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 skills-qagit 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/skills-qa)<a href="https://agentmods.dev/skills/cynco-labs/ai-accounting-skills/skills-qa"><img src="https://agentmods.dev/badge/skills/cynco-labs/ai-accounting-skills/skills-qa/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/skills-qa"><img src="https://agentmods.dev/badge/skills/cynco-labs/ai-accounting-skills/skills-qa.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 | $0.00021 | $0.00885 |
| Opus 5 | $0.00010 | $0.00443 |
| Sonnet 5 | $0.00004 | $0.00177 |
| Haiku 4.5 | $0.00002 | $0.00089 |
Grade A, and why
skills-qa 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/skills-qa
Purpose
Independent design review for skills that will touch financial data — and for builder skills that teach others how to.
Load
shared/skill-craft.md(predictability, invocation, hierarchy, pruning)shared/skill-design-framework.md(scorecard)CONTEXT.md(domain language)shared/guardrails.mdshared/user-questions.md(if skill asks the human anything)- Target
SKILL.mdraw — quote it; do not review from memory alone shared/skill-collapse-map.md(intent placement)
Process
1. Identity
- Plugin, skill name, directory match
- Invocation: model-invoked vs
disable-model-invocation: true - Intent under collapse map (or builder-only)
- Pipeline gate before / after
2. Scorecard (0–2 each)
- Purpose / triggers / invocation choice
- Preconditions
- Doctrine completeness
- Gates
- Provenance (+ engine /
roll_tbwhere math) - Outputs + completion criteria
- Failure modes
- Trust surface
- Pipeline / intent position
- No firm lock-in / no fabricated numbers
- Craft (description lean, hierarchy, pruning, positive steering, leading words)
Ship bar: ≥ 18/22 and no zeros on items 4, 5, or 11 when the skill produces numbers.
3. Craft diagnostics (label findings)
| Failure | Look for |
|---|---|
| Premature completion | Steps with no checkable done condition; orchestrator pasting all stages |
| Duplication | Same rule in description + body + CLAUDE.md without single source |
| Sediment | Stale paths, dead scripts, obsolete stage names |
| Sprawl | SKILL.md > ~150 lines of reference that should be disclosed |
| No-op | “Be careful / be thorough” without a stronger leading word or criterion |
| Negation | Bans without positive procedure (“don’t invent TB” without roll_tb path) |
| Context load | Model-invoked description that essays the whole skill or stacks synonym triggers |
| Wrong invocation | Builder skill left model-invoked; rare issuance skill auto-firing |
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 · 111 lines · 21 tokens per session scan A 7082f6752cfe
skills-qa is a skill published in the GitHub repository cynco-labs/ai-accounting-skills (3 stars, last pushed 2mo ago), licensed MIT. It adds 21 tokens to every session and 885 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.