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.
npx skills add teamtinvio/jaz-ai --skill transaction-recipesgit clone --depth 1 https://github.com/teamtinvio/jaz-aiWrote 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/teamtinvio/jaz-ai/transaction-recipes)<a href="https://agentmods.dev/skills/teamtinvio/jaz-ai/transaction-recipes"><img src="https://agentmods.dev/badge/skills/teamtinvio/jaz-ai/transaction-recipes/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/teamtinvio/jaz-ai/transaction-recipes"><img src="https://agentmods.dev/badge/skills/teamtinvio/jaz-ai/transaction-recipes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00124 | $0.06000 |
| Opus 5.5 | $0.00050 | $0.02400 |
| Sonnet 5.5 | $0.00025 | $0.01200 |
| Haiku 4.5 | $0.00012 | $0.00600 |
Grade A, and why
jaz-recipes 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 today.
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 — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Transaction Recipes Skill
You are modeling complex multi-step accounting scenarios in Jaz: transactions that span multiple periods, involve changing amounts, or require several linked entries to complete a single business event.
Jaz-native, not generic. Every recipe in this skill is designed around the Jaz calculators (
calculate/clio calc), Jaz capsule types, Jaz CoA classifications, and Jaz scheduler primitives. It is NOT an interchangeable IFRS reference; it is the operating manual for posting these transactions through the Jaz ledger. Never work the amounts by hand: run the calculator first and post the lines it returns. Nothing posts a recipe for you: the calculator posts nothing, and you create the capsule and each entry yourself (see "Posting a Recipe: Three Steps").
This skill provides Jaz-contextual recipes with full accounting logic. For API field names and payloads, load the jaz-api skill alongside this one. For the operational close workflows that invoke these recipes (month-end close, GST/VAT filing, year-end close), load the jaz-jobs skill.
When to Use This Skill
- Setting up prepaid expenses, deferred revenue, or accrued liabilities
- Modeling loan repayment schedules with amortization tables
- Implementing IFRS 16 lease accounting (right-of-use assets + lease liabilities)
- Recording hire purchase agreements (ownership transfers, depreciate over useful life)
- Recording depreciation using methods Jaz doesn't natively support (declining balance, 150DB)
- Managing fixed deposit placements with interest accrual schedules (IFRS 9)
- Disposing of fixed assets: sale, scrap, or write-off with gain/loss calculation (IAS 16)
- Verifying the period-end FX revaluation Jaz posts itself (IAS 21): the calculator checks the figure, and its result is not posted
- Calculating expected credit loss provisions on aged receivables (IFRS 9)
- Accruing employee leave and bonus obligations (IAS 19)
- Recognizing provisions at PV with discount unwinding (IAS 37)
- Declaring and paying dividends
- Recording and reconciling intercompany transactions across entities
- Capitalizing costs in WIP and transferring to fixed assets
- Any scenario that groups related transactions in a capsule over multiple periods
What ships with it
17 files 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.
- references/accrued-expenses.md 10 KB
- references/asset-disposal.md 16 KB
- references/bad-debt-provision.md 12 KB
- references/bank-loan.md 13 KB
- references/building-blocks.md 25 KB
- references/capital-wip.md 15 KB
- references/declining-balance.md 12 KB
- references/deferred-revenue.md 11 KB
- references/dividend.md 12 KB
- references/employee-accruals.md 11 KB
- references/fixed-deposit.md 12 KB
- references/fx-revaluation.md 10 KB
- references/hire-purchase.md 7.7 KB
- references/ifrs16-lease.md 14 KB
- references/intercompany.md 11 KB
- references/prepaid-amortization.md 10 KB
- references/provisions.md 13 KB
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.
- today Changed cd07392ec9f4
- 10d ago Changed 3cfdd6d9d6e5
- 11d ago Changed 7647eeb5f379
- 15d ago Changed 4c5b77409dc0
- 21d ago Changed 8da48978f29a
- 22d ago Changed d8910c2bf391
- 23d ago Changed 99fd7bdf9dd4
- 24d ago Changed 547dd78e44dc
- 27d ago Changed · -63 lines · +4 tokens per session 30c80d555f2f
- 28d ago First seen · 360 lines · 120 tokens per session scan A 9fdad0bc2f93
jaz-recipes is a skill published in the GitHub repository teamtinvio/jaz-ai (8 stars, last pushed yesterday), licensed MIT. It adds 124 tokens to every session and 6,000 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
validate-iban-before-payment
Validate an IBAN and identify its bank with the IBANforge REST API before money is sent to it, or before it is saved as the bank details of a supplier, customer or employee. Use when writing code that pays out to an IBAN, onboards a payee, imports bank details from a form or a CSV file, or needs the bank name, the BIC…
correction-memory
A local memory system that stores tax-accountant corrections to transaction classifications. It matches future transactions to earlier vendor or description patterns.
nightly-batch
Batch-process all client companies overnight. Fetches unprocessed transactions from freee API, runs the full classification pipeline, and generates a summary for morning review.
tax-classifier
A system for assigning Japanese business transactions to accounting categories, called 勘定科目, and consumption-tax treatments. It checks exclusions, past corrections, keywords, and then uses AI when needed.
csv-importer
A tool for importing transaction CSV files—spreadsheet files separated by commas—from Japanese accounting software and classifying every imported row.
monthly-closer
A monthly accounting report generator that summarizes transactions by account category and compares them with the previous month.