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.
npx skills add markmhendrickson/neotoma --skill remember-financesgit clone --depth 1 https://github.com/markmhendrickson/neotomaWrote 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/markmhendrickson/neotoma/remember-finances)<a href="https://agentmods.dev/skills/markmhendrickson/neotoma/remember-finances"><img src="https://agentmods.dev/badge/skills/markmhendrickson/neotoma/remember-finances.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00028 | $0.00777 |
| Opus 5 | $0.00014 | $0.00388 |
| Sonnet 5 | $0.00006 | $0.00155 |
| Haiku 4.5 | $0.00003 | $0.00078 |
Grade A, and why
remember-finances 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 4d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Remember Finances
Import financial documents — bank statements, receipts, invoices — into Neotoma memory with structured transaction extraction and full provenance.
When to use
When the user has financial documents (CSV/PDF bank statements, receipt images, invoice PDFs) and wants to persist the transactions as structured, queryable records.
Prerequisites
Run the ensure-neotoma skill first if Neotoma is not yet installed or configured in your current harness.
Supported sources
| Source | Format | Method |
|---|---|---|
| Bank statements | CSV, PDF | File read, parse_file for PDFs |
| Receipts | Images (JPEG, PNG), PDF | Vision, parse_file |
| Invoices | PDF, email attachments | parse_file, email MCP |
| Plaid | Live bank data | Plaid MCP (optional) |
Workflow
Phase 0: Verify Neotoma
Confirm Neotoma MCP is connected (call get_session_identity).
Phase 1: Identify financial documents
- Ask the user what to import:
- Bank statement file path (CSV or PDF)
- Receipt image(s)
- Invoice file(s)
- Live bank account via Plaid MCP
- Detect the format and choose the appropriate parsing method.
Phase 2: Parse and preview
- CSV statements: read columns, detect header row, identify date/amount/description fields.
- PDF statements: use
parse_fileto extract text, then parse rows. - Receipt images: use vision to read merchant, date, items, total, tax.
- Invoices: use
parse_fileto extract vendor, line items, amounts, due date. - Present a preview: transaction count, date range, total amounts, top merchants/vendors.
- Ask for confirmation.
Phase 3: Extract entities
For each document, extract:
- Transactions: one
transactionentity per line item or statement row withamount,currency,date,description,merchant,category(when inferable). - Contacts: merchants, vendors, or counterparties as
contactentities. - Invoices/Receipts: the document itself as a
receiptorinvoiceentity with total, tax, line items.
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.
- 4d ago First seen · 90 lines · 28 tokens per session scan A 4c46ed7166ec
remember-finances is a skill published in the GitHub repository markmhendrickson/neotoma (31 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 777 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 2026-09-03.
Other skills, from other repositories
tushare-data
A Chinese-language workflow for researching financial and market data through Tushare, a data service covering Chinese stocks and related economic information. It turns natural-language questions into steps for retrieving, cleaning, comparing, filtering, exporting, and briefly analysing data.
finance-tracker
Track expenses, analyze spending patterns, categorize transactions. Works with bank CSV exports or manual input.
tradememory-bridge
Bridge between Binance trading events and TradeMemory Protocol. Automatically journals trades, recalls similar past setups, detects behavioral biases, and provides outcome-weighted recall for AI trading agents. Use this skill after executing Binance spot trades to build persistent memory.
trading-memory
Domain knowledge for AI trading memory — Outcome-Weighted Memory (OWM) architecture, 5 memory types, recall scoring, and behavioral analysis. Use when recording trades, recalling similar contexts, analyzing performance, or checking behavioral drift. Triggers on "record trade", "remember trade", "recall", "similar…
tcx-memory
Review past investment decisions, run point-in-time historical replays, compare resolved forecasts and forward outcomes, and validate lesson candidates. Use when the user asks what happened before, why a thesis changed, whether a strategy lesson held out of sample, or what prior evidence is relevant to a current…
context-manager
Gestion avancée du contexte pour agents IA — fenêtre de contexte, compression, RAG dynamique, sliding window, prompt caching. Se déclenche avec "context window", "contexte agent", "token limit", "context management", "context overflow", "trop de contexte", "agent context", "context stuffing", "context compression".…