cove-for-ynab: Skill for Claude Code

.claude/skills/month-close/SKILL.md

month-close is a skill for Claude Code from walensis-labs/cove-for-ynab. It costs 72 tokens per session (1,177 once invoked), scanned A, original, MIT.

A guided session for closing a month in YNAB, a budgeting app, by checking account balances and then planning the budget. It uses connected MCP tools to review transactions, categories, approvals, and credit-card coverage.

In plain words
What is it for?
Run month-end checks, review uncategorized or unapproved transactions, identify credit-card coverage issues, suggest money moves, and apply approved moves when YNAB writes are enabled.
Why use it?
It helps find unresolved budgeting gaps before the month is closed and pairs each problem with a proposed fix. Changes are only applied when writes are enabled, and the session does not automatically approve items.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: positional $N argument.

This is walensis-labs/cove-for-ynab's own configuration. It tells Claude Code how to work on cove-for-ynab 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 cove-for-ynab configures →

Reuse

Borrowing it

Nothing to install: this file belongs to walensis-labs/cove-for-ynab. 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/walensis-labs/cove-for-ynab/main/.claude/skills/month-close/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/walensis-labs/cove-for-ynab

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 month-close

README.md
[![agentmods](https://agentmods.dev/badge/skills/walensis-labs/cove-for-ynab/month-close/github.svg)](https://agentmods.dev/skills/walensis-labs/cove-for-ynab/month-close)
Your own site
<a href="https://agentmods.dev/skills/walensis-labs/cove-for-ynab/month-close"><img src="https://agentmods.dev/badge/skills/walensis-labs/cove-for-ynab/month-close/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 month-close

Your own site · 80×15
<a href="https://agentmods.dev/skills/walensis-labs/cove-for-ynab/month-close"><img src="https://agentmods.dev/badge/skills/walensis-labs/cove-for-ynab/month-close.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,177 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 $0.00072 $0.01177
Opus 5 $0.00036 $0.00589
Sonnet 5 $0.00014 $0.00235
Haiku 4.5 $0.00007 $0.00118

Measured 10d ago against content hash bcdaead94295, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

month-close 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 10d 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.

.claude/skills/month-close/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run the month-close session exactly as specified in the playbook below. Before starting: confirm the cutoff date (default: last day of the month being closed) and that the "MCP for YNAB" server is connected (35 tools). Writes require YNAB_ALLOW_WRITES=1 — if writes are disabled, run the Balance steps read-only, present the moves you WOULD make, and tell the user how to enable writes for the apply step.

The Month-Close Session (Balance → Plan)

You are guiding a monthly catch-up session against YNAB via the "MCP for YNAB" tools. Anchor everything to the user's cutoff date (ask if not given — normally the last day of the month being closed). Principles, non-negotiable: numbers are PROVISIONAL until blockers are empty; donor moves before Ready-to-Assign; never auto-approve; every applied move gets a reason; pair every surfaced problem with its one-tap fix; keep healthy findings to one line.

BALANCE

1. Hygiene. Run month_close with the cutoff. If gapStatus is "provisional", present the blocker counts and work through them: show blockers.uncategorized and blockers.unapproved rows, propose categories (from payee history via list_transactions if helpful), and apply ONLY what the user approves via update_transactions (categorize + approve together; never approve without the user seeing the categorization). Uncleared-before-cutoff rows need INVESTIGATION, not force: uncleared is YNAB register state, not "pending at the bank". For each one, either it settled (mark it cleared via update_transactions) or it never happened and is corrupting the gap (delete_transaction, with the user's approval). Walk them with the user.

2. Trusted gap. Re-run month_close until gapStatus is "final". "Final" is reached by cleaning the register, not by waiting: resolve every uncleared-before-cutoff row per step 1's investigation. Only present a provisional gap if the user explicitly defers an unresolved row — say so when you do. Present per-card: working/cleared as-of balances, available at month end, and the gap (0 = covered; negative = short). Heed any warnings (unmatched or ambiguous cards are NOT covered by the report).

Read the full file on GitHub · 75 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. 10d ago First seen · 75 lines · 72 tokens per session scan A bcdaead94295

Subscribe to this mod's changes

month-close is a skill published in the GitHub repository walensis-labs/cove-for-ynab (0 stars, last pushed 29d ago), licensed MIT. It adds 72 tokens to every session and 1,177 once invoked, about $0.0004 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

okx-cex-portfolio

This skill should be used when the user asks about 'account balance', 'how much USDT do I have', 'my funding account', 'show my positions', 'open positions', 'position P&L', 'unrealized PnL', 'closed positions', 'position history', 'realized PnL', 'account bills', 'transaction history', 'trading fees', 'fee tier'…

okx/agent-trade-kit · 236 tokens

agoragentic-transaction-assurance

Prepare, evaluate, and reconcile autonomous agent transactions without self-granting payment or owner authority. Use when an agent must bind principal authority, seller terms, payment evidence, execution, delivered outcome, and reconciliation; handle paid retries safely; or prepare an authority request for owner…

rhein1/agoragentic-integrations · 65 tokens

stripe

Query and manage Stripe resources (customers, payments, subscriptions). Reads from apps/website/.env. Write operations blocked on live keys.

Kevin-Liu-01/Agent-Machines · 29 tokens

recurrent-payment

A recurring-payment workflow for T-Kassa, a payment service. It links a customer's card during an initial payment and later charges that saved payment authorisation for a subscription.

theYahia/WWmcp · 26 tokens

refund-payment

A payment procedure for refunding a completed T-Kassa payment or cancelling a payment that is still on hold. T-Kassa is a payment service, and the procedure can also send the required closing receipt.

theYahia/WWmcp · 20 tokens

agreement-setup

Set up a bKash tokenized agreement for repeat charges and check its status.

theYahia/WWmcp · 20 tokens