Usage Inspector
One line above the prompt: context, cost, per-turn tokens and 5h/7d limit pace.
Illustration. Actual results depend on the mod, terminal and environment.
Install
/plugin marketplace add purplecofe/usage-inspector
/plugin install usage-inspector@usage-inspector
/reload-pluginsRun these commands one at a time in a Claude Code session.
claude plugin marketplace add purplecofe/usage-inspector
claude plugin install usage-inspector@usage-inspectorThen run /reload-plugins in your session, or start a new session.
Please install the Claude Code mod "Usage Inspector" (https://github.com/purplecofe/usage-inspector). Before installing, read the Security and Requirements sections of its README and tell me what it reads and writes, which commands it runs, whether it uses the network, and which Claude Code version, OS and terminal it needs. If everything looks fine, run claude plugin marketplace add purplecofe/usage-inspector and claude plugin install usage-inspector@usage-inspector, then remind me to run /reload-plugins in my session.Send this to Claude Code so it reads the author’s instructions before installing.
git clone https://github.com/purplecofe/usage-inspector
cd usage-inspector
claude --plugin-dir .Clone the repository and try it in a local session with --plugin-dir.
What it accesses
Based on the author’s documentation, checked when listed; use claude plugin validate to check for yourself.
Reads
YesReads session context, cost and 5h/7d limit usage.
Writes files
YesSaves the last 8 turns of token history in the plugin store.
Runs commands
UnspecifiedNot stated in the README; no external commands seen in the code.
Network
UnspecifiedNot stated in the README; no network calls seen in the code.
Introduction
Usage Inspector is a Claude Code mod that pins a one-line usage band above the prompt, so you don't need /context or /usage.
- Context: percent used,
tokens / windowand session cost; green below 60%, yellow 60–84%, red from 85%. - Turns: tokens added by each of the last 8 prompts; the latest bar is blue and labelled (e.g.
+12k) and grows live while Claude responds. - 5h / 7d: percent of each limit used next to a marker for time elapsed, plus time left and reset time; when usage runs ahead of time the gap is hatched, turning red beyond 15 points or at 90% used.
- Click
ⓘor run/context-detailfor a pane with model, auto-compact threshold and headroom, cache hit rate, tokens per category, top MCP servers and memory files, and tokens used by skills, agents and slash commands; it refreshes every turn while open.
The last 8 turns are kept in the plugin store and return in a new session. The author says it works in the terminal, desktop app and VS Code; no minimum Claude Code version or security section is given. The preview is illustrative.
Who it is for
- People who want context and limits in view without running /context
Requirements
- Author says it works in the terminal, desktop app and VS Code; no minimum Claude Code version stated.