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.
curl -O https://raw.githubusercontent.com/natejswenson/local-budget/main/.claude/skills/budget-categorize/SKILL.mdgit clone --depth 1 https://github.com/natejswenson/local-budgetWrote 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.
[](https://agentmods.dev/skills/natejswenson/local-budget/budget-categorize)<a href="https://agentmods.dev/skills/natejswenson/local-budget/budget-categorize"><img src="https://agentmods.dev/badge/skills/natejswenson/local-budget/budget-categorize/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.
<a href="https://agentmods.dev/skills/natejswenson/local-budget/budget-categorize"><img src="https://agentmods.dev/badge/skills/natejswenson/local-budget/budget-categorize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00022 | $0.00547 |
| Opus 5 | $0.00011 | $0.00273 |
| Sonnet 5 | $0.00004 | $0.00109 |
| Haiku 4.5 | $0.00002 | $0.00055 |
Grade A, and why
budget-categorize 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 10d 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.
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 Categorize
Work the review queue. Follow the budget-analyst discipline: never invent a
number, and print each tool's rendered block verbatim before synthesizing.
Read first
review_queue— the uncategorized merchants and checks that need attention.query_transactions— pull the specific transactions behind a merchant when you need detail before deciding a category.list_categories— the exact assignable vocabulary. Call it before proposing categories so every proposal uses an exact existing name (writes reject near-misses like "Grocerys").
Print each tool's rendered block verbatim.
Write — confirm each one
For each categorization, confirm before writing: show the user the exact change (merchant or transaction → proposed category) and get an explicit "yes" before calling the write tool. One confirmation per write.
set_merchant_category— assign a category to a merchant (applies going forward).set_txn_category— assign a category to a single transaction.add_custom_category— create a new category when none of the existing ones fit.remove_category— remove a spend category by merging it into another (moves its transactions, rules and budget). Destructive-ish: spell out exactly what moves where before asking for the yes.
Never write without the user's yes. If the user declines a proposed category, move on to the next item in the queue.
Undo. A wrong categorization is fixed by re-calling the same set tool with the
right category. A whole import gone wrong (wrong file, duplicates) is undone from
the terminal with budget undo — that's a CLI escape hatch, not a tool; point the
user there rather than trying to reverse an import tool-by-tool.
Never propose "Random." It's a last-resort catch-all, not a default for
ambiguous merchants — proposing it defeats the point of categorizing at all.
If nothing fits, say so and leave the item in the review queue for the user
to decide, rather than defaulting into Random. (The write tools also refuse
category="Random" unless explicitly confirmed, as a backstop — but the
right move here is to just not propose it.)
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.
- 10d ago First seen · 50 lines · 22 tokens per session scan A 542c35fe5bc7
budget-categorize is a skill published in the GitHub repository natejswenson/local-budget (0 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 547 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.
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.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
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…
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.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
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.