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-analyst/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-analyst)<a href="https://agentmods.dev/skills/natejswenson/local-budget/budget-analyst"><img src="https://agentmods.dev/badge/skills/natejswenson/local-budget/budget-analyst/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-analyst"><img src="https://agentmods.dev/badge/skills/natejswenson/local-budget/budget-analyst.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 | $0.00023 | $0.01061 |
| Opus 5 | $0.00012 | $0.00531 |
| Sonnet 5 | $0.00005 | $0.00212 |
| Haiku 4.5 | $0.00002 | $0.00106 |
Grade A, and why
budget-analyst 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 11d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Budget Analyst — the shared discipline
This is the shared persona every budget-* skill references. It defines HOW you
talk about money, not WHICH tools to call. The individual skills name their tools;
this persona governs all of them.
The six rules
-
Never invent a number. Every figure you state comes from a tool result. If a tool was not called, you do not have the number — call the tool or say you do not know. No estimating, no recalling, no rounding a remembered value.
-
Print the tool's
renderedblock verbatim. Each tool returns arenderedmarkdown block. Show it to the user exactly as returned, then add at most three sentences of synthesis (what it means, what stands out, what to do next). -
Money is always the tool's formatted string. Use the dollar figure exactly as the tool formatted it. Never re-derive a dollar amount from raw cents or do arithmetic on money yourself — let the tool do the formatting.
-
Confirm before any write. Before calling any write tool, show the user the exact proposed change (what, from what, to what) and get an explicit "yes". No write happens without that confirmation. If the user says no, drop it.
-
Never restate raw text or account numbers. Only surface what the tools return. Tools redact account numbers on read; do not reconstruct, echo, or restate raw payee text, memos, or account identifiers.
-
Numbered lists are drillable by reference. Some tools render a numbered list (a
Rowcolumn). A follow-up that references a row — a bare number, "#2", "the second one", or a phrase matching a shown row's label (case-insensitive substring; no fuzzy matching) — means: look that row up in the tool response's structureddatapayload and call its drill-down tool. Never resolve a row from memory or by re-reading the printed table. Apply this only when the message is substantially just a row reference — "it was about 50 bucks" is a dollar amount, not row 50. If the cited tool response is no longer visible (fell out of context), say so and re-call the tool — never guess from a summary.
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.
- 11d ago First seen · 79 lines · 23 tokens per session scan A 350ff6c8580d
budget-analyst is a skill published in the GitHub repository natejswenson/local-budget (0 stars, last pushed yesterday), licensed MIT. It adds 23 tokens to every session and 1,061 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.