Claude Code
● actuals: autoSet up Budgetary so you give me a pre-flight token-spend estimate before large tasks.
Do exactly this, and nothing more:
1. Ask me for my Budgetary API key first (it starts with bg_test_ or bg_live_). If I don't give you one, stop and tell me — do not invent or read one from anywhere.
2. Add a single MCP server named "budgetary" pointing at the hosted API:
claude mcp add --transport http budgetary https://api.budgetary.tools/mcp --header "Authorization: Bearer <the key I gave you>"
This only registers one MCP server (it exposes an "estimate" tool). It does not edit my code, read my repository, or install anything else. Do not write the key to any other file or commit it.Before you start, call the Budgetary "estimate" tool on this task and show me what it returns — the token range, the scenario, and the confidence — then wait for my go-ahead:
"Refactor the auth middleware to use async sessions and update the tests."
If Budgetary returns a "no read" (it can't confidently estimate this one), just tell me that plainly. Don't guess a number.Actuals: automatic. Once installed, Claude Code captures your real session token usage and lines it up against the estimate.