plaid

plaid is a skill for Claude Code from yuechen/plaid-mcp. It costs 38 tokens per session (1,935 once invoked), scanned A, original, MIT.

A skill for answering questions about linked bank accounts, cards, transactions, investments, mortgages, and net worth from a local Plaid data cache. Plaid is a service that connects financial accounts to apps.

In plain words
What is it for?
Use it to inspect balances, transactions, holdings, debts, and net worth, or to refresh the cache or manage bank connections when explicitly needed.
Why use it?
It lets the assistant query stored financial data without directly changing the accounts, while also checking when the cache was last updated.

Skill for Claude Code

Written for Claude Code: when-to-use in frontmatter.

Good fit Use it to inspect balances, transactions, holdings, debts, and net worth, or to refresh the cache or manage bank connections when explicitly needed.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yuechen/plaid-mcp/plaid
Install

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.

Any agent
npx skills add yuechen/plaid-mcp --skill plaid
Clone the repo
git clone --depth 1 https://github.com/yuechen/plaid-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for plaid

README.md
[![agentmods](https://agentmods.dev/badge/skills/yuechen/plaid-mcp/plaid.svg)](https://agentmods.dev/skills/yuechen/plaid-mcp/plaid)
Your own site
<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>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,935 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 7d ago against content hash 12d7e1ed1e22, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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.

skills/plaid/SKILL.md · 173 lines

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 against plaid_* tables and vw_plaid_* views. Use this for almost everything.
  • plaid_sync() — refresh from Plaid. Slow (seconds). Only call if the user's question needs fresh data AND plaid_status shows 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 a hosted_link_url and link_token; opens the browser. After the user says they're done, call plaid_link_complete(link_token).
  • plaid_relink(item_id) — re-authenticate an existing bank (after ITEM_LOGIN_REQUIRED etc.). Preserves transaction history. Returns a link_token and item_id; pass BOTH back to plaid_link_complete(link_token, item_id) once the user finishes.
  • plaid_link_complete(link_token, item_id?) — finalize a flow started by plaid_link or plaid_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 — call plaid_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 without confirmed=True returns an error. Describe the action to the user first, wait for an explicit yes, then re-call with confirmed=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"

Read the full file on GitHub · 173 lines

Changes

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.

  1. 7d ago First seen · 173 lines · 38 tokens per session scan A 12d7e1ed1e22

Subscribe to this mod's changes

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.

Related

Other skills, from other repositories