Claude Code mod

lk-token-budget

Stop runaway token spend: budgets per session and per subagent with warn, deny-agents or stop actions, plus a prompt-cache countdown, cold-cache pings and keep-warm.

1 starsContext & usage mods Plugin marketplaceValidates on Claude Code 2.1.316 Source

Install

Inside Claude Code
/plugin marketplace add connectwithub/loopkeeper
/plugin install lk-token-budget@loopkeeper

Mods install like plugins. Run /reload-plugins or start a new session to load it.

What it can access

Reach
L2Writes or runs: drives Claude, reads files, reads env vars, reads mod state, persists state, draws
Sees
classic hooks, compaction, every prompt, subagent spawns, every tool call
Draws in
AbovePromptPane
Hooks
session.startclassic.SessionStartsession.compactprompt.submitsession.endturn.stepturn.startturn.completeagent.spawntool.callcommand.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.
Claude Code docs

Details

Folder
plugins/lk-token-budget
Marketplace
loopkeeper
Author
connectwithub
License
NOASSERTION
Last updated
14 October 2026

FAQ

What is lk-token-budget?

Stop runaway token spend: budgets per session and per subagent with warn, deny-agents or stop actions, plus a prompt-cache countdown, cold-cache pings and keep-warm. It is a mod for Claude Code, from connectwithub/loopkeeper on GitHub.

What can the lk-token-budget mod access?

Its widest reach is "writes or runs" (drives Claude, reads files, reads env vars, reads mod state, persists state, draws). It sees classic hooks, compaction, every prompt, subagent spawns, every tool call. It draws in AbovePrompt, Pane. Like any mod, it runs with your permissions.

How do I install lk-token-budget?

Inside Claude Code (v2.1.287 or later), run /plugin marketplace add connectwithub/loopkeeper and then /plugin install lk-token-budget@loopkeeper.

Is lk-token-budget popular?

connectwithub/loopkeeper has 1 GitHub stars and 0 forks, and is included in 1 curated Claude Code list. It was last updated on 14 October 2026.

More context & usage mods

lk-agent-map

1

connectwithub/loopkeeper

See and cap your subagents: cards with cost, tokens, context and progress, spawn caps with an override you approve, tree and team views, idle alerts and a Stop button.

Context & usage mods/plugin install

lookout

1

StartupBros-com/hov-marketplace

A second pair of eyes while Claude works. Every few model steps it asks one tool-less fork of the session (served from the prompt cache) whether there is something you should know and might miss, and shows the answer above the prompt. No model call while nothing draws the session.

Context & usage mods

litellm-key

1

juninmd/cc-litellm

See your LiteLLM virtual key inside Claude Code: budget, spend, limits, expiry, models and recent usage. Admins can also create and edit keys, grant extra budget and read router fallbacks.

Context & usage mods/plugin install

luna-pruner

1

luancamara/luna-pruner

Context-size meter, noisy tool-output pruning and a cost audit for Claude Code, using OpenAI Decisions (gpt-6-luna).

Context & usage mods/plugin install

limits-band

1

burnrate-ai/burnrate

Band above the prompt: 5h/7d limits with reset timers, context fill, cache hit rate and what fills your context.

Context & usage mods/plugin install

model-picker

1

juampymdd/claude-code-model-picker

A band above the prompt to pick which model, and which version of it, runs the next requests, with cost, tokens and cache stats an animated pane of charts and live agents for the whole session, and a tab where Claude notes the theory behind what it builds.

Context & usage mods/plugin install

Browse the most popular Claude Code mods, all context & usage mods, or the skills and MCP server directories.