budget-guard 0.16.1
Keeps token spend down: Opus capped at medium effort, compaction at 200k, context guard, subagent cap, image/generated-file read guard, and a budget HUD above the prompt (with LiteLLM key spend).
nbotondInstall
/plugin marketplace add nbotond20/claude-mods /plugin install budget-guard@my-mods
Run both lines inside Claude Code.
Hooks into
- Pane
- Prompt
- Tool calls
- Toasts
- Slash commands
Also in nbotond20/claude-mods
-
usage-analytics
0.16.1
Records every model request, tool call, prompt, context breakdown, compaction and rate-limit reading from every profile into one store in the mods data folder, with a live dashboard, a weekly digest, shareable summaries, mod impact verdicts and a statistical advisor.
nbotond in Usage & cost, updated
0
-
lsp-first
0.5.3
Makes Claude actually use the TypeScript LSP: the LSP tool is loaded up front, the system prompt says when to prefer it, and symbol-shaped Greps over TS/JS get a nudge.
nbotond in Guardrails, updated
0
-
lean-tools
0.5.3
Cuts what tool calls put into the context: caps huge shell output (full log kept on disk), bounds git log, and nudges toward parallel/batched calls, ranged reads, Edit over Write and no re-reads.
nbotond in Git, updated
0
-
no-attribution
0.3.3
Claude never credits itself: no Co-Authored-By, no 'Generated with Claude Code', no Claude author, in commits, PRs, files or tool calls
nbotond in Git, updated
0
-
timesheet
0.4.1
mod + skill
NetSuite-ready timesheets from your Claude Code and OpenCode sessions, git and GitHub history and Google Calendar: the timesheet CLI and web app, the timesheet skill, and /timesheet.
nbotond in Git, updated
0
-
observability
0.1.8
A free, local observability platform for Claude Code: Grafana with trace waterfalls, logs, metrics and dashboards (spend, latency, where time goes, errors, tools, hooks, MCP) for every profile, fed by Claude Code's own OpenTelemetry. Runs in Docker on 127.0.0.1; nothing leaves the machine.
nbotond in Usage & cost, updated
0
More usage & cost mods
-
token-weather
0.1.0
A live forecast of the context window, drawn above the prompt.
deepseek-ai in Usage & cost, updated
269.9k
-
token-optimizer
5.13.51
mod + skill
Audit, fix, and monitor Claude Code context window usage. Find the ghost tokens.
Alex Greenshpun in Usage & cost, updated
2.6k
-
token-run
0.1.3
A fully local ASCII runner game for Claude Code request failures and short breaks
YeonwooSung in Usage & cost, updated
1.1k
-
artifact-dashboard
0.1.0
A one-line summary of the project's shared Kanban artifact above the prompt, read through Claude's own ArtifactData tool
Danny McAteer in Usage & cost, updated
750
-
context-bar
0.1.5
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.
Hamza Zafar in Usage & cost, updated
436