installing |
| lemo-meter 用量横条：输入框上方显示上下文、5 小时额度、花费和 git 分支；状态栏显示消息编号（已有自己的状态栏时默认关闭）；点「检查」才联网查新版本 / Usage meter: context, 5-hour quota, | 24 ★ | Low risk |
| tunnel-cost MIDDLEWARE TUNNEL stage 2: Cost analyzer: estimates the call's token cost from the args size | 22 ★ | Low risk |
| xray CLAUDE RUNTIME X-RAY: wildcard inspector with filters (/xray all|tools|subagents|session|usage|ui|errors|unkno | 22 ★ | Review before installing |
| costclaw-live COSTCLAW LIVE: per-request cost, cache decay and repeated-read detection while the session runs, and it serves | 22 ★ | Low risk |
| deck A cockpit for Claude Code: plan bars and subagent strips, context, usage limits with reset countdowns and burn | 20 ★ | Review before installing |
| context-meter Context window and session cost meter, drawn above the prompt. | 20 ★ | Low risk |
| flight-recorder See inside a turn: a live Gantt timeline of model requests, tool calls and subagents, with tokens and cost per | 20 ★ | Low risk |
| cache-meter Gauges how long the conversation's prompt cache stays warm, its hit ratio and misses, and what the next messag | 19 ★ | Low risk |
| usage-meter Shows context, 5-hour, weekly and per-model weekly limit usage above the prompt | 19 ★ | Low risk |
| gitlab GitLab workflow best practices and glab CLI usage | 18 ★ | Low risk |
| token-weather-usage One line above the prompt: context tokens with their weather, a bar per recent prompt, your 5-hour and 7-day l | 17 ★ | Low risk |
| idle-compact Compact once after 50 idle minutes, while the 1h prompt cache is still warm. | 17 ★ | Low risk |
| desktop-statusline Status band above the prompt in the Claude Desktop app's Code tab: folder, git branch and state, session age, | 16 ★ | Low risk |
| burn-meter Live session cost odometer above the prompt: a burning fuse, real-world comparisons, threshold alerts | 15 ★ | Low risk |
| cache-warmer Keep the main conversation's prompt cache warm by automatically forking its last request, tools denied and bil | 14 ★ | Review before installing |
| usage-band A band above the prompt showing your 5-hour and 7-day limits, context window and prompt-cache hit rate, styled | 14 ★ | Low risk |
| statuspane A floating status card above the Claude Code prompt — model, effort, context, 5h/week limits, cost, directory | 13 ★ | Review before installing |
| bridge KOZMOS Bridge: a mission-control sidebar. Model and effort, context fill, 5-hour and weekly limits with reset | 13 ★ | Review before installing |
| chronicle KOZMOS Chronicle: the session as a timeline. Prompts, turn ends with duration, tool count and spend, subagents | 13 ★ | Low risk |
| epilogue KOZMOS Epilogue: a recap band after every turn. Duration, tool families as colored chips, files written, subag | 13 ★ | Low risk |
| hivemind KOZMOS Hivemind: the agent swarm as a live tree. The main loop at the root and every subagent beneath its pare | 13 ★ | Low risk |
| hourglass KOZMOS Hourglass: the limit oracle. For the 5-hour, weekly and spend windows: percent used, reset countdown, a | 13 ★ | Low risk |
| laurels KOZMOS Laurels: 32 achievements earned from what the session does (Hydra, Night Owl, Cache Wizard, Bug Squashe | 13 ★ | Low risk |
| marquee KOZMOS Marquee: a status-line ticker. Model and effort, context fill, 5-hour and weekly limits with the reset | 13 ★ | Low risk |
| mosaic KOZMOS Mosaic: a GitHub-style activity calendar across sessions. 26 weeks of days colored by turns, tool calls | 13 ★ | Low risk |
| orrery KOZMOS Orrery: subagents as planets circling a central sun above the prompt. Running agents orbit at a speed s | 13 ★ | Low risk |
| polaroid KOZMOS Polaroid: /polaroid snapshots the session as a self-contained dark-neon HTML report in .kozmos/reports: | 13 ★ | Low risk |
| relay KOZMOS Relay: the API latency lab in a sidebar. Every model request of the main loop and its subagents with la | 13 ★ | Low risk |
| stamp KOZMOS Stamp: a receipt on every finished turn. The closing 'Baked for 42s' line becomes a compact row of dura | 13 ★ | Low risk |
| thrift KOZMOS Thrift: a frugal mode. /thrift on|off|auto; while on, every prompt carries a short note asking Claude t | 13 ★ | Low risk |
| throttle KOZMOS Throttle: a car dashboard above the prompt. Speedometer of output tokens per second, fuel gauge of the | 13 ★ | Low risk |
| tokenomics KOZMOS Tokenomics: the cost lab. Session cost as the headline, an estimated split by model and by token type, | 13 ★ | Low risk |
| warpdrive KOZMOS Warpdrive: a starfield at warp above the prompt. Stars stream out of the center at the speed of Claude' | 13 ★ | Low risk |
| pixelband Animated pixel art above your Claude Code prompt that reacts while Claude works: seven scenes, or your own ima | 13 ★ | Review before installing |
| token-usage 5h / 7d usage, token totals and cost pills above the prompt | 12 ★ | Low risk |
| handoff-compact Replaces Claude Code's compaction with a structured handoff: a fork of the session writes it from the prompt c | 12 ★ | Review before installing |
| agentpane A side pane for Claude Code that lists the subagents a session runs, what each is doing and what it costs in t | 12 ★ | Low risk |
| cache-warm Keeps the 1-hour prompt cache warm for a window you set, or with no end in every session under always, with on | 11 ★ | Review before installing |
| effort-auto Has a small model rate how hard each prompt is and runs that turn and its subagents at the matching effort, wi | 11 ★ | Low risk |
| gemini-core Keeps the Gemini keys and tier of every Gemini mod, and each mod's model and thinking level, in one place: add | 11 ★ | Review before installing |
| limit-watch Shows the subscription usage limits under the prompt or in the shared sidebar with a reset countdown and a pro | 11 ★ | Low risk |
| session-watch Shows this session's state in the sidebar: context fill, token totals, cost, model and effort, the Claude Code | 11 ★ | Review before installing |
| subagent-ledger Shows each subagent of the session with its turns, time, model and tokens, the costliest first, yellow while i | 11 ★ | Low risk |
| flowpane A live workflow pane: replaces the default Workflow progress list with a phase-by-phase graph or a timeline be | 11 ★ | Low risk |
| cache-clock Shows how long the prompt cache stays warm, and when it expires, exactly how many tokens your next message wil | 10 ★ | Low risk |
| kit-updates Tells you when a newer version of an installed claude-pro-kit mod is out, and /kit-update installs it along wi | 10 ★ | Review before installing |
| peek Typing "status" while background shells or subagents run opens a pane with each task's exact elapsed time, the | 10 ★ | Low risk |
| pro-hud Desktop heads-up display for the Pro plan: exact 5h/7d usage gauges, context gauge, turn receipts, usage in th | 10 ★ | Low risk |
| prompt-polish An Improve button above the prompt (and /polish) rewrites your draft with Opus at low effort (/polish model pi | 10 ★ | Low risk |
| session-receipt /receipt opens a pane with the exact tokens every turn of the session spent (uncached, cached, output, subagen | 10 ★ | Low risk |
| turn-budget When one turn uses more than +5 session points or 500,000 uncached input tokens, writes a handoff from exact s | 10 ★ | Review before installing |
| quota-meter Shows the subscription plan limits - the 5-hour window, the 7-day window and a gateway spend limit - as a pinn | 9 ★ | Low risk |
| token-ledger A per-turn cost and token ledger: a pinned status line with the session cost, the last turn's tokens and the c | 9 ★ | Low risk |
| usage-meter Plan-limit bars with burn rate and time-to-empty, session cost, cache hit ratio and tokens-per-turn sparkline. | 9 ★ | Low risk |
| jev-context Jev keeps the context window lean so compaction comes later: prunes tool output on entry, caps subagent report | 8 ★ | Review before installing |
| usage-band Your Claude plan usage in one line above the prompt: 5-hour and weekly limits with reset times, context window | 8 ★ | Low risk |