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 Proxy2021/Enso --skill financesgit clone --depth 1 https://github.com/Proxy2021/EnsoWrote 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/proxy2021/enso/finances)<a href="https://agentmods.dev/skills/proxy2021/enso/finances"><img src="https://agentmods.dev/badge/skills/proxy2021/enso/finances/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/proxy2021/enso/finances"><img src="https://agentmods.dev/badge/skills/proxy2021/enso/finances.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 | $0.00069 | $0.01166 |
| Opus 5.5 | $0.00028 | $0.00466 |
| Sonnet 5.5 | $0.00014 | $0.00233 |
| Haiku 4.5 | $0.00007 | $0.00117 |
Grade A, and why
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 1mo 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Financial accounts dashboard — unified view across brokerage and private-bank accounts with wealth monitoring, refresh logs, and notification settings. Each account is a Cortex entity; each periodic statement is its own synthesis page. Privacy: all data lives at ~/.enso/wiki/ and ~/.enso/data/finances/ (local only — never committed to git).
Tool Reference
enso_finances_list_accounts (primary)
List all known financial accounts with current balance, account type, and holdings count. Reads ~/.enso/data/finances/accounts.json (the local index built by the refresh executors). Use when the user says 'show my accounts', 'financial dashboard', 'net worth', 'wealth overview'.
enso_finances_account_detail
Show full detail for one financial account: holdings, recent activity, statements list. Use when user clicks an account row or says 'show '.
Parameters:
accountId(string): Stable account identifier
enso_finances_statement_detail
Show one periodic statement (snapshot) for an account. Renders opening/closing value, net change, holdings, transactions, fees.
Parameters:
statementId(string)
enso_finances_refresh_kk_live
Re-read the local FactorStrategies accounts directory (data/development/accounts/*.json) and rewrite the financial-account entity pages + per-rebalance statement pages in the Cortex. Use when user says 'refresh accounts', 'update KK_Live', or after a new rebalance.
Parameters:
accountsDir(string): Override the default FactorStrategies accounts dir.
enso_finances_configure_bank
Add, update, or remove a bank entry in the local config at ~/.enso/data/finances/banks.json. Each entry binds a sender email + subject pattern to a bank id used by refresh_rm_emails. The shipped repo has NO seed entries — config is per-user, local-only, never committed.
Parameters:
id(string): Short bank slug (e.g. 'gtjas', 'citi-pb').displayName(string): Human-readable bank name.senderEmail(string): Substring or full sender email (e.g. RM address).subjectMatch(string): Substring (case-insensitive) the email subject must contain.accountType(string): 'brokerage' or 'private-bank'. Default 'brokerage'.baseCurrency(string): Default currency. Default 'USD'.remove(boolean): If true, remove the entry with this id.
What ships with it
11 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.
- app.json 12 KB
- executors/account_detail.js 5.9 KB runs code
- executors/configure_bank.js 3.7 KB runs code
- executors/list_accounts.js 8.5 KB runs code
- executors/refresh_kk_live.js 11 KB runs code
- executors/refresh_log.js 2.4 KB runs code
- executors/refresh_rm_emails.js 24 KB runs code
- executors/statement_detail.js 5.9 KB runs code
- executors/wealth_config.js 3.2 KB runs code
- executors/wealth_status.js 6.8 KB runs code
- template.jsx 59 KB
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.
- 1mo ago First seen · 87 lines · 69 tokens per session scan A cdd9fd71ee2d
finances is a skill published in the GitHub repository Proxy2021/Enso (6 stars, last pushed 5mo ago), licensed MIT. It adds 69 tokens to every session and 1,166 once invoked, about $0.0003 per session on Opus 5.5. 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
paysh-catalog
Catalog of pay.sh services payable via agentpay (x402). OPT-IN ONLY — activate when the user explicitly invokes pay.sh / paysh / x402 / 'pay for' / 'pay with burner', or asks what they can pay for. Stay dormant otherwise; defer to free tools. Activation triggers are the frontmatter triggers: list (authoritative)…
burner-wallet
Operate the burner wallet — a small, app-managed Solana wallet that signs autonomously within caps. Use when: user asks about the burner, autonomous payments, x402, raising/lowering caps, funding the burner, or wiping/swapping the key (paste-only — the app never generates keys). Don't use when: user wants a regular…
crypto-prices
Get real-time cryptocurrency prices and market data from CoinGecko (free, no API key). Use when: user asks about crypto prices, token values, market data, 'what's BTC at?'. Don't use when: user wants to swap/trade tokens (use wallet tools), or wants crypto news (use news skill).
gplay-orders
Look up and refund Google Play orders by order ID with gplay orders (admin diagnostics, not purchase-token verification). Use when holding an order ID from a buyer complaint or payout report, or when refunding an order.
business-model
Use when deciding or revisiting how the product makes money — pricing, tiers, trial shape, ad load, unit economics — by ceo when setting the model, by cpo when a scope decision turns on revenue, and by product-researcher when investigating willingness to pay. A pricing analysis is a document, not a standing role.
authentication
User-facing sign-in for a fintech iOS app, built on Apple's AuthenticationServices (ASAuthorization, ASWebAuthenticationSession) and LocalAuthentication (LAContext). Targets the iOS 26 era. This skill covers how the user proves identity; storing the resulting tokens/keys is a separate concern.