user-memory

user-memory is a skill for Claude Code, Codex from peerjakobsen/smartspender. It costs 31 tokens per session (2,469 once invoked), scanned A, original, MIT.

A memory feature that records personal financial details, preferences, and corrections shared during Cowork sessions.

In plain words
What is it for?
Use it to remember details such as savings, debt, income, pension, subscription corrections, merchant names, and preferred output format.
Why use it?
It avoids making you repeat information and helps keep later financial discussions consistent with what you previously said.

Skill for Claude CodeCodex

Part of the smartspender plugin — 13 skills, 19 commands shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/peerjakobsen/smartspender/user-memory
Any agent
npx skills add peerjakobsen/smartspender --skill user-memory
Clone the repo
git clone --depth 1 https://github.com/peerjakobsen/smartspender

Made for: Claude Code, Codex.

Or install smartspender, the plugin that ships this one along with the rest of its 13 skills, 19 commands.

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 user-memory

README.md
[![agentmods](https://agentmods.dev/badge/skills/peerjakobsen/smartspender/user-memory.svg)](https://agentmods.dev/skills/peerjakobsen/smartspender/user-memory)
Your own site
<a href="https://agentmods.dev/skills/peerjakobsen/smartspender/user-memory"><img src="https://agentmods.dev/badge/skills/peerjakobsen/smartspender/user-memory.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,469 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00031 $0.02469
Opus 5 $0.00015 $0.01234
Sonnet 5 $0.00006 $0.00494
Haiku 4.5 $0.00003 $0.00247

Measured 3d ago against content hash a0de4eb5ee28, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

user-memory 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 3d 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.

skills/user-memory/SKILL.md · 270 lines

How it starts

The opening of the file, as written. The whole thing — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.

User Memory

Purpose

Automatically detect when users provide information about their financial situation, preferences, or corrections, and persist this to the appropriate learnings file so future sessions can use it.

When to Activate

This skill activates automatically when:

  1. User answers a question about their financial situation
  2. User volunteers personal context information
  3. User corrects a categorization, subscription status, or merchant name
  4. User states an output preference

Trigger Patterns

Financial Situation (Danish)

Pattern Category Extraction
Jeg har [X] kr i nødopsparing/opsparing emergency_fund amount
Min nødopsparing er [X] kr emergency_fund amount
Jeg har [X] måneder i opsparing emergency_fund months_coverage
Jeg har gæld i/til [X] debt creditor
Min gæld er [X] kr debt amount
Jeg skylder [X] kr til [Y] debt amount, creditor
Min pension er [X]% pension percentage
Jeg indbetaler [X]% til pension pension percentage
Jeg har pension hos [X] pension provider
Min løn er [X] kr income amount
Jeg tjener [X] kr om måneden income amount
Min bruttoløn er [X] kr income gross_amount

Financial Situation (English)

Pattern Category Extraction
I have [X] in emergency fund/savings emergency_fund amount
My emergency fund is [X] emergency_fund amount
I have [X] months of expenses saved emergency_fund months_coverage
I have debt with/to [X] debt creditor
I owe [X] to [Y] debt amount, creditor
My pension is [X]% pension percentage
I contribute [X]% to pension pension percentage
My salary is [X] income amount
I earn [X] per month income amount

Personal Context (Danish)

Pattern Category Extraction
Jeg arbejder hos [X] employer company_name
Min arbejdsgiver er [X] employer company_name
Jeg er ansat hos [X] employer company_name
Jeg vil gerne [X] goal goal_description
Mit mål er at [X] goal goal_description
Jeg sparer op til [X] goal savings_goal
Jeg planlægger at [X] goal plan_description
Jeg er [X] (single/married/etc.) life_situation status
Jeg har [X] børn life_situation children_count
Jeg bor i [X] life_situation location
Jeg er [X] år life_situation age

Read the full file on GitHub · 270 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. 3d ago First seen · 270 lines · 31 tokens per session scan A a0de4eb5ee28

Subscribe to this mod's changes

user-memory is a skill published in the GitHub repository peerjakobsen/smartspender (5 stars, last pushed 7mo ago), licensed MIT. It adds 31 tokens to every session and 2,469 once invoked, about $0.0002 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

researchers-financial

Researches SEC filings, earnings calls, analyst reports, and market data. Use when the album subject involves financial crimes, corporate stories, or market events.

bitwize-music-studio/claude-ai-music-skills · 36 tokens

finance-cleanup

Use when the user wants to clean up transactions, fix categories, find missing recurring charges, or do general transaction hygiene in Copilot Money.

ignaciohermosillacornejo/copilot-money-mcp · 32 tokens

finance-pulse

Use when the user asks how they're doing financially, wants a spending check-in, asks about free money or discretionary budget, or says 'pulse'. Read-only — never writes to Copilot Money.

ignaciohermosillacornejo/copilot-money-mcp · 43 tokens

finance-trip

Use when the user wants to track trip expenses, tag travel transactions, find late-posting charges from a trip, or get a trip spending summary. Example: 'tag my Tahiti trip expenses' or 'how much did I spend in Whistler?'.

ignaciohermosillacornejo/copilot-money-mcp · 54 tokens

finance

Use for open-ended financial questions: 'can I afford X?', 'should I buy X?', 'how much can I spend on Y?', or any affordability, budgeting, or financial planning question. Also use when the user asks a financial question that doesn't fit /finance-cleanup, /finance-pulse, or /finance-trip.

ignaciohermosillacornejo/copilot-money-mcp · 68 tokens

portfolio-rs

Use when operating in a portfoliors finance workspace, reviewing portfolios, generating reports, drafting decisions, or working with INVESTMENTPOLICY.md, positions.json, portfolio/policy.toml, diary, decisions, theses, reports, or watchlist files.

MarkusZoppelt/portfolio_rs · 53 tokens