yuki

yuki is a skill for Claude Code from apideck-libraries/api-skills. It costs 71 tokens per session (2,294 once invoked), scanned A, original, Apache-2.0.

A Yuki connection through Apideck's shared accounting API. Yuki is an online accounting service for business finances.

In plain words
What is it for?
Use it to read, write, or reconcile invoices, bills, payments, accounts, and journal entries in Yuki.
Why use it?
It provides a common way to work with accounting systems and reduces per-customer connection work. The connector is in beta, so some operations may be incomplete.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the apideck plugin — 181 skills, 3 commands shipped together

Good fit Use it to read, write, or reconcile invoices, bills, payments, accounts, and journal entries in Yuki.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/apideck-libraries/api-skills/yuki
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 apideck-libraries/api-skills --skill yuki
Clone the repo
git clone --depth 1 https://github.com/apideck-libraries/api-skills

Made for: Claude Code.

Or install apideck, the plugin that ships this one along with the rest of its 181 skills, 3 commands.

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 yuki

README.md
[![agentmods](https://agentmods.dev/badge/skills/apideck-libraries/api-skills/yuki/github.svg)](https://agentmods.dev/skills/apideck-libraries/api-skills/yuki)
Your own site
<a href="https://agentmods.dev/skills/apideck-libraries/api-skills/yuki"><img src="https://agentmods.dev/badge/skills/apideck-libraries/api-skills/yuki/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 yuki

Your own site · 80×15
<a href="https://agentmods.dev/skills/apideck-libraries/api-skills/yuki"><img src="https://agentmods.dev/badge/skills/apideck-libraries/api-skills/yuki.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,294 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00071 $0.02294
Opus 5.5 $0.00028 $0.00918
Sonnet 5.5 $0.00014 $0.00459
Haiku 4.5 $0.00007 $0.00229

Measured 20d ago against content hash c5899d9d2df9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

yuki scanned grade A with 1 finding 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 20d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl 'https://unify.apideck.com/proxy' \
providers/claude/plugin/skills/yuki/SKILL.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Yuki (via Apideck)

Access Yuki through Apideck's Accounting unified API — one of 34 Accounting connectors that share the same method surface. Code you write here ports to Access Financials, Acumatica, banqUP and 30 other Accounting connectors by changing a single serviceId string. Apideck handles auth, pagination, rate limiting, and retries so you don't write per-tenant Yuki plumbing.

Beta connector. Yuki is currently in beta on Apideck. Expect partial resource coverage and occasional mapping gaps. Always verify coverage (see below) and fall back to the Proxy API for unsupported operations.

Quick facts

At a glance

  • Implementation difficulty: moderate — API key authentication over SOAP
  • Vendor partnership required: no — There is no app registration, review or partner agreement for Yuki's web services.
  • Apideck-managed credentials: not available — Each consumer connects with their own web service key, so there is no shared Apideck application.
  • Account type required: Yuki account on any bundle, including the free Minimal bundle, with web service access activated on the domain.
  • Consumer access level: A user with the Portal administrator or Management role — only those roles can create web service keys.
  • Sandbox: not available — Yuki's free Minimal bundle is a real account, not a test environment; there is no developer sandbox or demo administration.
  • Costs: Free to 1,000 calls/day. Above that: EUR 10.50/month for 1,001-5,000 calls/day, EUR 105/month for 5,001-10,000 — added by the consumer's accountant.
  • Rate limits: 1,000 web service calls per day per domain; paid add-ons raise the ceiling.
  • Authentication: A WebserviceAccessKey; not OAuth, and no redirect for your consumer to complete.
  • Webhooks: No webhooks — Yuki documents no event or subscription mechanism, and this connector adds no virtual webhooks, so poll for changes.

Read the full file on GitHub · 180 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 20d ago Changed · +24 lines c5899d9d2df9
  2. 1mo ago First seen · 156 lines · 71 tokens per session scan A 02300198579b

Subscribe to this mod's changes

yuki is a skill published in the GitHub repository apideck-libraries/api-skills (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 71 tokens to every session and 2,294 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories