Claude Code mod
agent-usage
A pane showing how many tokens the main conversation and each subagent consumed, in Vesuvius colors
Install
/plugin marketplace add pompeitech/affreschi
/plugin install agent-usage@affreschiMods install like plugins. Run /reload-plugins or start a new session to load it.
What it can access
- Reach
- L1Reads: reads mod state, draws
- Sees
- every prompt, subagent spawns, every tool call, Agent calls
- Draws in
Pane- Hooks
session.startcommand.runprompt.submitagent.spawnturn.steptool.callturn.completeui.render
From a static scan of the mod's code by awesome-claude-code-mods. It shows what the code asks for, not a security review.
How Claude Code mods work
- A mod is a plugin with a JavaScript or TypeScript module that runs inside Claude Code (version 2.1.287 or later). It can draw panes beside the transcript, a band above the prompt, buttons and toasts, restyle the spinner and tool rows, and watch or rewrite tool calls and prompts.
- It installs like any plugin: add its marketplace with /plugin marketplace add owner/repo, then /plugin install name@marketplace.
- Check what a mod can reach before installing: it runs with your permissions. Reach goes from drawing only, to reading files, to writing files or running processes, to the network. Run claude plugin validate on a clone to list its hooks and calls without running it.
- Turn one off from the Installed tab in /plugin, or start Claude Code with --safe-mode to skip every customization for a session.
Details
- Repository
- pompeitech/affreschi
- Folder
plugins/agent-usage- Marketplace
affreschi- Author
- Davide D'Antonio
- Last updated
- 26 October 2026
- Listed in
- awesome-claude-code-mods
FAQ
What is agent-usage?
A pane showing how many tokens the main conversation and each subagent consumed, in Vesuvius colors It is a mod for Claude Code, from pompeitech/affreschi on GitHub.
What can the agent-usage mod access?
Its widest reach is "reads" (reads mod state, draws). It sees every prompt, subagent spawns, every tool call, Agent calls. It draws in Pane. Like any mod, it runs with your permissions.
How do I install agent-usage?
Inside Claude Code (v2.1.287 or later), run /plugin marketplace add pompeitech/affreschi and then /plugin install agent-usage@affreschi.
More context & usage mods
cost-bar
1Justmalhar/awesome-claude-mods
A one-row band above the prompt with session cost, 5h/7d plan limits and an optional budget bar.
auto-resume
tartinerlabs/claude-code-mods
Sends "continue" once a usage limit resets, so a turn cut off by the limit picks up where it stopped.
context-xray
12VedantAndhale/claude-pro-kit
A pane with the exact breakdown of what fills Claude's context: system prompt, tools, memory files, skills, messages, and which tools load on every request.
cache-countdown
broening/claude-mods
Zeigt ueber dem Prompt, wie lange der Prompt-Cache noch warm ist, mit Compact-Knopf und Auto-Compact kurz vor kalt
marquee
21ersinkoc/claude-mods
KOZMOS Marquee: a status-line ticker. Model and effort, context fill, 5-hour and weekly limits with the reset countdown, session cost, git branch with ahead and dirty counts, and the tool running now, refreshed every second; it scrolls like a marquee when longer than its width. /marquee toggles it.
compact-advisor
vincentlauriat/ModsTools
Toasts once when the context crosses a threshold; /compact-advisor prints a ready-to-paste /compact line with branch, edited files, open tasks and the last goal
Browse the most popular Claude Code mods, all context & usage mods, or the skills and MCP server directories.