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.
git 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/commands/teamtinvio/jaz-ai/jaz-gst)<a href="https://agentmods.dev/commands/teamtinvio/jaz-ai/jaz-gst"><img src="https://agentmods.dev/badge/commands/teamtinvio/jaz-ai/jaz-gst/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/commands/teamtinvio/jaz-ai/jaz-gst"><img src="https://agentmods.dev/badge/commands/teamtinvio/jaz-ai/jaz-gst.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 | $0.00018 | $0.00404 |
| Opus 5 | $0.00009 | $0.00202 |
| Sonnet 5 | $0.00004 | $0.00081 |
| Haiku 4.5 | $0.00002 | $0.00040 |
Grade A, and why
jaz-gst 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.
What it actually says
GST/VAT Filing Preparation
Execute the GST/VAT filing workflow via clio jobs gst-vat. Reviews the tax ledger and produces a filing-ready summary.
Usage
/jaz-gst 2025-Q1
/jaz-gst 2025-Q4
Workflow
1. Generate the blueprint
clio jobs gst-vat --period 2025-Q1 --json
2. Review the tax ledger
The blueprint walks through:
- Output tax (sales) totals by tax code
- Input tax (purchases) totals by tax code
- Exempt and out-of-scope transactions
- Discrepancies (e.g., transactions missing tax codes)
3. Fix discrepancies
For transactions missing tax: update them via clio invoices update, clio bills update, etc.
For misclassified tax codes: correct the underlying transactions.
4. Generate reports for filing
clio reports generate trial-balance --to 2025-03-31 --json
The GST summary from the blueprint maps directly to the GST F5 return boxes (Singapore) or equivalent local form.
5. File
The actual filing is done outside Jaz (IRAS myTax Portal for Singapore, etc.). The output provides the numbers to enter.
Key Rules
- Period format:
YYYY-QN(Q1 = Jan-Mar for standard FY) - GST/VAT only applies to tax-enabled transactions —
isTaxVatApplicable: true - Output tax = collected on sales, Input tax = paid on purchases
- Net GST payable = output tax - input tax
- Singapore-specific: 9% GST, quarterly filing, due 1 month after quarter-end
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.
- 10d ago First seen · 57 lines · 18 tokens per session scan A 3dcc8333e9d7
jaz-gst is a command published in the GitHub repository teamtinvio/jaz-ai (7 stars, last pushed today), licensed MIT. It adds 18 tokens to every session and 404 once invoked, about $0.0001 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.
Other commands, from other repositories
setup
An interactive setup wizard for configuring a Japanese tax accountant's office. It asks about the firm, clients, accounting software, expense rules, overseas services, invoices, payroll, and report sharing.
classify
A command that classifies one Japanese business transaction into an accounting category and tax type. It checks exclusions, past corrections, known keywords, and uses AI when needed.
correct
A command for correcting an incorrectly classified accounting transaction and saving the correction for future matching transactions.
import
A command that imports CSV files exported by Japanese accounting software and automatically classifies their transactions. CSV is a plain-text table format commonly used to move data between programs.
nightly
A command that runs overnight bookkeeping processing for every company connected through the freee accounting service.
report
A command that creates a monthly closing report for a client company. Monthly closing is the accounting process of summarizing and reviewing a month's transactions.