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-fa-review)<a href="https://agentmods.dev/commands/teamtinvio/jaz-ai/jaz-fa-review"><img src="https://agentmods.dev/badge/commands/teamtinvio/jaz-ai/jaz-fa-review/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-fa-review"><img src="https://agentmods.dev/badge/commands/teamtinvio/jaz-ai/jaz-fa-review.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 | $0.00629 |
| Opus 5.5 | $0.00007 | $0.00252 |
| Sonnet 5.5 | $0.00004 | $0.00126 |
| Haiku 4.5 | $0.00002 | $0.00063 |
Grade A, and why
jaz-fa-review 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fixed Asset Review
Run the FA review playbook from the jaz-jobs skill (references/fa-review.md). Reviews the fixed asset register for accuracy and completeness.
Usage
/jaz-fa-review
/jaz-fa-review check for assets to dispose
Workflow
1. Open the playbook
The steps are in the jaz-jobs skill: references/fa-review.md. Read it first and walk its steps in order; it names the exact tool or command for each one.
2. Review assets
The playbook walks through:
- Assets with zero remaining book value (candidates for write-off/disposal)
- Assets past useful life but still active
- Depreciation accuracy vs policy
- Missing or misclassified assets
3. Process disposals
For assets to dispose, use the calculator first:
clio calc asset-disposal --cost 50000 --salvage 5000 --life 5 --acquired 2020-01-01 --disposed 2025-06-15 --proceeds 8000 --json
The calculator returns the gain or loss; it posts nothing. A registered asset is disposed of through the register, which books the disposal itself. Do not also post the calculator's full disposal journal: that books it twice.
# Scrapped: no journal
clio fixed-assets discard <assetResourceId> --disposal-date 2025-06-15 --depreciation-end-date 2025-06-15 --json
# Sold: post the proceeds as the sale entry first (Dr bank, Cr the asset's fixed-asset account),
# then mark the asset sold against that journal's credit line
clio journals create --input sale-entry.json --json
clio fixed-assets sell --id <assetResourceId> --depreciation-end-date 2025-06-15 --gain-loss-account <accountId> --sale-type JOURNAL_MANUAL --sale-item <journalCreditLineId> --json
Compare the gain or loss the register booked with the calculator's figure.
4. Verify
Check the trial balance for fixed asset and accumulated depreciation accounts:
clio accounts search "Fixed Asset" --json
clio reports generate trial-balance --to 2025-12-31 --json
Key Rules
- Disposals compute gain/loss: proceeds - (cost - accumulated depreciation)
clio calc asset-disposalonly calculates; you post the disposal journal and update the register- The register update is a separate call:
clio fixed-assets sell(sold) orclio fixed-assets discard(scrapped); without it Jaz keeps depreciating the asset - Depreciation methods for CLI calculators:
sl(straight-line),ddb(double declining),150db
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.
- 1mo ago Changed 4a82e6d275c3
- 1mo ago Changed · +6 lines c922230211b7
- 1mo ago Changed fa778a2eedff
- 2mo ago First seen · 62 lines · 18 tokens per session scan A 91fe2e336e6d
jaz-fa-review is a command published in the GitHub repository teamtinvio/jaz-ai (8 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 629 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.
jaz-fa-review compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| jaz-fa-reviewteamtinvio/jaz-ai | Command | 8 | yesterday | MIT | A | 18 | Claude Code |
| correctmichielinksee/bantou | Command | 2 | 2mo ago | MIT | A | 13 | Claude Code |
| importmichielinksee/bantou | Command | 2 | 2mo ago | MIT | A | 14 | Claude Code |
| nightlymichielinksee/bantou | Command | 2 | 2mo ago | MIT | A | 15 | Claude Code |
| setupmichielinksee/bantou | Command | 2 | 2mo ago | MIT | A | 16 | Claude Code |
| classifymichielinksee/bantou | Command | 2 | 2mo ago | MIT | A | 16 | Claude Code |
| reportmichielinksee/bantou | Command | 2 | 2mo ago | MIT | A | 12 | Claude Code |