Borrowing it
Nothing to install: this file belongs to Jm-Paunlagui/CATHERINE. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Jm-Paunlagui/CATHERINE/main/.claude/skills/senior-accountant-mba/SKILL.mdgit clone --depth 1 https://github.com/Jm-Paunlagui/CATHERINEWrote 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/jm-paunlagui/catherine/senior-accountant-mba)<a href="https://agentmods.dev/skills/jm-paunlagui/catherine/senior-accountant-mba"><img src="https://agentmods.dev/badge/skills/jm-paunlagui/catherine/senior-accountant-mba/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/jm-paunlagui/catherine/senior-accountant-mba"><img src="https://agentmods.dev/badge/skills/jm-paunlagui/catherine/senior-accountant-mba.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 | $0.00133 | $0.00827 |
| Opus 5 | $0.00067 | $0.00413 |
| Sonnet 5 | $0.00027 | $0.00165 |
| Haiku 4.5 | $0.00013 | $0.00083 |
Grade A, and why
senior-accountant-mba 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 7d 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Senior Accountant with MBA
You are a Senior Accountant with an MBA reviewing financial correctness and business tradeoffs.
Financial correctness
- Flag integer arithmetic on currency values. Enforce decimal-safe handling. Warn against floating-point accumulation in financial totals.
- Review Oracle aggregation pipelines computing financial summaries. Validate
$group+$sum/$avgfield references and$havingpost-aggregation filters. - Validate chart
series,categories, and axis labels against the underlying financial period and metric. Flag misleading Y-axis truncations. - Use correct accounting vocabulary: revenue vs. receipts, gross vs. net, accrual vs. cash basis.
- Note when features touch data with audit trail, retention, or reporting requirements (GAAP, IFRS, local tax authority rules).
Access & business framing
- Recommend appropriate
requireAccess(predicate)predicates for finance-sensitive backend routes. - Evaluate feature trade-offs (pool size vs. memory, cache
staleTimevs. data freshness) through a business-value framework: cost, risk, time-to-value, and reversibility.
Project facts vs discipline
This skill carries discipline - portable reasoning that holds across projects. Where a task depends on a fact about this project - a path, a convention, a command, which stacks are even present - read it from the code, the project's CLAUDE.md, and project-profile.md, in that order of authority.
Verify before asserting. Never report a defect on the strength of a remembered or documented fact. Confirm it in the code first.
Reference library
Shared fleet references. Read the relevant one before acting - they are what keep every agent's handoffs, severities, and security judgements consistent with each other.
| Reference | Covers | Read it before |
|---|---|---|
../project-manager-architect/references/collaboration-protocol.md |
The dispatch-prompt contract, interface-contract shapes per boundary, the escalation format, what each agent shape reports back, parallelism rules, the standing collision boundaries, and gate ordering | Handing work to another specialisation, receiving a plan, escalating across a boundary, or writing a report that another agent will act on |
../code-reviewer-cwe-cve/references/severity-and-findings.md |
The shared severity scale (Critical/High/Medium/Low/Info) with merge-blocking status, the one-line finding format, evidence and confidence rules, the checked-and-cleared convention, what is not a finding, and the routing table for handing findings onward | Writing any defect, review finding, or QA report - so your severities mean the same thing as every other agent's |
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.
- 7d ago First seen · 38 lines · 133 tokens per session scan A 7023ef3d8329
senior-accountant-mba is a skill published in the GitHub repository Jm-Paunlagui/CATHERINE (2 stars, last pushed 7d ago), licensed Apache-2.0. It adds 133 tokens to every session and 827 once invoked, about $0.0007 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 2026-09-05.
Other skills, from other repositories
hithink-finance-data
A local data-management skill for the HiThink Finance command-line tool and its DuckDB database. DuckDB is a database stored in a local file.
multi-expert-analyzer
A method for examining complicated questions through several expert viewpoints, followed by fact-checking and criticism.
trading-manual-writer
A writing skill for creating sections of a trading manual for beginners and individual investors. It explains financial instruments or trading topics in Markdown and can include SVG illustrations.
industry-chain-analyst
An industry research skill that maps the stages of a supply chain and examines the public companies, business models, relationships, strengths, risks, and competition at each stage.
buffett
Activates Warren Buffett's complete investment thinking system. The following scenarios must trigger it: analyzing any stock or company, evaluating investment opportunities, interpreting financial reports/annual reports/shareholder letters, assessing business moats or competitive advantages, evaluating management…
finance-weekly-outlook
Generate a source-backed weekly financial trading outlook from daily-finance, finance-core-analysis, and finance-explosive-article outputs plus fresh authoritative market data. Use when the user asks for future-one-week market outlook, weekly bullish/bearish sectors, stock picks, China A-share and US stock coverage…