All Claude Code modsdickyadrian/agent-toolbelt
usage-bar
Subscription usage (5h and 7d windows) as progress bars above the prompt
usage-bar reaches L1 (reads) and passed claude plugin validate with warnings on Claude Code 2.1.312.
- Events hooked: 4
- API methods referenced: 9
- Access from classified calls: L1, reads: reads env vars, reads mod state, persists state, draws
- Reads mod state: the scan does not record whose state, so this does not show that it reads another mod’s values
- Static scan, not a runtime test
Install hint
/plugin install usage-bar --marketplace dickyadrian/agent-toolbeltFrom the repository's own marketplace. Confirm the plugin name in the repository's README before installing. Mods need Claude Code 2.1.287 or later.
Access
L1 Readsreads env vars, reads mod state, persists state, drawsValidation
Passed with warnings on Claude Code 2.1.312Listed under Context and usage meters for Claude Code.
View the source on GitHub Back to the list
What the scan recorded
- Observed events
- Only what it hooks
- Hooks
session.start, session.measure, command.run {command=usage-bar}, ui.render {component=AbovePrompt}- API calls
$.clock.now, $.command.register, $.env.get, $.session.usage, $.state.get, $.state.set, $.store.get, $.store.set, $.ui.resolve- Validation on 2.1.312
- Passed with warnings
- Scanned revision
6602d96388f2- Marketplace passed
- agent-toolbelt
These are the hooks and API calls reported by claude plugin validate. Access levels describe the widest reach of those calls and are not safety ratings. Validation is a static check, not a runtime test, and a passing result does not prove that a mod works or is safe. What a mod can access and how the scan works.
More from dickyadrian/agent-toolbelt
- context-gaugeHow full the context window is, split into setup and chat, above the prompt once it passes a threshold
- model-routerLogs how hard each prompt is and what every turn costs, to measure whether routing easy prompts to a cheaper…
- notion-scopeLimits Notion MCP calls to the pages a project allows, from an allowlist that never gets committed
- standupJournals what you do in each session and drafts your daily standup with /standup
- subagent-paneA side pane listing each subagent with its model, effort, live context and run mode
Badge for your README
Authors can show the latest scan result in their README. Each badge links to this page.
[](https://mods.aidojo.si/mods/dickyadrian--agent-toolbelt--usage-bar/)
[](https://mods.aidojo.si/mods/dickyadrian--agent-toolbelt--usage-bar/)