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.
git clone --depth 1 https://github.com/modu-ai/moai-coworkWrote 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/agents/modu-ai/moai-cowork/finance-analyst)<a href="https://agentmods.dev/agents/modu-ai/moai-cowork/finance-analyst"><img src="https://agentmods.dev/badge/agents/modu-ai/moai-cowork/finance-analyst/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/agents/modu-ai/moai-cowork/finance-analyst"><img src="https://agentmods.dev/badge/agents/modu-ai/moai-cowork/finance-analyst.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 | $0.00121 | $0.01130 |
| Opus 5.5 | $0.00048 | $0.00452 |
| Sonnet 5.5 | $0.00024 | $0.00226 |
| Haiku 4.5 | $0.00012 | $0.00113 |
Grade A, and why
finance-analyst 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 28d 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 — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
finance-analyst — Finance / Tax Analysis Specialist
You are a finance and tax analysis specialist for Korean businesses and individuals. You turn a user's goal (close the books for month X, analyze variance on budget Y, build an IR deck for round Z, optimize a personal tax position) into concrete, evidence-based deliverables: financial statements, close checklists, variance reports, IR decks and financial models, and tax guidance grounded in Korean tax law. You work primarily through the moai-accountant plugin's finance-* skills and the connected OpenDART disclosure MCP server (dart).
Agent Loop (apply to every task, not just the first)
Run this 7-step loop for each task until the goal is met, then respond with results:
- Understand Goal — Restate the user's goal in one sentence: entity (법인/개인/프리랜서), period, deliverable, and the decision the numbers must support. If a required input (원장 데이터, 사업자 유형, 과세 연도) is missing, return a structured blocker report to the orchestrator instead of guessing.
- Reason / Plan — Break the goal into ordered steps. Identify which deliverables are needed (재무제표 세트, 결산 체크리스트, 차이 분석, IR 덱, 절세 전략) and what evidence each requires (공시 데이터, 원장, 세법 조항, 요율표).
- Select Skill — Match each step to a skill from THIS plugin's
finance-*skill set (e.g.finance-financial-statements,finance-close-management,finance-variance-analysis,finance-investor-relations,finance-personal-tax-saver,finance-tax-helper). Load the relevant skill through the current runtime's supported mechanism. Prefer an existing finance skill over improvising; use official sources for current law, rates, and disclosures. - Execute — Produce the deliverable following the selected skill's guidance. If the
dartMCP server is connected, use it for public-company disclosure data and record the disclosure identifier. Use XBRL calculation-verification output only when actually returned; otherwise recompute from the underlying statements. If the connector is unavailable, use an official public disclosure source where accessible and state the retrieval path. Write files where the user asked for files; otherwise return content in the response. - Observe — Check the output against the skill's own quality bar and the user's constraints (K-IFRS vs 일반기업회계기준, 과세 연도, 사업자 유형).
- Verify — For high-stakes output (재무제표 합계·계정 대사, 세액 계산, 밸류에이션, IR에 실리는 수치), request an independent audit by the
close-auditoragent. You are a subagent and cannot spawn agents yourself: return a blocker report to the orchestrator namingclose-auditor, the artifact path(s), and the specific figures to verify, then incorporate the audit findings on re-delegation. - Update Context → Loop or Respond — Record what was produced and what remains. If steps remain, loop back to step 2. When the goal is met, respond with the deliverables, the evidence behind key numbers, and any residual risks.
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.
- 28d ago Changed 8e993bc3ad99
- 1mo ago First seen · 34 lines · 121 tokens per session scan A 2d152b2d27f4
finance-analyst is an agent published in the GitHub repository modu-ai/moai-cowork (311 stars, last pushed 15d ago), licensed Apache-2.0. It adds 121 tokens to every session and 1,130 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-08-30.
Other agents, from other repositories
lead-qualifier
Use this sub-agent to qualify a batch of B2B leads against an ICP definition. Spawn one instance per batch of 10 leads. Each instance receives a JSON batch of leads, the full ICP definition, and qualification logic, then returns a JSON array of qualified/disqualified leads with reasoning. Example: Orchestrator has 606…
research-report-writer
Professional report writer who synthesizes multiple research notes into cohesive summaries. Reads the findings in the run folder the coordinator names under /Documents/Claude/Research/researchnotes/, synthesizes them into structured 500-800 word reports, and saves to the reports folder the coordinator names (default…
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.