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 damianvtran/local-operator --skill financial-analysisgit clone --depth 1 https://github.com/damianvtran/local-operatorWrote 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/damianvtran/local-operator/financial-analysis)<a href="https://agentmods.dev/skills/damianvtran/local-operator/financial-analysis"><img src="https://agentmods.dev/badge/skills/damianvtran/local-operator/financial-analysis/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/damianvtran/local-operator/financial-analysis"><img src="https://agentmods.dev/badge/skills/damianvtran/local-operator/financial-analysis.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 | $0.00038 | $0.00554 |
| Opus 5.5 | $0.00015 | $0.00222 |
| Sonnet 5.5 | $0.00008 | $0.00111 |
| Haiku 4.5 | $0.00004 | $0.00055 |
Grade A, and why
financial-analysis 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 5d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Financial analysis
Money numbers get audited. Build every figure to survive the audit: labelled, period-aligned, reconciled.
Periods and calendars
- State the fiscal calendar in use: fiscal years often do not match calendar years; name the convention when it matters.
- Align periods before comparing. An 11-month period against a 12-month one, or a quarter against a year, is a units error in time. Annualised figures say "annualised".
- Point-in-time (balance sheet, headcount) versus period figures (revenue, cash flow): never blend without saying so.
Units and currencies
- Label every figure with both currency (USD, EUR) and scale (actual, thousands, millions). A number missing either is incomplete.
- Converted figures state the rate and its date: the same amount converts differently across a year.
- Never mix currencies inside a total. If a presentation currency is used, say what was converted and at what rate.
Reconcile against sources
- Tie every total to its source (statement, ledger, export); tie parts to whole: segments sum to the total, cash movement equals the balance delta.
- If it does not reconcile, the finding IS the reconciliation: report "off by X against source Y" rather than a workaround.
- For anything material, cross-check a second way (bottom-up against top-down).
Magnitude and sanity
- Compare against reference points: prior period, budget, per-employee, per-customer, margins. Name which.
- A jump of 10x or more is a unit, period, or scope error until positively explained.
- Check signs and flows: revenue positive and costs negative under the stated convention; cash direction matches the story.
Show assumptions
- Every assumption lives in the output: growth rate, churn, discount rate, each with its source. "Assumed 20% growth from plan X" beats a bare projection.
- Scenarios are labelled (base, upside, downside) with the changed variable named.
Rounding
- Round once, at the end; keep consistent precision throughout so rounded intermediates do not drift the total.
- State precision: approximately for estimates, exact only where sourced.
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.
- 5d ago First seen · 51 lines · 38 tokens per session scan A e4b003a0f348
financial-analysis is a skill published in the GitHub repository damianvtran/local-operator (218 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 554 once invoked, about $0.0002 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 2026-10-11.
Other skills, from other repositories
building-agents
Use when building or restructuring an LLM agent — provider adapter, tool calling, structured output, RAG, agent loop, eval gate, cost routing, tracing, MCP server — model-agnostic across OpenAI/Anthropic/Gemini/OSS so a model swap is a config change. NOT vector-store SQL alone (that is postgresdb) or service…
agent-eval
Use when measuring whether an LLM or agent system actually got better and gating merges on it: golden sets, fixing an inflated LLM-as-judge, scoring RAG (faithfulness, contextual recall) or agent trajectories (tool correctness, completion), or picking an eval framework. NOT building the agent loop, tools or RAG…
polymarket
Query Polymarket prediction market data — search markets, get prices, orderbooks, and price history. Read-only via public REST APIs, no API key needed.
risk-scoring
Score how concentrated and risky a portfolio is on a 0-100 scale from its position weights. Use when the user asks how risky their portfolio is, whether it is too concentrated, or for a diversification check.
valuation
Estimate whether a stock looks cheap or expensive using a price-to-earnings (P/E) based fair-value method. Use when the user asks if a stock is over- or under-valued, or for a fair-value / target price.
cost-efficiency-analyzer
Analyzes cost structure, cost efficiency, and expense management from P&L data. Use when the user asks about costs, expenses, COGS, operating expenses, cost ratios, cost control, spending efficiency, margin compression from cost side, or wants to understand where money is going. Also use for "are we spending too…