Claude Code mod
usage-guard
Winds sessions and subagents down before the 5-hour or 7-day subscription limit: one wind-down note per band, a handoff file, spawn and loop denies near the limit, optional resume after the reset
Install
/plugin marketplace add aliaksei-loi/usage-guard
/plugin install usage-guard@usage-guardMods install like plugins. Run /reload-plugins or start a new session to load it.
What it can access
- Reach
- L2Writes or runs: writes files, drives Claude, reads files, reads env vars, reads the transcript, reads mod state, draws
- Sees
- every tool call, subagent spawns, classic hooks
- Draws in
AbovePrompt- Hooks
session.startsession.measuretool.callagent.spawnturn.completeclassic.StopFailurecommand.runui.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
- aliaksei-loi/usage-guard
- Folder
.- Marketplace
usage-guard- Author
- Aliaksei Loi
- License
- MIT
- Last updated
- 9 October 2026
- Listed in
- awesome-claude-code-mods
FAQ
What is usage-guard?
Winds sessions and subagents down before the 5-hour or 7-day subscription limit: one wind-down note per band, a handoff file, spawn and loop denies near the limit, optional resume after the reset It is a mod for Claude Code, from aliaksei-loi/usage-guard on GitHub.
What can the usage-guard mod access?
Its widest reach is "writes or runs" (writes files, drives Claude, reads files, reads env vars, reads the transcript, reads mod state, draws). It sees every tool call, subagent spawns, classic hooks. It draws in AbovePrompt. Like any mod, it runs with your permissions.
How do I install usage-guard?
Inside Claude Code (v2.1.287 or later), run /plugin marketplace add aliaksei-loi/usage-guard and then /plugin install usage-guard@usage-guard.
More context & usage mods
usage-gauges
maximemarc/Claude-mods
Bande projet, branche, diff et agents, jauges contexte, 5 h et hebdo, coût de session et alertes de seuil
usage-guard
Marnel8/claude-mods-
Asks before a large or token-heavy prompt is sent, showing your 5-hour and weekly usage and an estimate of what it may cost
usage-gauge
Joseph-Ayoub/claude-mods
(superseded by rd-ledger) A live cost chip in the prompt footer and a /spend Usage pane: the session's cost, context by category, rate limits, tokens and cache hit per model, subagent share and code changes, without /usage landing in the transcript.
usage-hud
chandan84/cache-time-pending-usage-limit-mod
Three-box HUD above the prompt: tokens and API-equivalent cost across all sessions (daily and per-session breakdown), context-window meter with a soft limit, and prompt-cache warmth countdown with last-turn tokens and cost.
usage-forecast
thangdo19/claude-code-mods
A live forecast of your context window, plus your session and weekly usage limits, in the band above the prompt.
usage-hud
Jang-seungminn/usage-hud
Above-prompt HUD for Claude Code: context fill, 5h/7d rate limits with burn ETA, turn cost, cache hit, git, model and two animated dogs
Browse the most popular Claude Code mods, all context & usage mods, or the skills and MCP server directories.