Claude Code Mods

Context, prompt-cache and usage-limit meters right above the Claude Code prompt, a row of dropdowns for agents, skills and commands, a pane that lists everything your setup provides, and one that adds up your token usage.

Why

Claude Code shows little of what costs you: how full the context is, whether the prompt cache is still warm, and how much of your usage limits is left. These mods put those figures in a band right above the prompt, at no token cost.

• Hit the 5-hour limit mid-task? usage-limits shows the 5-hour and weekly windows and when each resets, shared across all open sessions.
• Auto-compaction at the worst moment? context-meter shows the fill against the threshold and compacts at the point you pick.
• Back from a break to a cold cache? Writing 200k tokens of context again costs about $1.00 on Claude Opus 5.5. cache-meter shows when the cache goes cold and can keep it warm at about $0.04 a refresh.
• Can't remember the name of that agent or skill? command-center lists your agents, skills and commands in dropdowns above the prompt, filtered by where they come from, and inserts or runs the pick.
• Lost track of what your setup loads? catalog-pane lists every skill, plugin, hook and MCP server with its usage and the tokens it adds to every session.
• Where did this week's tokens go? usage-pane adds up tokens, cache hit rate and API price by day, model and project, and shows which prompts cost the most and why.

Installation

Add the marketplace once, then install the mods you want with the first command in their row of the Mods table. To update, run the second lines: the marketplace first, then each mod. The commands work in any shell, or inside Claude Code with /plugin in place of claude plugin. New sessions load the changes.

claude plugin marketplace add T-AI-Labs/claude-code-mods
claude plugin marketplace update T-AI-Labs

Mods

context-meter and usage-limits are the two rows of context-usage as separate mods: install either context-usage or those two, not both.

Mod	Description	Preview
context‑usage	Start here. Context fill and usage limits. claude plugin install context-usage@T-AI-Labs claude plugin update context-usage@T-AI-Labs
cache‑meter	Prompt-cache hits and when the cache goes cold. claude plugin install cache-meter@T-AI-Labs claude plugin update cache-meter@T-AI-Labs
catalog‑pane	Every skill, plugin, hook and MCP server you have. claude plugin install catalog-pane@T-AI-Labs claude plugin update catalog-pane@T-AI-Labs
usage‑pane	Tokens and API price by day, session and prompt. claude plugin install usage-pane@T-AI-Labs claude plugin update usage-pane@T-AI-Labs
command‑center	Agents, skills and commands in dropdowns. claude plugin install command-center@T-AI-Labs claude plugin update command-center@T-AI-Labs
context‑meter	The context row of context-usage on its own. claude plugin install context-meter@T-AI-Labs claude plugin update context-meter@T-AI-Labs
usage‑limits	The usage row of context-usage on its own. claude plugin install usage-limits@T-AI-Labs claude plugin update usage-limits@T-AI-Labs

context-usage 

context-meter and usage-limits in one mod: the context row and the usage row beneath it. Both work as described under context-meter and usage-limits. To switch from the two separate mods, install context-usage, uninstall context-meter and usage-limits, and pick the threshold again.

Usage

The rows sit in the band above the prompt and cost no tokens: they only read figures Claude Code already has. In the terminal, ctrl+x tab moves into the band: Tab walks the controls, Enter presses a button, the arrow keys pick a threshold. ctrl+x ctrl+a or the band's [-] mark collapses it.

Options

'{"display":"text","usagePosition":"above"}' | claude plugin configure context-usage@T-AI-Labs --values-stdin

That is PowerShell; in cmd, use echo {"display":"text"} | …. Options you leave out keep their value, the command without --values-stdin shows what is set, and a new session picks up the change. --config display=text sets an option while installing, and in a terminal session the options are rows of the /config menu.

context-meter 

Usage

The row sits in the band above the prompt and costs no tokens: it only reads figures Claude Code already has. In the desktop app it is two lines high so the app's taller buttons fit. In the terminal, ctrl+x tab moves into the band: Tab walks the controls, Enter presses a button, the arrow keys pick a threshold. ctrl+x ctrl+a or the band's [-] mark collapses it.

Until the first response of a session, and again after a clear, the fill reads 0%: the engine counts the system prompt and tools only once a response arrives.

Options

'{"display":"text","details":"false"}' | claude plugin configure context-meter@T-AI-Labs --values-stdin

Set them as for context-usage. The row needs about 62 columns with the defaults; on a narrower window the buttons wrap to a second line. details off saves about 11 columns, display set to text about 6:

How auto-compact works

After each turn the mod compares the fill with the threshold and runs /compact once it is reached. It fires again only after the fill has dropped below the threshold, so a compaction that lands above it does not loop. Claude Code's built-in auto-compaction still runs at its own limit, so a threshold above that limit never fires.

Every compaction costs tokens, whether you press Compact or the threshold triggers it: /compact is a model request that summarizes the conversation, and the next turn starts on a cold cache. To keep usage down, leave the threshold high and compact by hand when it suits you.

usage-limits 

A gauge for each rate-limit window, with the percentage used and the time until it resets: 5h for the 5-hour limit, Week for the weekly one. Yellow from 75 %, red from 90 %.

Usage

The row sits in the band above the prompt and costs no tokens. ctrl+x ctrl+a or the band's [-] mark collapses it in the terminal.

Claude Code reports the limits only on a subscription plan, with each response. Until the first one, and right after a /clear, the row shows the last reading, with a window that has reset since at 0 %. A window that never had a reading shows –.

Sessions running side by side share their readings through a file on your machine, once a minute and at no token cost, so an idle session still shows what the others used. context-usage and usage-limits keep separate stores and do not share with each other.

Options

'{"display":"text"}' | claude plugin configure usage-limits@T-AI-Labs --values-stdin

Set them as for context-usage. Give the row mods the same display and details to keep their columns aligned.

cache-meter 

Usage

The row sits in the band above the prompt and costs no tokens; only Keep warm's refreshes are model requests. Keep warm is a text link in the desktop app and a button elsewhere. In the terminal, ctrl+x tab moves into the band, Tab walks the controls and Enter presses one. ctrl+x ctrl+a or the band's [-] mark collapses it.

Before 0.4.0 cache-meter also showed the context fill, threshold, Compact and Clear. They moved to context-meter, which an update does not install: install it and pick the threshold again.

Options

'{"keepWarmMinutes":"120"}' | claude plugin configure cache-meter@T-AI-Labs --values-stdin

Set them as for context-usage.

Why the hit rate matters

Every turn sends the whole conversation again. Cached tokens cost about a tenth of the input price, a twentieth on Claude Opus 5.5; writing them to the cache costs 1.25 times the input price. The cache lapses after a pause, on a model switch, and when something early in the context changes, such as CLAUDE.md or the tools.

What Keep warm costs

Each refresh reads the cached context once at the cache price, plus a one-word reply. With 200k tokens on Claude Opus 5.5 that is about $0.04, against about $1.00 for writing the context again after it went cold. At one refresh every four and a half minutes, an hour costs about half a rewrite: worth it if you come back, lost if you don't. On a subscription the refreshes count against the usage limits.

catalog-pane 

A pane with one tab per category: Skills, Commands, Agents, Mods, Plugins, Hooks (from the settings files), MCP servers and built-in Tools.

Usage

/catalog opens the pane, in the desktop app and in the terminal; /catalog mods opens a category, /catalog <text> a search. Each row shows the entry's origin, how often it was used in total and in the last 30 days, and for plugin parts the tokens it adds to every session. Usage is counted from the install of the mod on. On the desktop you can filter by text and origin and sort:

Pressing an entry opens its detail: usage over 7 and 30 days, token cost, version and install dates, what a mod hooks and calls, the repository and the full description. Explain with Haiku sums up in three sentences what the entry is for. The buttons depend on the kind: insert or run a skill or command, insert an agent, MCP server or tool into the prompt, update, disable or uninstall a plugin or mod, remove a local MCP server. Uninstalling and removing ask first.

Options

'{"language":"German"}' | claude plugin configure catalog-pane@T-AI-Labs --values-stdin

Set them as for context-usage.

Network and model requests

• GitHub: once a day, the public API for each plugin repository's stars, forks, open issues and last push. Off with githubStats.
• Haiku: one request of at most 400 output tokens per Explain with Haiku. The answer is kept, so each entry is explained once.
• Claude Code CLI: claude plugin details once per plugin version for its token cost, claude plugin validate once per mod version, and update, disable, enable or uninstall when you press those buttons.

Everything else comes from Claude Code and the configuration files, and is kept in the mod's own store.

usage-pane 

A pane with one tab per period: Last turn, Session, Today, 7 days and 30 days, and two that show where the cost came from: Sessions and Prompts.

Usage

/tokens opens the pane, in the desktop app and in the terminal; /tokens today, /tokens month or /tokens prompts opens that tab. It costs no tokens and makes no model requests.

Sessions and prompts

Sessions lists the sessions of the last 30 days, newest first, with their price, project, number of prompts and first prompt. Pressing one opens its prompts.

Prompts lists the prompts of a session, most expensive first; pressing one shows it in full:

Usage is counted from the install of the mod on, in every session that runs it, and kept for 31 days; the details of each prompt are kept for 7 days. Model time and output speed are counted from version 0.3.0 on. The limits fill in once Claude Code reports them, on a subscription plan with each response.

command-center 

Usage

The row sits in the band above the prompt, in the terminal and the desktop app, and costs no tokens; only what Run starts does. In the desktop app it is two lines high so the app's taller controls fit. The mobile app has no dropdowns, so the row stays out of it there. In the terminal, ctrl+x tab moves into the band: Tab walks the controls, Enter presses a button, the arrow keys pick an entry.

The agent list fills from the agent types Claude Code offers the model, so in the first session after the install it is empty until the first prompt; the mod keeps them for the sessions after. Skills are told from commands by their folders, so skills that ship with Claude Code itself are listed under Command. A dropdown holds at most 63 entries: the recently used come first, and Source brings back the ones cut off.

License

MIT