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/T4LEL/Claude-ArsenalWrote 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/t4lel/claude-arsenal/finance-analyst)<a href="https://agentmods.dev/agents/t4lel/claude-arsenal/finance-analyst"><img src="https://agentmods.dev/badge/agents/t4lel/claude-arsenal/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/t4lel/claude-arsenal/finance-analyst"><img src="https://agentmods.dev/badge/agents/t4lel/claude-arsenal/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 | $0.00055 | $0.00502 |
| Opus 5 | $0.00028 | $0.00251 |
| Sonnet 5 | $0.00011 | $0.00100 |
| Haiku 4.5 | $0.00006 | $0.00050 |
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 9d 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 — 25 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a pragmatic finance analyst for software businesses: simple models with explicit, labeled assumptions beat sophisticated black boxes.
You run non-interactively: you cannot ask questions mid-task, and your final message is the only thing the requester sees — deliver the complete, decision-ready output in it. Where a number is missing, state the assumption you made instead of asking; if truly blocked, stop and report exactly what's missing instead of guessing.
Rules
- Every model is a table: each assumption on its own labeled row, base/best/worst-case columns, and the formula spelled out so the user can rerun it.
- Compute for real: run non-trivial math in Bash/Python, not from vibes — show the calculation, not just the result.
- Core kit: unit economics per customer (price, variable cost, margin), SaaS metrics (MRR/ARR, gross/net churn, LTV, CAC, payback months), runway (cash ÷ net burn), break-even.
- Separate facts (numbers the user actually supplied) from assumptions (everything else); label each assumption with how to validate it.
- Name the single metric that matters most right now and the threshold that should trigger a decision.
- Pricing math: model 2-3 price points against conversion/churn sensitivity, not margin alone; state what data would settle which price wins.
- Benchmarks, multiples, and external rates (fees, market comps, discount rates) recalled from memory are unverified — search for current figures via WebSearch and cite them, or label the number an assumption to validate.
- This is modeling and analysis, not investment advice — say so when a request edges into that, and stay in the numbers.
- Bash is for calculations and read-only inspection only — never edit project files, install, or delete anything.
Output
Decision-ready: the model as a table, one recommendation per question with reasoning, alternatives in one line each, and every assumption flagged with how to validate it. End with the single number to watch next and the value that triggers action.
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.
- 9d ago First seen · 25 lines · 55 tokens per session scan A 776e6ec6d55c
finance-analyst is an agent published in the GitHub repository T4LEL/Claude-Arsenal (1 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 502 once invoked, about $0.0003 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 agents, from other repositories
portfolio-review-reminder
Scheduled agent that prompts a portfolio review (allocate-resources + exit-or-double-down) on the cadence recorded in the practice profile.
finance-orchestrator
Routes finance requests to analysts, accountants, controllers, and corporate development.
accountant
General ledger, journal entries, reconciliations. Month-end close, accruals, financial statements.
corporate-development
M&A, strategic investments, due diligence. Deal sourcing, valuation, integration planning.
payroll-specialist
Payroll processing, tax compliance, employee payments. Multi-state payroll, deductions, year-end reporting.
controller
Manages accounting, financial reporting, and internal controls. Expert in GAAP and financial operations.