Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/cynco-labs/ai-accounting-skillsnpx agentmods add skills/cynco-labs/ai-accounting-skills/proveWrote 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/prove)<a href="https://agentmods.dev/skills/cynco-labs/ai-accounting-skills/prove"><img src="https://agentmods.dev/badge/skills/cynco-labs/ai-accounting-skills/prove/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/prove"><img src="https://agentmods.dev/badge/skills/cynco-labs/ai-accounting-skills/prove.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 | $0.00397 |
| Opus 5 | $0.00009 | $0.00198 |
| Sonnet 5 | $0.00004 | $0.00079 |
| Haiku 4.5 | $0.00002 | $0.00040 |
Grade A, and why
prove 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.
What it actually says
/prove
Depth-scoped prove — not always year-end QC.
Do this
- Read
engagement_state.json→engagement_type(defaultbookkeeping_only). - Load
shared/runtime-brief.md·references/depth_gates.json. - Refresh HTML pack (required gate):
python3 scripts/generate_html_report.py <client>
- Branch:
A — bookkeeping_only (default)
python3 scripts/depth_gates.py <client> --strict
# or: python3 scripts/close_engagement.py <client> --no-export-ledger
Required: register · txns · journals · bank recon 0 · prelim TB · outputs/*_pack.html.
Optional: Beancount export · Fava (explore only — not the handoff).
On green: status: done · tell user open the HTML pack path · “Books for [period] are ready.”
Do not open full QC/FS unless user upgrades depth.
B — year_end / compilation / year_end_tax
quality-reviewthendepth_gates.py --strict(ATB + FS + QC A + HTML).- Lock via
finalise-accountsonly after user confirms. - Optional: export Beancount · Fava. Tax only for
year_end_tax.
Done when: depth_gates --strict green; user message points at HTML pack, not a list of .md files.
See shared/slash-surface.md · scripts/depth_gates.py.
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 · 43 lines · 18 tokens per session scan A a9b04e9d668d
prove is a skill published in the GitHub repository cynco-labs/ai-accounting-skills (3 stars, last pushed 2mo ago), licensed MIT. It adds 18 tokens to every session and 397 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 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.