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 jobsgit 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/jobs)<a href="https://agentmods.dev/skills/teamtinvio/jaz-ai/jobs"><img src="https://agentmods.dev/badge/skills/teamtinvio/jaz-ai/jobs/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/jobs"><img src="https://agentmods.dev/badge/skills/teamtinvio/jaz-ai/jobs.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 | $0.00088 | $0.03428 |
| Opus 5 | $0.00044 | $0.01714 |
| Sonnet 5 | $0.00018 | $0.00686 |
| Haiku 4.5 | $0.00009 | $0.00343 |
Grade A, and why
jaz-jobs 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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jobs Skill
You are helping an SMB accountant or bookkeeper complete recurring accounting tasks in Jaz — period-end closes, bank reconciliation, tax filing, payment processing, and operational reviews. These are the real jobs that keep the books accurate and the business compliant.
Jaz-native, not generic. Every job in this skill names specific Jaz tools (
search_invoices,quick_reconcile,bulk_finalize_drafts,reconcile_with_payments, report tools likegenerate_trial_balance,download_export), Jaz reconciliation modes, and Jaz capsule patterns. It is NOT an interchangeable accounting workflow reference; it is the operating manual for running these processes through the Jaz platform tools. When the playbook says "match bank entries", it means call the 5-phase cascade matcher (clio jobs bank-recon matchfor a local CLI run, or follow the cascade logic inreferences/bank-match.mdand drive thereconcile_*tools directly), not "use any matching algorithm".
Jobs combine recipes, calculators, and platform tools into complete business processes. If recipes are ingredients, jobs are the meal. Each per-job reference is the canonical end-to-end orchestration: it lists the phases, and for each step names the exact report tool, recipe, or API call to run.
How to run a job
You orchestrate the real platform tools directly, following the phase sequence in the per-job reference:
- Hosted / MCP agent (no shell): the per-job reference is your checklist. Walk its phases in order and call the named platform tools —
plan_recipe/execute_recipe,search_invoices/search_bills/search_bank_records, thegenerate-reports/*report tools (generate_trial_balance,generate_aged_ar,generate_vat_ledger, …),reconcile_*,create_journal,bulk_finalize_drafts,update_accountlockDate, and so on. There is no separate "blueprint tool" to call — the reference IS the plan. - Local CLI convenience: if you're running
clioin a terminal (e.g. Claude Code),clio jobs <type> --jsonprints the same phased checklist for the period so a human or script can follow it. This is a convenience, not the main path for a hosted agent — the platform tools above are the path that actually does the work.
What ships with it
23 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/audit-prep.md 15 KB
- references/bank-match.md 12 KB
- references/bank-recon.md 21 KB
- references/building-blocks.md 10 KB
- references/credit-control.md 9.4 KB
- references/document-collection.md 10 KB
- references/fa-review.md 9.8 KB
- references/gst-vat-filing.md 11 KB
- references/month-end-close.md 19 KB
- references/payment-run.md 12 KB
- references/quarter-end-close.md 9.5 KB
- references/sg-tax/add-backs-guide.md 22 KB
- references/sg-tax/capital-allowances-guide.md 16 KB
- references/sg-tax/data-extraction.md 15 KB
- references/sg-tax/enhanced-deductions.md 11 KB
- references/sg-tax/exemptions-and-rebates.md 8.3 KB
- references/sg-tax/form-cs-fields.md 10 KB
- references/sg-tax/ifrs16-tax-adjustment.md 8.8 KB
- references/sg-tax/losses-and-carry-forwards.md 11 KB
- references/sg-tax/overview.md 9.5 KB
- references/sg-tax/wizard-workflow.md 17 KB
- references/supplier-recon.md 9.5 KB
- references/year-end-close.md 14 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 a43b59b45ead
- yesterday Changed 6d966392ba6c
- 3d ago Changed 5495fefddb02
- 5d ago Changed 22a8519663eb
- 6d ago Changed 6de2a5f81d94
- 7d ago Changed b693d9818724
- 11d ago First seen · 186 lines · 88 tokens per session scan A 84806e17a629
jaz-jobs is a skill published in the GitHub repository teamtinvio/jaz-ai (7 stars, last pushed yesterday), licensed MIT. It adds 88 tokens to every session and 3,428 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.
Other skills, from other repositories
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.
voiden
Create and edit Voiden .void files for API testing. Covers the .void file format and all enabled extension block types.