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 defeat-beta/defeatbeta-api --skill defeatbeta-earnings-key-datagit clone --depth 1 https://github.com/defeat-beta/defeatbeta-apiWrote 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/defeat-beta/defeatbeta-api/defeatbeta-earnings-key-data)<a href="https://agentmods.dev/skills/defeat-beta/defeatbeta-api/defeatbeta-earnings-key-data"><img src="https://agentmods.dev/badge/skills/defeat-beta/defeatbeta-api/defeatbeta-earnings-key-data/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/defeat-beta/defeatbeta-api/defeatbeta-earnings-key-data"><img src="https://agentmods.dev/badge/skills/defeat-beta/defeatbeta-api/defeatbeta-earnings-key-data.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00138 | $0.01342 |
| Opus 5 | $0.00069 | $0.00671 |
| Sonnet 5 | $0.00028 | $0.00268 |
| Haiku 4.5 | $0.00014 | $0.00134 |
Grade A, and why
defeatbeta-earnings-key-data 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DefeatBeta Earnings Key Data
Extract financial facts from one earnings-call transcript. Preserve the selected template's schema and output format instead of merging all transcript analysis into a generic report.
Route the Request
Select the narrowest matching template:
- Template 11 - Extract Key Financial Data from Earnings Call
- Use for broad requests such as "latest earnings call," "key financial data," "what did the company report," or "results and guidance."
- Extract current-quarter results, next-quarter guidance, and full-fiscal-year guidance.
- Template 12 - Analyze Financial Metric Changes from Earnings Call
- Use when the user asks what changed QoQ, sequentially, or YoY.
- Extract factual completed-period comparison sentences only.
- Template 13 - Analyze Financial Metric Forecasts from Earnings Call
- Use when the user asks for forecasts, numerical outlook, targets, expectations, guidance sentences, or management attitude toward those forecasts.
- Extract numerical forward-looking sentences and classify attitude.
If the user explicitly requests all three analyses, run the templates separately and present each template's own output. Do not combine their records into one generic table.
Select the Output Medium
- Use Markdown by default.
- Create DOCX, PDF, or both only when the user explicitly requests a file or formal report.
- For a document artifact, read references/report-layout.md and preserve the selected template's tables, summaries, and evidence.
- Keep the validated extraction identical across chat, DOCX, and PDF outputs.
Resolve the Company and Fiscal Period
- Require an unambiguous public-company ticker. Ask for the ticker when a company name maps to multiple securities or share classes.
- Call
get_stock_earning_call_transcripts_list(symbol)before retrieving a transcript. - For an explicitly requested period, match the exact returned
fiscal_yearandfiscal_quarter. Treat fiscal periods as company-defined rather than calendar-defined. - For "latest," select the entry with the latest valid
report_date. Do not assume the first array element is latest. If dates tie or are missing, use the highest fiscal year and quarter and disclose the fallback. - Call
get_stock_earning_call_transcript(symbol, fiscal_year, fiscal_quarter)with the selected period. - Stop and report the gap when the transcript list is empty, the requested period is unavailable, or the returned
paragraphsarray is empty.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 99 lines · 138 tokens per session scan A 40feac72f860
defeatbeta-earnings-key-data is a skill published in the GitHub repository defeat-beta/defeatbeta-api (746 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 138 tokens to every session and 1,342 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 2026-08-30.
Other skills, from other repositories
eastmoney-stock-valuation
A lookup for daily valuation figures on Chinese A-share stocks, such as price-to-earnings, price-to-book, market value and closing price. It can return one stock, a date range, one trading day, or the whole market.
stock-holder-ften
A stock-market lookup for the ten largest holders of a company's freely tradable shares in Chinese A-shares. It can show historical reports for one stock or the latest report across the market.
stock-share-chg
A record of A-share shareholder increases and decreases in their holdings. It can show the history for one stock or the latest reported change across the market.
ftshare-market-data
A collection of tools for retrieving financial and economic data from Chinese, Hong Kong, and United States markets. It covers items such as stock lists, prices, charts, company financial statements, funds, indexes, bonds, news, and macroeconomic data.
cb-base-data
Basic information about one convertible bond, a bond that may be exchanged for shares. It includes items such as the bond name, related stock, conversion price and value, maturity date and issue size.
eastmoney-market-valuation
A tool for retrieving daily valuation data for major Chinese A-share market indexes, such as price-to-earnings ratios, market value, and closing levels.