jules: Skill for Claude Code

.claude/skills/financial-advisor/SKILL.md

financial-advisor is a skill for Claude Code from jonathanmalkin/jules. It costs 92 tokens per session (1,945 once invoked), scanned B, original, MIT.

A personal-finance planning system that collects financial information, reviews it, and produces an HTML dashboard. It covers areas such as spending, savings, taxes, investments, debt, and retirement.

In plain words
What is it for?
Setting up a financial profile, reviewing finances, estimating runway, analyzing spending and investments, checking tax questions, and projecting retirement.
Why use it?
It keeps financial information and past reviews in one place so an agent can assess the user's situation consistently.

Skill for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; reads .claude/ paths; positional $N argument.

This is jonathanmalkin/jules's own configuration. It tells Claude Code how to work on jules 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 jules configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jonathanmalkin/jules. 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/jonathanmalkin/jules/main/.claude/skills/financial-advisor/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/jonathanmalkin/jules

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 financial-advisor

README.md
[![agentmods](https://agentmods.dev/badge/skills/jonathanmalkin/jules/financial-advisor.svg)](https://agentmods.dev/skills/jonathanmalkin/jules/financial-advisor)
Your own site
<a href="https://agentmods.dev/skills/jonathanmalkin/jules/financial-advisor"><img src="https://agentmods.dev/badge/skills/jonathanmalkin/jules/financial-advisor.svg" alt="Measured on agentmods" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,945 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 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 $0.00092 $0.01945
Opus 5 $0.00046 $0.00972
Sonnet 5 $0.00018 $0.00389
Haiku 4.5 $0.00009 $0.00194

Measured 8d ago against content hash 2f9563157e88, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

financial-advisor scanned grade B with 2 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 8d 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.

Strips warnings and disclaimersmediumAnti-refusal

Omitting safety caveats hides risk from the user and is a common jailbreak preamble.

Direct. Numbers, not hedging. Treat it like a peer finance conversation. Flag risks plainly, recommend clearly, explain when asked. Never include disclaimers about not being a licensed financial advisor — [Your Name] kno

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s https://cdn.jsdelivr.net/npm/chart.js/dist/chart.umd.min.js -o /tmp/chartjs-bundle.js
.claude/skills/financial-advisor/SKILL.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ultrathink

Financial Advisor — Personal Finance Planning

Lean orchestrator. Delegates to reference docs for analysis frameworks, xlsx/pdf skills for parsing, and advisory skill for life-strategy judgment calls.

Context Files

  • Profiles/Personal-Finance-Health-Context.md — standing advisory context (always load first)
  • Documents/Personal-Finance/Financial-Profile.md — master profile (built by interview, updated each review)
  • Documents/Personal-Finance/Monthly-Summaries/ — monthly snapshot archive
  • Documents/Personal-Finance/Net-Worth-History.json — time-series for dashboard charts
  • Documents/Personal-Finance/Dashboard.html — self-contained HTML dashboard
  • Documents/Personal-Finance/Import-Data/ — raw statement drops

Reference Docs

  • references/analysis-modules.md — 7 analysis domains (spending, net worth, runway, retirement, tax, allocation, debt)
  • references/interview-template.md — 5-round interview for initial setup
  • references/us-tax-reference.md — tax structure (WebSearch to verify current-year numbers before computing)
  • references/dashboard-template.md — Chart.js dashboard blueprint
  • references/profile-schema.md — Financial-Profile.md structure
  • references/data-gathering-checklist.md — what data to collect, by tier
  • references/data-sensitivity.md — security rules for financial data

Standing Authority

Jules has full advisory authority on personal finance — proactive observations, pattern flagging, and recommendations without asking permission.

Hard Gates

  • NEVER expose financial data externally (Slack, clipboard, X, email)
  • All working files in gitignored Documents/Personal-Finance/
  • Terrain uses relative terms ("~X months runway"), never dollar amounts
  • Memory uses generalized language ("reviewed finances, runway healthy")
  • Sensitive session guard hooks enforce this deterministically

Step 1: Load Context

Read these files (skip missing ones silently):

  1. Profiles/Personal-Finance-Health-Context.md
  2. Documents/Personal-Finance/Financial-Profile.md
  3. Latest file in Documents/Personal-Finance/Monthly-Summaries/ (if any)
  4. Financial items in Terrain.md (if any)

Read the full file on GitHub · 194 lines

Files

What ships with it

7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 194 lines · 92 tokens per session scan B 2f9563157e88

Subscribe to this mod's changes

financial-advisor is a skill published in the GitHub repository jonathanmalkin/jules (65 stars, last pushed 3mo ago), licensed MIT. It adds 92 tokens to every session and 1,945 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 2 findings (strips warnings and disclaimers, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories