usage-meter

One live line above the prompt per running subagent or background shell: its model, time, tool count and what it's doing. /radar shows every agent and its messages.

Holds risky Bash commands and shows what they would change before they run.

Shows if this session has a Playwright browser and who holds it. /browser clean closes leftover browsers. A subagent that wants the browser waits until the one using it is done.

A prompt-cache line under your status line, from Claude Code's own cache figures: time left while warm, hit rate and misses, and how many tokens the next message re-caches once cold. /cache-clock setup adds it.

Your context window as a stacked bar above the prompt, a color per category, with token counts and the compaction point. /context-bar shows or hides it.

One line above the prompt with what needs you: next meeting, PRs, Linear issues and Slack DMs. /glance lists them all.

Claude Code mod: watch Headroom snip tokens off every request, with an animated band, a /headroom log and a running total.

While Claude works, Clawd (Claude Code's mascot) acts out the spinner's -ing word and the running tool on a little stage above the prompt: 26 animated scenes, wandering the band, changing scene every 30 seconds on long turns.

1 skill

Optional companion to claude-blog (needs claude-blog 2.3.2 or later): article status band, live pipeline and five-gate review panel, history of past blogs, and an explicit Run checks control. A Claude Code mod served from the blog-studio branch; install it separately.

claude-reflect as a Claude Code mod (early access): checks each short prompt with a model, saves rules from a band above the prompt

Screens a dismissal — proposed or already done — against the unfair dismissal framework for England & Wales, and shows where it is exposed. Structures the qualifying-service question, the automatically-unfair categories (no qualifying period), and a Burchell / Polkey / band-of-reasonable-responses analysis for a solicitor to verify — it does not determine fairness. Surfaces specific procedural risks. Use when the user says 'is this unfair', 'screen this dismissal', 'ordinary unfair dismissal', 'automatic unfair dismissal', or wants a structured fairness review before or after dismissal.

200 skills

Tripwire for out-of-band config changes: warns on every mid-session settings/skills change (or blocks it with CONFIG_WATCH_BLOCK=true) to catch installer scripts and npm payloads rewriting settings behind Claude Code's back.

hooks