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 KCNyu/clawock --skill earnings-reviewgit clone --depth 1 https://github.com/KCNyu/clawockWrote 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/kcnyu/clawock/earnings-review)<a href="https://agentmods.dev/skills/kcnyu/clawock/earnings-review"><img src="https://agentmods.dev/badge/skills/kcnyu/clawock/earnings-review/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/kcnyu/clawock/earnings-review"><img src="https://agentmods.dev/badge/skills/kcnyu/clawock/earnings-review.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 | $0.00098 | $0.01191 |
| Opus 5 | $0.00049 | $0.00596 |
| Sonnet 5 | $0.00020 | $0.00238 |
| Haiku 4.5 | $0.00010 | $0.00119 |
Grade A, and why
earnings-review 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 11d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Earnings Review
Event-driven, never scheduled. Run this when an issuer reports, when a commitment comes due, or before a thesis review that needs first-party numbers. It is not part of any cron path.
The output is not a report. It is memory/earnings/<TICKER>/<period>.json, and the
Markdown you write afterwards is a rendering of that file.
What the code owns and what you own
Owned by clawock earnings |
Owned by you |
|---|---|
Source grade A/B/C and whether footnote claims are allowed |
Reading the filing and paraphrasing what it says |
| Cash conversion, FCF, working-capital gaps, dilution, SBC share, margins | Choosing which segments and footnotes matter |
| Guidance beat / inline / miss | Recording the commitment and its measurable target |
Promise roll-forward to met / partial / missed / not_due / unverifiable |
Locating the document that proves the result |
| The release gate over the provenance manifest | Deciding whether the period changes the thesis |
Never assert a computed number in prose. Run the script and quote its output.
Step 1 — collect first-party documents
Source order is not negotiable:
- US — SEC filing (10-K/10-Q/8-K) or issuer IR first;
clawock filingssupplies the structured XBRL numbers used to verify them. - HK — HKEX announcement or issuer IR first;
clawock fundamentals(Eastmoney) is a secondary structured source, never a substitute for a footnote. - A third-party summary may only fill a gap, and it lowers the grade.
Record each document once in documents[] with its source_class, a stable
locator, retrieved_at, and whether it covers_period. Store a short paraphrase
and the locator — never long transcript passages.
Grades are mechanical: A needs a covering primary document plus a structured
dataset; B has the dataset but no covering primary document; C is
third-party only. B/C disable every footnote claim, and the validator enforces
that. A low grade describes the sources, not the company.
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.
- 11d ago First seen · 110 lines · 98 tokens per session scan A 1b3370161cad
earnings-review is a skill published in the GitHub repository KCNyu/clawock (14 stars, last pushed yesterday), licensed MIT. It adds 98 tokens to every session and 1,191 once invoked, about $0.0005 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
tushare
A Python interface to Tushare, a financial-data service providing market, company, fund, futures, and other finance-related data. It shows how to authenticate and query the service into pandas tables.
financial-expense-automation
An expense-receipt workflow that reads PDF and image attachments, extracts their details, checks whether they are valid expense receipts, and records them in Feishu Bitable, a cloud table service.
credit-analysis
A framework for analysing bonds and other fixed-income investments, including issuer credit quality, interest-rate sensitivity, credit spreads, and default risk. A credit rating estimates how likely an issuer or specific bond is to repay its debt.
crypto-monitor
A scheduled cryptocurrency price checker that uses CoinGecko, a service providing market data. It tracks Bitcoin, Ethereum, and Litecoin in US dollars and Chinese yuan, including their change over the past 24 hours.
vibe-trading
Professional finance research toolkit — backtesting (7 engines + benchmark comparison panel), factor analysis, Alpha Zoo (452 pre-built alphas across qlib158/alpha101/gtja191/academic), options pricing, 79 finance skills, 29 multi-agent swarm teams, Trade Journal analyzer, and Shadow Account (extract → backtest →…
quant-statistics
Quantitative statistical methods: ADF unit-root / cointegration tests, GARCH volatility modeling, regression diagnostics (heteroskedasticity / autocorrelation), Bootstrap, and hypothesis testing.