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 cynco-labs/ai-accounting-skills --skill quality-reviewgit clone --depth 1 https://github.com/cynco-labs/ai-accounting-skillsWrote 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/cynco-labs/ai-accounting-skills/quality-review)<a href="https://agentmods.dev/skills/cynco-labs/ai-accounting-skills/quality-review"><img src="https://agentmods.dev/badge/skills/cynco-labs/ai-accounting-skills/quality-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/skills/cynco-labs/ai-accounting-skills/quality-review"><img src="https://agentmods.dev/badge/skills/cynco-labs/ai-accounting-skills/quality-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 | $0.00040 | $0.00697 |
| Opus 5 | $0.00020 | $0.00349 |
| Sonnet 5 | $0.00008 | $0.00139 |
| Haiku 4.5 | $0.00004 | $0.00070 |
Grade A, and why
quality-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 12d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/quality-review
Purpose
Independent checklist pass before anything is called final. Main job: prove.
Load shared/guardrails.md and execute every item in
references/qc_checklist.md (plugin or repo root shim).
Preconditions
- Active engagement on disk (
engagement_state.json). - Adjusted TB present when FS claimed —
roll_tbderived, not freestyle. - Re-read workpapers/FS if context was compacted (disk is truth).
Steps
1 — Section A mathematical integrity [BLOCKERS]
Run every Section A check in references/qc_checklist.md against artifacts on disk.
| Check | Pass when |
|---|---|
| TB DR = CR | tb_adjusted.json (or claimed TB) difference 0 |
| BS balances | Assets = liabilities + equity |
| P&L ↔ RE | RE movement ties to profit and distributions |
| Each JE balances | Period + YE journals |
| Bank GL = recon | Diff 0.00 per bank or with limitation logged |
| Cash flow ↔ cash | Net CF explains cash movement |
Done when: every Section A item is Pass, or any Fail is written and finalisation is blocked.
2 — Sections B–E
Execute Data integrity, Standards, Completeness, Format from the same checklist. Material fails → queries or fix list; do not silent-pass.
Standards-aware classify (prove):
If classify_depth is standards_aware or engagement_type is year_end / compilation:
- Material money-in without
workpapers/analysis/revenue_recognition.md→ Fail C6b or documented with limitation - Material capex candidates without
workpapers/analysis/capital_vs_expense.md→ Fail C6c or with limitation - Analysis conclusions must not contradict coded
transactions.jsonwithout an open query
Done when: every checklist row has Pass / Fail / N/A with evidence path.
3 — Report + state
Write QC report under the engagement (e.g. workpapers/qc_report.md or firm path).
Update engagement_state.json: prove stage result; must stop if any Section A Fail.
Done when: report on disk and state reflects pass or blocker.
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.
- 12d ago First seen · 82 lines · 40 tokens per session scan A 2f9e1411c3f3
quality-review is a skill published in the GitHub repository cynco-labs/ai-accounting-skills (3 stars, last pushed 2mo ago), licensed MIT. It adds 40 tokens to every session and 697 once invoked, about $0.0002 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
countbean-accounting
Rules for writing correct double-entry Beancount transactions when managing a Countbean cloud book — account naming, how to balance postings, categorisation, and safe ingestion. Use whenever recording, importing, or correcting financial data in a Countbean book.
bookkeeping
Use when a small business needs audit-ready books — a chart of accounts, posting a transaction to the right account and side, clearing an uncategorized bank feed, cash vs accrual, or a ledger that won't tie to the bank. NOT interpreting the numbers — runway, burn, P&L cadence (that is finance-ops), NOT issuing…
jangbu-jongso
A Korean tax-document checklist generator for individuals, freelancers, sole-company owners, mixed earners, and certain business owners.
korean-jangbu-for
A Korean bookkeeping assistant for startups, freelancers, sole proprietors, and one-person companies. It processes financial files locally, helps classify transactions, and prepares accounting and tax outputs.
jangbu-import
A data-import workflow for turning bank files, card records, spreadsheets, receipts, tax invoices, and statement PDFs into a standard set of 13 transaction fields. OCR, or optical character recognition, is used to read information from document images and PDFs.
jangbu-connect
A setup guide for connecting Korean tax, bank, card, and social-insurance data through CODEF, an external API service. It explains how users obtain their own CODEF credentials and store them locally.