prove

prove is a skill for Claude Code from cynco-labs/ai-accounting-skills. It costs 18 tokens per session (397 once invoked), scanned A, original, MIT.

A bookkeeping quality-check workflow for an accounting engagement. It chooses checks based on whether the work is routine bookkeeping or a year-end, compilation, or tax engagement.

In plain words
What is it for?
Use it to check bookkeeping records, transactions, journals, bank reconciliations, and trial balances, or to run deeper year-end checks and financial-statement review. It can mark the engagement complete when the required checks pass.
Why use it?
It helps prevent a job from receiving checks that are too extensive or too limited for its agreed scope. It also makes the final handoff point to a generated HTML report.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/generate_html_report.py <client>.

Part of the accounting-engagement plugin — 45 skills shipped together

Good fit Use it to check bookkeeping records, transactions, journals, bank reconciliations, and trial balances, or to run deeper year-end checks and financial-statement review. It can mark the engagement complete when the required checks pass.

Compare 6 skills from other repositories ↓
Install

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.

Clone the repo
git clone --depth 1 https://github.com/cynco-labs/ai-accounting-skills
agentmods
npx agentmods add skills/cynco-labs/ai-accounting-skills/prove

Made for: Claude Code.

Or install accounting-engagement, the plugin that ships this one along with the rest of its 45 skills.

Wrote 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.

agentmods badge for prove

README.md
[![agentmods](https://agentmods.dev/badge/skills/cynco-labs/ai-accounting-skills/prove/github.svg)](https://agentmods.dev/skills/cynco-labs/ai-accounting-skills/prove)
Your own site
<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.

agentmods 80×15 button for prove

Your own site · 80×15
<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>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 397 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 12d ago against content hash a9b04e9d668d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

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.

accounting-engagement/skills/prove/SKILL.md · 43 lines

What it actually says

/prove

Depth-scoped prove — not always year-end QC.

Do this

  1. Read engagement_state.jsonengagement_type (default bookkeeping_only).
  2. Load shared/runtime-brief.md · references/depth_gates.json.
  3. Refresh HTML pack (required gate):
python3 scripts/generate_html_report.py <client>
  1. 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

  1. quality-review then depth_gates.py --strict (ATB + FS + QC A + HTML).
  2. Lock via finalise-accounts only after user confirms.
  3. 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.

Changes

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.

  1. 12d ago First seen · 43 lines · 18 tokens per session scan A a9b04e9d668d

Subscribe to this mod's changes

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.

Related

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.

CPUtester5465/countbean-plugin · 54 tokens

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…

ericrisco/rsc-harness · 84 tokens

jangbu-jongso

A Korean tax-document checklist generator for individuals, freelancers, sole-company owners, mixed earners, and certain business owners.

kimlawtech/korean-jangbu-for · 139 tokens

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.

kimlawtech/korean-jangbu-for · 144 tokens

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.

kimlawtech/korean-jangbu-for · 97 tokens

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.

kimlawtech/korean-jangbu-for · 98 tokens