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 financy-setupgit 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/financy-setup)<a href="https://agentmods.dev/skills/open-finance-ai/financy/financy-setup"><img src="https://agentmods.dev/badge/skills/open-finance-ai/financy/financy-setup.svg" alt="Measured on agentmods" 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 | $0.00127 | $0.02076 |
| Opus 5 | $0.00063 | $0.01038 |
| Sonnet 5 | $0.00025 | $0.00415 |
| Haiku 4.5 | $0.00013 | $0.00208 |
Grade C, and why
financy-setup scanned grade C with 1 finding 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
them collect credentials that will fail at the last step. How it starts
The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
financy setup
Get the financy CLI configured and verified for this user. When you are done,
financy status exits 0 and every other financy command works.
Minimum CLI version: 0.1.0
Guardrails
These are not optional and they apply to every step below.
- Never handle the client secret at all. Do not ask the user to paste it into
the conversation, and never place it in a command you run — a command you run
is recorded in the transcript, and it is visible in shell history and to
anything that can list processes. The user types the secret into
financy setup, which masks it at the prompt; you never see it. If the user pastes it anyway, do not repeat it, do not use it in a command, and tell them to rotate it in Financy → Settings → API. Never print it, read it back for confirmation, or include it in a summary, and nevercatthe config file. Ifsetupwarns that the input is not masked (a terminal where Node cannot hide input, e.g. Git Bash / mintty, where stdin is a pipe), tell the user to run it in PowerShell or Windows Terminal instead of typing the secret in the clear. - Confirm before spending credits.
financy refreshcosts 20 credits per run. Never run it without the user explicitly agreeing to that cost in this conversation. - Exit code 4 means the plan, not the credentials. The credentials are valid but the account is not on a paid plan. Do not retry, do not suggest re-entering the credentials — point the user at the upgrade path and stop.
What the user needs before you start
The financy data API is a paid feature. To finish this skill the user must have:
- A registered Financy account at https://open-finance.ai.
- A paid plan — Starter, Pro, or Ultra. The data API is not available on the free plan.
- Three values from the Financy app → Settings → API:
clientId,clientSecret, anduserId.
If the user does not have a paid plan yet, say so up front rather than letting them collect credentials that will fail at the last step.
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.
- 8d ago First seen · 199 lines · 127 tokens per session scan C 00f1ed336d79
financy-setup is a skill published in the GitHub repository open-finance-ai/financy (6 stars, last pushed 5d ago), licensed Apache-2.0. It adds 127 tokens to every session and 2,076 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 1 finding (harvests environment variables). 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.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
vectorbt
High-performance vectorized backtesting with parameter optimization, portfolio simulation, and rich performance metrics.