ynab-mcp-server: Skill for Claude Code

.agents/skills/ynab-tool-development/SKILL.md

ynab-tool-development is a skill for Claude Code, Codex from calebl/ynab-mcp-server. It costs 34 tokens per session (944 once invoked), scanned A, original, MIT.

A development guide for adding or changing tools that connect to YNAB, a budgeting service, through its API or software library.

In plain words
What is it for?
Use it when implementing or updating a YNAB MCP tool, YNAB API integration, transaction-listing call, or SDK version.
Why use it?
It standardises tool schemas, plan-ID handling, API calls, error responses, and registration so new tools fit the existing codebase. It also covers transaction-listing and SDK-version changes.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is calebl/ynab-mcp-server's own configuration. It tells Claude Code and Codex how to work on ynab-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ynab-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to calebl/ynab-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/calebl/ynab-mcp-server/main/.agents/skills/ynab-tool-development/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/calebl/ynab-mcp-server

Made for: Claude Code, Codex.

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 ynab-tool-development

README.md
[![agentmods](https://agentmods.dev/badge/skills/calebl/ynab-mcp-server/ynab-tool-development/github.svg)](https://agentmods.dev/skills/calebl/ynab-mcp-server/ynab-tool-development)
Your own site
<a href="https://agentmods.dev/skills/calebl/ynab-mcp-server/ynab-tool-development"><img src="https://agentmods.dev/badge/skills/calebl/ynab-mcp-server/ynab-tool-development/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.

agentmods 80×15 button for ynab-tool-development

Your own site · 80×15
<a href="https://agentmods.dev/skills/calebl/ynab-mcp-server/ynab-tool-development"><img src="https://agentmods.dev/badge/skills/calebl/ynab-mcp-server/ynab-tool-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 944 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 $0.00034 $0.00944
Opus 5.5 $0.00014 $0.00378
Sonnet 5.5 $0.00007 $0.00189
Haiku 4.5 $0.00003 $0.00094

Measured 18d ago against content hash e2b7cd7ad211, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ynab-tool-development 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 18d 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.

.agents/skills/ynab-tool-development/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adding New Tools

Before adding a tool

Check whether the behavior fits as an option on an existing tool (a new filter, date bound, or output mode) before creating a new one. Add a new tool only when no existing tool covers the same data and intent, and say in the PR which existing tools were considered and why they didn't fit. Overlapping tools make the model more likely to pick the wrong one.

  1. Create src/tools/MyTool.ts:
import { z } from "zod";
import * as ynab from "ynab";
import { resolvePlanId } from "./planId.js";

export const name = "my_tool";
export const description = "What this tool does";
export const inputSchema = {
  planId: z.string().optional().describe("The plan ID (optional, defaults to YNAB_PLAN_ID; budgetId is a deprecated alias)"),
  budgetId: z.string().optional().describe("Deprecated alias of planId (still accepted)"),
  requiredParam: z.string().describe("Description of required param"),
};

interface MyToolInput {
  planId?: string;
  budgetId?: string;
  requiredParam: string;
}

export async function execute(input: MyToolInput, api: ynab.API) {
  try {
    const planId = resolvePlanId(input);
    const result = await api.someMethod(planId, input.requiredParam);

    return {
      content: [{ type: "text" as const, text: JSON.stringify(result, null, 2) }]
    };
  } catch (error) {
    return {
      content: [{ type: "text" as const, text: `Error: ${error instanceof Error ? error.message : 'Unknown error'}` }]
    };
  }
}
  1. Register in src/registry.ts — import the module and add it to the tools array. Both entry points build from this one list, so registering here serves the tool from the stdio server and the Cloudflare Worker alike.
import * as MyTool from "./tools/MyTool.js";

export const tools: ToolEntry[] = [
  // ...
  { title: "My Tool", module: MyTool, writes: false },
];

Set writes: true for any tool that changes data in YNAB. YNAB_READ_ONLY filters on that flag, so a mislabelled tool would be exposed in a deployment meant to be read-only.

Read the full file on GitHub · 79 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. 18d ago Changed · +3 lines e2b7cd7ad211
  2. 22d ago First seen · 76 lines · 34 tokens per session scan A 31020c720eeb

Subscribe to this mod's changes

ynab-tool-development is a skill published in the GitHub repository calebl/ynab-mcp-server (162 stars, last pushed 4d ago), licensed MIT. It adds 34 tokens to every session and 944 once invoked, about $0.0001 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 2026-10-16.

Related

ynab-tool-development compared with skills from other repositories

ynab-tool-development next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ynab-tool-developmentcalebl/ynab-mcp-serverSkill1624d agoMITA34Claude Code, Codex
sector-rotationHKUDS/Vibe-TradingSkill38kyesterdayMITA39Claude Code, Codex
twitter-readerhimself65/finance-skillsSkill3.5k2d agoMITA110Claude Code
strategy-pivot-designertradermonty/claude-trading-skillsSkill3.7k2d agoMITA28Claude Code, Codex
energy-procurementhashgraph-online/awesome-codex-pluginsSkill1.5kyesterdayApache-2.0A93Claude Code, Codex
airdrop-hunting-guidenirholas/three.wsSkill269yesterdayApache-2.0A54Claude Code, Codex
multi-expert-analyzerdigoal/blogSkill8.6k2d agoGPL-2.0A292Codex