By thriftell
Pre-flight, probabilistic token-spend estimate (range, scenario, confidence) for a coding task.
This plugin requires configuration values that are prompted when the plugin is enabled. Sensitive values are stored in your system keychain.
api_keyAPI key used to authenticate the Budgetary estimate tool and the session-end actuals submission. Starts with bg_live_ or bg_test_.
${user_config.api_key}Requires secrets
Needs API keys or credentials to function
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Budgetary tells you how many tokens an LLM query will cost — before you run it.
Budgetary is a hosted API at https://api.budgetary.tools that returns probabilistic pre-inference token-spend estimates for LLM queries. This repository holds the open-source clients that talk to it: language SDKs and editor plugins.
import { BudgetaryClient } from "@budgetary/sdk";
const budgetary = new BudgetaryClient({ apiKey: process.env.BUDGETARY_API_KEY! });
const estimate = await budgetary.estimate("Summarize the attached PDF in three bullets.");
The SDK in this release is a stub — the call above illustrates the shape of the API surface, not a working implementation.
See docs/installation.md for per-client setup:
@budgetary/sdk on npmbudgetary on PyPIBearer-auth HTTP API at https://api.budgetary.tools. The wire contract is published at docs/api-contract.md.
Early access. The hosted API is live, but client interfaces may change between releases until they reach 1.0. Pin exact versions in production.
Apache-2.0. Copyright Budgetary.
npx claudepluginhub thriftell/budgetary-clients --plugin budgetaryPermanent coding companion for Claude Code — survives any update. MCP-based terminal pet with ASCII art, stats, reactions, and personality.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.