prompt-polish 0.1.3
An Improve button above the prompt (and /polish) rewrites your draft with Opus at low effort (/polish model picks another) using the prompt-master rules (MIT, nidhinjs/prompt-master); Undo puts the original back. Each press is one model call; its exact tokens are shown.
Vedant AndhaleInstall
/plugin marketplace add VedantAndhale/claude-pro-kit /plugin install prompt-polish@claude-pro-kit
Run both lines inside Claude Code.
Hooks into
- Prompt
- Toasts
- Slash commands
Also in VedantAndhale/claude-pro-kit
-
turn-budget
0.4.0
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. No model calls.
Vedant Andhale in Status line, updated
4
-
session-receipt
0.2.0
/receipt opens a pane with the exact tokens every turn of the session spent (uncached, cached, output, subagents) and the costliest turns. No tokens spent.
Vedant Andhale in Panes, updated
4
-
pro-hud
0.3.1
Desktop heads-up display for the Pro plan: exact 5h/7d usage gauges, context gauge, turn receipts, usage in the spinner and compact tool cards. No estimates, no tokens spent.
Vedant Andhale in Usage & cost, updated
4
-
output-diet
0.2.0
Trims long shell output, Grep results and subagent reports before Claude reads them (head, tail and error lines kept); the untrimmed text is saved to a file Claude can open.
Vedant Andhale in Status line, updated
4
-
tool-diet
0.1.3
Moves tools you have not used lately behind ToolSearch, so their descriptions stop riding along on every request; core tools and anything you used in your last five sessions stay loaded.
Vedant Andhale in Status line, updated
4
-
context-xray
0.2.0
A pane with the exact breakdown of what fills Claude's context: system prompt, tools, memory files, skills, messages, and which tools load on every request.
Vedant Andhale in Panes, updated
4
-
reread-guard
0.2.0
Stops Claude re-reading a file it already read in this conversation, with Read or a plain cat, sed -n, head, tail or Get-Content, when the file has not changed since; a deliberate second attempt still goes through.
Vedant Andhale in Guardrails, updated
4
-
cache-clock
0.2.0
Shows how long the prompt cache stays warm, and when it expires, exactly how many tokens your next message will re-send uncached. No tokens spent.
Vedant Andhale in Status line, updated
4
-
read-cap
0.2.0
Stops Claude reading a file over 1,000 lines whole (with Read, cat or Get-Content) and gives it an outline tool (definitions with line numbers) so it reads only the range it needs. A retry still reads it whole.
Vedant Andhale in Status line, updated
4
-
budget-guard
0.1.0
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 goes through. No tokens spent.
Vedant Andhale in Usage & cost, updated
4
More usage & cost mods
-
token-weather
0.1.0
A live forecast of the context window, drawn above the prompt.
You in Usage & cost, updated
246.5k
-
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
538
-
token-weather
0.1.0
A live forecast of the context window, drawn above the prompt: a weather icon, the fill percentage, and a chart of the last turns.
Claude Code DevRel in Usage & cost, updated
179
-
context-bar
0.1.1
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
170
-
tw-stock-mod
0.13.5
mod + skill
Watchlist band above the Claude Code prompt: Taiwan hours show the Taiwan list (紅漲綠跌), US hours show the US list (綠漲紅跌), in a broker-style table with a Solari split-flap footer, plus a 損益 mode (P&L view) for your holdings. 20 symbols a market, 10 on screen at a time. Live prices from Yahoo by def...
Darrell Wang in Usage & cost, updated
64