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 yuechen/plaid-mcp --skill plaidgit clone --depth 1 https://github.com/yuechen/plaid-mcpWrote 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/yuechen/plaid-mcp/plaid)<a href="https://agentmods.dev/skills/yuechen/plaid-mcp/plaid"><img src="https://agentmods.dev/badge/skills/yuechen/plaid-mcp/plaid.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 | $0.00038 | $0.01935 |
| Opus 5 | $0.00019 | $0.00967 |
| Sonnet 5 | $0.00008 | $0.00387 |
| Haiku 4.5 | $0.00004 | $0.00194 |
Grade A, and why
plaid 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 7d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
plaid skill
The user has plaid-mcp installed. It exposes seven MCP tools backed by a local SQLite cache of their Plaid-linked financial data:
Query / status — use these all the time:
plaid_query(sql)— read-only SQLite againstplaid_*tables andvw_plaid_*views. Use this for almost everything.plaid_sync()— refresh from Plaid. Slow (seconds). Only call if the user's question needs fresh data ANDplaid_statusshows the cache is more than ~12h stale.plaid_status()— last-sync times and any per-institution errors.
Manage connections — only when the user explicitly asks:
plaid_link()— start a flow to add a NEW bank. Returns ahosted_link_urlandlink_token; opens the browser. After the user says they're done, callplaid_link_complete(link_token).plaid_relink(item_id)— re-authenticate an existing bank (after ITEM_LOGIN_REQUIRED etc.). Preserves transaction history. Returns alink_tokenanditem_id; pass BOTH back toplaid_link_complete(link_token, item_id)once the user finishes.plaid_link_complete(link_token, item_id?)— finalize a flow started byplaid_linkorplaid_relink. Polls for up to 60s; if the result is{status: "pending"}, the user hasn't actually finished yet — wait a moment and call again. Does NOT sync — callplaid_sync(item_id)next if you want fresh data immediately.plaid_unlink(item_id, confirmed=True)— permanently remove a bank. Destructive. The tool ENFORCES confirmation: a call withoutconfirmed=Truereturns an error. Describe the action to the user first, wait for an explicit yes, then re-call withconfirmed=True.
When to use this skill
Trigger on personal-finance questions even if the user doesn't mention Plaid or banks explicitly:
- "what did I spend on food last month"
- "how much do I have in the bank"
- "am I behind on any credit cards"
- "did the rent payment go through"
- "what's my net worth"
- "show me my AAPL position"
- "when is my mortgage payment due"
- "biggest expenses this quarter"
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.
- 7d ago First seen · 173 lines · 38 tokens per session scan A 12d7e1ed1e22
plaid is a skill published in the GitHub repository yuechen/plaid-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 38 tokens to every session and 1,935 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.
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.