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.
curl -O https://raw.githubusercontent.com/calebl/ynab-mcp-server/main/.agents/skills/ynab-tool-development/SKILL.mdgit clone --depth 1 https://github.com/calebl/ynab-mcp-serverWrote 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/calebl/ynab-mcp-server/ynab-tool-development)<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.
<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>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 | $0.00034 | $0.00944 |
| Opus 5.5 | $0.00014 | $0.00378 |
| Sonnet 5.5 | $0.00007 | $0.00189 |
| Haiku 4.5 | $0.00003 | $0.00094 |
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.
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.
- 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'}` }]
};
}
}
- Register in
src/registry.ts— import the module and add it to thetoolsarray. 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.
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.
- 18d ago Changed · +3 lines e2b7cd7ad211
- 22d ago First seen · 76 lines · 34 tokens per session scan A 31020c720eeb
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.
ynab-tool-development compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ynab-tool-developmentcalebl/ynab-mcp-server | Skill | 162 | 4d ago | MIT | A | 34 | Claude Code, Codex |
| sector-rotationHKUDS/Vibe-Trading | Skill | 38k | yesterday | MIT | A | 39 | Claude Code, Codex |
| twitter-readerhimself65/finance-skills | Skill | 3.5k | 2d ago | MIT | A | 110 | Claude Code |
| strategy-pivot-designertradermonty/claude-trading-skills | Skill | 3.7k | 2d ago | MIT | A | 28 | Claude Code, Codex |
| energy-procurementhashgraph-online/awesome-codex-plugins | Skill | 1.5k | yesterday | Apache-2.0 | A | 93 | Claude Code, Codex |
| airdrop-hunting-guidenirholas/three.ws | Skill | 269 | yesterday | Apache-2.0 | A | 54 | Claude Code, Codex |
| multi-expert-analyzerdigoal/blog | Skill | 8.6k | 2d ago | GPL-2.0 | A | 292 | Codex |