local-budget: Skill for Claude Code

.claude/skills/budget-coach/SKILL.md

budget-coach is a skill for Claude Code from natejswenson/local-budget. It costs 20 tokens per session (561 once invoked), scanned A, original, MIT.

A read-only assistant for answering personal budgeting questions from actual budget records. It can summarize spending and income, group expenses, find transactions, compare periods, and identify major merchants.

In plain words
What is it for?
Use it to understand monthly finances, investigate particular purchases, compare spending periods, or see where the most money went.
Why use it?
It keeps financial answers tied to retrieved data instead of guessed figures, while preventing changes to the budget database.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is natejswenson/local-budget's own configuration. It tells Claude Code how to work on local-budget itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything local-budget configures →

Reuse

Borrowing it

Nothing to install: this file belongs to natejswenson/local-budget. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/natejswenson/local-budget/main/.claude/skills/budget-coach/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/natejswenson/local-budget

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for budget-coach

README.md
[![agentmods](https://agentmods.dev/badge/skills/natejswenson/local-budget/budget-coach/github.svg)](https://agentmods.dev/skills/natejswenson/local-budget/budget-coach)
Your own site
<a href="https://agentmods.dev/skills/natejswenson/local-budget/budget-coach"><img src="https://agentmods.dev/badge/skills/natejswenson/local-budget/budget-coach/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for budget-coach

Your own site · 80×15
<a href="https://agentmods.dev/skills/natejswenson/local-budget/budget-coach"><img src="https://agentmods.dev/badge/skills/natejswenson/local-budget/budget-coach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 561 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00020 $0.00561
Opus 5 $0.00010 $0.00280
Sonnet 5 $0.00004 $0.00112
Haiku 4.5 $0.00002 $0.00056

Measured 12d ago against content hash 9722e1ac29ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

budget-coach scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/budget-coach/SKILL.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Budget Coach

Answer any money question the user asks, grounded in real data. Follow the budget-analyst discipline: never invent a number — every figure comes from a tool result — and print each tool's rendered block verbatim before adding at most three sentences of synthesis. This skill is read-only for budget data; it never writes to the budget database. (Rendering a chart to a local PDF, per below, is a file write to reports/, not a database write, so it doesn't conflict with this.)

Tools and order

Start broad, then drill down based on what the user asked:

  1. get_month_summary — the headline for a period (spent / income / net).
  2. get_category_breakdown — where the money went, by category.
  3. query_transactions — pull specific transactions to answer a pointed question.
  4. compare_periods — this period vs. another (month-over-month, etc.).
  5. top_merchants — the biggest places money went.

Pick the smallest set that answers the question. Print each tool's rendered block verbatim, then synthesize.

Preferences (file-backed notes, not budget data)

When the user states a durable preference or standing fact worth remembering ("treat Costco as groceries when I ask", "my mortgage payment counts as fixed"), offer to save it with save_user_note — one sentence, and confirm the exact wording before saving (it's a write, rule 4 applies even though it never touches the budget DB). list_user_notes at the start of a session-long money conversation recalls them; delete_user_note removes one the user retracts.

Charts

If the user asks to see a chart, graph, or visual, the visual report is rendered by the deterministic render_report tool (see budget-visualizer) — never hand-built here. That tool isn't in this skill's list, so point the user to the owning skill: "Want to run /budget-monthly-brief for the visual report? It covers the stat row, spend/budget chart, trend, and flags in one PDF."

Handoff

If the answer reveals uncategorized or miscategorized spending, offer: "Want to run /budget-categorize to clean that up?"

Read the full file on GitHub · 50 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 50 lines · 20 tokens per session scan A 9722e1ac29ab

Subscribe to this mod's changes

budget-coach is a skill published in the GitHub repository natejswenson/local-budget (0 stars, last pushed 2d ago), licensed MIT. It adds 20 tokens to every session and 561 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

sector-rotation

An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.

HKUDS/Vibe-Trading · 39 tokens

strategy-pivot-designer

Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.

tradermonty/claude-trading-skills · 28 tokens

twitter-reader

Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…

himself65/finance-skills · 161 tokens

chenhao-limit-up

A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.

questflowai/investorskills · 44 tokens

furusato

A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.

kazukinagata/shinkoku · 102 tokens

reading-receipt

An image-reading workflow for extracting structured information from receipts, invoices, and hometown-tax donation certificates. It can first extract text from PDFs and otherwise read their images.

kazukinagata/shinkoku · 64 tokens