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/jwangkun/claude-for-financial-services-cnWrote 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/plugins/jwangkun/claude-for-financial-services-cn/china-earnings-reviewer)<a href="https://agentmods.dev/plugins/jwangkun/claude-for-financial-services-cn/china-earnings-reviewer"><img src="https://agentmods.dev/badge/plugins/jwangkun/claude-for-financial-services-cn/china-earnings-reviewer/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/plugins/jwangkun/claude-for-financial-services-cn/china-earnings-reviewer"><img src="https://agentmods.dev/badge/plugins/jwangkun/claude-for-financial-services-cn/china-earnings-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
china-earnings-reviewer 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.
What it actually says
{
"name": "china-earnings-reviewer",
"version": "0.1.0",
"description": "A-share earnings analysis — model update, variance table, post-earnings note",
"author": { "name": "Anthropic FSI China" }
}
What it installs
The manifest is a name and a version. 31 skills, 1 agent travel with it, and installing the plugin installs all of them — 2,722 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill china-3-statement-model A 73 tokens
- Skill china-catalyst-calendar A 96 tokens
- Skill china-idea-generation A 96 tokens
- Skill china-lbo-model A 64 tokens
- Skill china-market-data A 101 tokens
- Skill china-sector-overview A 102 tokens
- Skill china-audit-xls A 81 tokens
- Skill china-clean-data-xls A 74 tokens
- Skill china-comps-analysis A 78 tokens
- Skill china-earnings-analysis A 108 tokens
- Skill china-earnings-preview A 108 tokens
- Skill china-ib-check-deck A 87 tokens
- Skill china-initiating-coverage A 100 tokens
- Skill china-model-update A 92 tokens
- Skill china-morning-note A 82 tokens
- Skill china-pptx-author A 145 tokens
- Skill china-skill-creator A 103 tokens
- Skill china-tax-loss-harvesting A 89 tokens
- Skill china-thesis-tracker A 98 tokens
- Skill china-xlsx-author A 77 tokens
- Skill china-accrual-schedule A 88 tokens
- Skill china-break-trace A 73 tokens
- Skill china-deal-screening A 83 tokens
- Skill china-deck-refresh A 77 tokens
- Skill china-gl-recon A 83 tokens
- Skill china-ppt-template-creator A 77 tokens
- Skill china-variance-commentary A 76 tokens
- Skill china-comps A 45 tokens
- Skill china-roll-forward A 71 tokens
- Skill china-dcf A 54 tokens
- Skill china-dcf-model A 80 tokens
- Agent china-earnings-reviewer A 61 tokens
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 · 7 lines scan A cdbe1e6259a3
china-earnings-reviewer is a plugin published in the GitHub repository jwangkun/claude-for-financial-services-cn (744 stars, last pushed 3mo ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
shinkoku
A Claude Code plugin for Japanese tax filing. It supports employees with side businesses, including business-income, blue-return, income-tax, and consumption-tax filings.
investor
Financial research MCP server — Yahoo Finance quotes, historical prices, options, market movers, earnings, fear & greed, and technical indicators.
secedgar-mcp-server
Query SEC EDGAR filings, XBRL financials, and company data through MCP. STDIO & Streamable HTTP.
bitbank-lab-mcp
Experimental MCP server for bitbank — botters lab community edition. Market data, technical analysis, charting, and Private API trading tools.
datarails-financeos
Datarails Finance OS integration - analyze financial data, detect anomalies, and generate insights.
comptabilite
Comptabilite, fiscalite, financement et epargne en France. Quatre roles : Comptable (/comptable) pour l entreprise ; Impots (/impots) pour le particulier ; Financement (/financement) pour l argent de l activite - banque et droit au compte, credit et rupture de credit, caution du dirigeant, tresorerie, mediation du…