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-recon)<a href="https://agentmods.dev/commands/teamtinvio/jaz-ai/jaz-recon"><img src="https://agentmods.dev/badge/commands/teamtinvio/jaz-ai/jaz-recon/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-recon"><img src="https://agentmods.dev/badge/commands/teamtinvio/jaz-ai/jaz-recon.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 | $0.00524 |
| Opus 5.5 | $0.00007 | $0.00210 |
| Sonnet 5.5 | $0.00004 | $0.00105 |
| Haiku 4.5 | $0.00002 | $0.00052 |
Grade A, and why
jaz-recon 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 25d 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
Bank Reconciliation
Run the bank recon playbook from the jaz-jobs skill (references/bank-recon.md). Includes automated matching and manual resolution steps.
Usage
/jaz-recon DBS Current 2025-01
/jaz-recon all accounts last month
Workflow
1. Open the playbook
The steps are in the jaz-jobs skill: references/bank-recon.md. Read it first and walk its steps in order; it names the exact tool or command for each one.
2. Import bank statement (if not already imported)
clio bank import --account "DBS Current" --file statement.csv --json
Or for OFX/QIF files, same command (format auto-detected).
3. Run automated matching
clio jobs bank-recon match --input bank-data.json --json
--input is a JSON file holding the unreconciled bankRecords and the candidate transactions (format in the jaz-jobs skill, references/bank-match.md). The matcher takes no --account flag: pull the account's records first (clio bank records <bankAccountResourceId> --status UNRECONCILED --json).
The matcher uses a 5-phase cascade: 1:1 exact, N:1 group, 1:N split, N:M complex, fuzzy.
4. Review unmatched items
The matcher output lists unmatched bank records and book entries. For each:
- Bank record with no book entry: Create the missing transaction (invoice, bill, cash entry, journal)
- Book entry with no bank record: Verify timing (may match next period's statement)
- Partial matches: Confirm and adjust
5. Verify
clio reports generate cash-balance --to 2025-01-31 --json
Compare closing balance per books vs bank statement.
Key Rules
clio bank import --accountaccepts the bank account name (fuzzy matched)- Bank records are imported via
clio bank import(CSV, OFX, QIF) - The matcher runs offline; it suggests matches but doesn't auto-confirm
- Bank statement balance vs book balance difference = unreconciled items
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.
- 25d ago Changed 043d0c233447
- 1mo ago Changed 1bc2b242b4b8
- 1mo ago First seen · 62 lines · 18 tokens per session scan A 8bde9285c097
jaz-recon is a command published in the GitHub repository teamtinvio/jaz-ai (8 stars, last pushed 9d ago), licensed MIT. It adds 18 tokens to every session and 524 once invoked, about $0.0001 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 commands, from other repositories
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.
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.
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.