What is turn-budget?
turn-budget is a Claude Code mod by VedantAndhale that when one turn uses more than +5 session points or 500,000 uncached input tokens, writes a handoff from exact session data and copies it for a new session; the old session is never cleared. It is listed under Cost & usage and has 10 GitHub stars.
| Type | Claude code mod |
|---|---|
| Author | VedantAndhale |
| Repository | VedantAndhale/claude-pro-kit |
| Popularity | 10 GitHub stars |
| Category | Cost & usage |
| Security | Review before installing (64/100) |
| Rank | #532 of 5,272 Claude Code mods; #95 in Cost & usage |
| License | MIT |
| Last commit | 2026-10-09 |
| Stars this week | +4 |
| Hooks | 7 events |
| Sees | every tool call |
| Draws on | nothing |
Is turn-budget safe to install?
turn-budget scores 64/100 on the MCPMods security check: Review before installing. Things to review: starts processes outside the sandbox; writes files or config; reads environment variables. It passed 5 of 8 checks.
Mod footprints come from claude plugin validate, which lists every event a mod hooks and every API call it makes without running it.
| Check | Result |
|---|---|
| No network access | Pass |
| Starts processes outside the sandbox | Review |
| Writes files or config | Review |
| Reads environment variables | Review |
| Only sees the events it hooks | Pass |
| Doesn't drive Claude | Pass |
| Passes claude plugin validate | Pass |
| Has an open-source license | Pass |
API calls in its code
| Call | What it means |
|---|---|
$.clock.now | |
$.command.register | |
$.env.get | reads env vars |
$.fs.write | writes files |
$.process.run | runs processes |
$.session.append | |
$.session.cwd | |
$.session.messages | reads the transcript |
$.store.get | keeps its own state |
$.store.set | keeps its own state |
$.turn.abort | drives Claude |
$.ui.ask | draws interface |
$.ui.copy | draws interface |
$.ui.status | draws interface |
$.ui.toast | draws interface |
How do I install turn-budget?
- Check your Claude Code version. Mods need Claude Code 2.1.287 or later and are on by default.
claude --version
- Read its footprint. This lists every event it hooks and every API call it makes, without running it.
git clone https://github.com/VedantAndhale/claude-pro-kit claude plugin validate ./claude-pro-kit/plugins/turn-budget
- Install it. Run this in your terminal, then /reload-plugins in an open session.
claude plugin marketplace add VedantAndhale/claude-pro-kit && claude plugin install turn-budget@claude-pro-kit
Or ask Claude to set it up
Paste this into Claude Code and it installs turn-budget for you:
Install the "turn-budget" Claude Code mod from https://github.com/VedantAndhale/claude-pro-kit/tree/main/plugins/turn-budget. Run claude plugin validate on it first and show me what it can access before you enable it.
More from VedantAndhale/claude-pro-kit
This repository has at least 9 Claude Code mods on MCPMods.
- agent-diet: Runs search-only subagents (Explore by default) on Haiku instead of your main model; a model Claude asks for still wins, (Low risk)
- answer-pane: Explain, plan and ELI5 pages drawn natively in a side pane: diagrams in place, plan decisions as buttons, Respond fills (Review before installing)
- budget-guard: Holds a prompt back once your 5-hour or weekly usage is at or over a limit you set (90% by default); sending it again go (Low risk)
- cache-clock: Shows how long the prompt cache stays warm, and when it expires, exactly how many tokens your next message will re-send (Low risk)
- cmd-diet: Adds quiet flags to noisy shell commands before they run (git status, pytest, cargo, npm install, mvn, curl, wget, docke (Low risk)
- collision-guard: Asks before Claude edits a file another chat on this machine changed in the last 30 minutes. Each chat keeps its own sma (Review before installing)
- compact-keeper: After a compaction, adds one message with exact facts from before it: your latest prompt in full, up to 4 earlier ones, (Low risk)
- context-xray: A pane with the exact breakdown of what fills Claude's context: system prompt, tools, memory files, skills, messages, an (Low risk)