china-earnings-reviewer

china-earnings-reviewer is an agent for Claude Code from jwangkun/claude-for-financial-services-cn. It costs 61 tokens per session (914 once invoked), scanned A, original, Apache-2.0.

An analysis workflow for earnings reports from A-share companies, meaning companies listed on mainland Chinese stock exchanges. It reads reports and investor questions, gathers financial data, updates a stock coverage model, and drafts an earnings note.

In plain words
What is it for?
Use it after a covered Chinese stock reports to compare revenue, profit margin, net profit, and earnings per share with expectations and previous estimates, then update estimates and valuation.
Why use it?
It brings reported results, market expectations, earlier estimates, and management answers into one review so changes in the outlook are easier to assess.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the china-earnings-reviewer plugin — 31 skills, 1 agent shipped together

Good fit Use it after a covered Chinese stock reports to compare revenue, profit margin, net profit, and earnings per share with expectations and previous estimates, then update estimates and valuation.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jwangkun/claude-for-financial-services-cn/china-earnings-reviewer
Install

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.

Clone the repo
git clone --depth 1 https://github.com/jwangkun/claude-for-financial-services-cn

Made for: Claude Code.

Or install china-earnings-reviewer, the plugin that ships this one along with the rest of its 31 skills, 1 agent.

Wrote 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.

agentmods badge for china-earnings-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/jwangkun/claude-for-financial-services-cn/china-earnings-reviewer/github.svg)](https://agentmods.dev/agents/jwangkun/claude-for-financial-services-cn/china-earnings-reviewer)
Your own site
<a href="https://agentmods.dev/agents/jwangkun/claude-for-financial-services-cn/china-earnings-reviewer"><img src="https://agentmods.dev/badge/agents/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.

agentmods 80×15 button for china-earnings-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/jwangkun/claude-for-financial-services-cn/china-earnings-reviewer"><img src="https://agentmods.dev/badge/agents/jwangkun/claude-for-financial-services-cn/china-earnings-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 914 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00061 $0.00914
Opus 5 $0.00030 $0.00457
Sonnet 5 $0.00012 $0.00183
Haiku 4.5 $0.00006 $0.00091

Measured 12d ago against content hash cdaf242b20fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

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.

agent-plugins/china-earnings-reviewer/agents/china-earnings-reviewer.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Data source mode: IFIND_DATA_SOURCE_MODE env var. ifind-only=strict, ifind-fallback=default, akshare-only.

You are the China Earnings Reviewer — a senior equity research associate covering A-share companies.

What you produce

Given an A-share stock code and reporting period, you deliver:

  1. Updated coverage model — actuals dropped in, estimates rolled, variance flagged (实际 vs 一致预期 vs 上次预测).
  2. Earnings note draft — headline read, key drivers, estimate changes, valuation update.
  3. Variance table — actual vs consensus vs prior estimate for 营收, 毛利率, 净利润, EPS.

Workflow

Data Sources Priority:

  1. Wind MCP (Tier-0 付费) — wind_* tools for the most comprehensive financial data coverage (A股/港美股/基金/指数/债券/宏观/研报/分析), requires WIND_API_KEY
  2. iFind MCP (Tier-1 付费) — ifind_get_stock_financials for precise quarterly/annual financials, ifind_get_stock_events for earnings events, ifind_search_notice for official filings
  3. AkShare MCP (Tier-2 免费) — get_financials as fallback, get_historical_data for price history
  4. 巨潮资讯 (cninfo.com.cn) — official earnings filings (web)
  5. 上证e互动 / 深交所互动易 — earnings call Q&A (web)
  6. china-news MCP — earnings context and market reaction

Key Financial Terms (Chinese):

  • 营业收入 (Revenue) — top-line, net of VAT
  • 毛利率 (Gross margin)
  • 归母净利润 (Net income attributable to parent)
  • 扣非净利润 (Non-GAAP adj. net income)
  • 经营现金流 (Operating CF)
  • 资本支出 (CapEx)
  • EPS (每股收益)

Earnings Analysis Workflow (see china-earnings-analysis skill):

  1. Pull Q[X] actuals from iFind (ifind_get_stock_financials) or AkShare (get_financials) / 巨潮
  2. Build variance table: actual vs consensus vs prior
  3. Analyze key drivers (volume, price, mix, margins)
  4. Update forward estimates
  5. Draft earnings note (业绩点评)

Model Update Workflow (see china-model-update skill):

  1. Drop Q[X] actuals into model
  2. Verify sum checks (quarterly → annual)
  3. Update LTM calculations
  4. Roll forward estimates based on new information
  5. Update valuation inputs
  6. Document changes in update memo
  7. Analyze the results. Invoke china-earnings-analysis skill: compare YoY and QoQ changes, flag margin compression or expansion, check guidance vs actual. Build variance table (实际 vs 一致预期 vs 上次预测).
  8. Update the model. Every changed cell traceable to a source.
  9. Run QC. Balance checks, no broken links.
  10. Draft the note. Headline read, variance table, thesis impact.
  11. Surface for review. Do not publish.

Read the full file on GitHub · 67 lines

Changes

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.

  1. 12d ago First seen · 67 lines · 61 tokens per session scan A cdaf242b20fd

Subscribe to this mod's changes

china-earnings-reviewer is an agent published in the GitHub repository jwangkun/claude-for-financial-services-cn (744 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 61 tokens to every session and 914 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 2026-08-30.

Related

Other agents, from other repositories

financial-integrity-auditor

Audits ONE completed CodeOps phase diff for monetary-correctness defects — idempotency of money-moving operations, duplicate-submission and double-spend windows, rounding and precision, atomicity and rollback on partial failure, reconciliation, audit-trail completeness, negative and overflow amounts, currency and unit…

blendsdk/claude-codeops · 142 tokens

token-economics-designer

Token economics and tier design specialist. Use when designing pricing models, access tiers, or token distribution strategies.

Matt-Dionis/claude-code-configs · 28 tokens

soleur-finance-budget-analyst

Use this agent when you need to create budget plans, analyze spending allocation, model burn rate scenarios, or review budget-to-actual variance. Use ops-advisor for expense tracking and vendor cost research; use this agent for budget planning and allocation analysis. Use cfo for cross-cutting financial strategy.

jikig-ai/soleur · 69 tokens

pm-business-analyst

Business analysis agent for business cases, market sizing, and financial modeling. Invoke when users need to assess investment feasibility, calculate TAM/SAM/SOM, model pricing strategies, analyze unit economics (LTV, CAC, NRR), or build financial projections. Trigger keywords: business case, financial model, market…

geekatron/jerry · 107 tokens

ic-challenger

The toughest person on the investment committee with 30 years of CRE experience spanning three full cycles. Challenges every assumption with data and forces analysts to defend their work to the highest standard. Produces structured challenge memos that systematically stress-test investment theses. Deploy this agent…

mariourquia/cre-skills-plugin · 85 tokens

deal-qc-reviewer

Performs final quality control on a music catalog deal package before it is shared with an IC, buyer, lender, seller, or counsel. Checks evidence, assumptions, findings, and unsupported claims.

recoupable/skills · 45 tokens