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 open-finance-ai/financy --skill freshness-checkgit clone --depth 1 https://github.com/open-finance-ai/financyWrote 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/open-finance-ai/financy/freshness-check)<a href="https://agentmods.dev/skills/open-finance-ai/financy/freshness-check"><img src="https://agentmods.dev/badge/skills/open-finance-ai/financy/freshness-check/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/open-finance-ai/financy/freshness-check"><img src="https://agentmods.dev/badge/skills/open-finance-ai/financy/freshness-check.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 | $0.00129 | $0.01361 |
| Opus 5 | $0.00064 | $0.00681 |
| Sonnet 5 | $0.00026 | $0.00272 |
| Haiku 4.5 | $0.00013 | $0.00136 |
Grade A, and why
freshness-check 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 12d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
freshness check
Answer one question — is this data current enough to use? — and act on the answer. Every analysis skill that reads financy data should start here.
Minimum CLI version: 0.1.0
Guardrails
- Confirm before spending credits.
financy refreshcosts 20 credits every time it is called. Never run it without stating the cost and getting an explicit yes from the user in this conversation. "The data is stale, want me to refresh?" is not enough — say the number. - Never echo the client secret or the contents of the config file. If you
need to show what is configured, use
financy config, which masks the secret. - Exit code 4 means the plan, not the credentials. Point the user at the upgrade path at https://open-finance.ai and stop; do not retry and do not ask for new credentials.
Method
1. Read the status
financy status --json
The envelope:
{
"data": [
{
"provider": "hapoalim",
"status": "ACTIVE",
"fresh": "2026-08-01",
"expires": "2026-11-14",
"accounts": 3
}
],
"staleThresholdDays": 2
}
Per row:
provider— the bank or card issuer.nullwhile a connection is still being established.status—ACTIVEmeans the connection itself is healthy. Anything else is a broken connection, not a staleness problem.fresh— the date the data runs through, asYYYY-MM-DD.nullmeans the connection has never fetched anything.expires— when the user's bank consent lapses. Not a freshness signal, but worth surfacing when it is close.accounts— how many accounts, cards, savings, loans and securities this connection covers.
staleThresholdDays is the CLI's own threshold (2 days). Read it from the
response rather than hard-coding it.
Handle the exit code before the body: 3 → the CLI is not configured or the
credentials are rejected, so run the financy-setup skill instead; 4 → see
the guardrail above; 7 → the API is unreachable, retry once then report.
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.
- 12d ago First seen · 140 lines · 129 tokens per session scan A b65e814ff6fe
freshness-check is a skill published in the GitHub repository open-finance-ai/financy (6 stars, last pushed 2d ago), licensed Apache-2.0. It adds 129 tokens to every session and 1,361 once invoked, about $0.0006 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.
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.
reading-receipt
An image-reading workflow for extracting structured information from receipts, invoices, and hometown-tax donation certificates. It can first extract text from PDFs and otherwise read their images.