china-tax

china-tax is a skill for Claude Code from Esonhugh/ibkr-trade-analyzer. It costs 120 tokens per session (1,578 once invoked), scanned A, original, MIT.

Reference instructions for organizing overseas brokerage records for China tax residents, including dividend records, U.S. withholding, exchange-rate evidence, and foreign tax credits. They provide informational estimates and planning guidance, not a final tax decision.

In plain words
What is it for?
Reviewing IBKR data, Form 1042-S records, dividend withholding, foreign tax credit evidence, currency conversions, and year-end filing preparation.
Why use it?
Brokerage forms and foreign-income records can be difficult to reconcile, and tax rules depend on the relevant year and the person’s circumstances.

Skill for Claude Code

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

Part of the ibkr-trade-analyzer plugin — 2 skills, 7 commands, 1 MCP server shipped together

Good fit Reviewing IBKR data, Form 1042-S records, dividend withholding, foreign tax credit evidence, currency conversions, and year-end filing preparation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/esonhugh/ibkr-trade-analyzer/china-tax
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.

Any agent
npx skills add Esonhugh/ibkr-trade-analyzer --skill china-tax
Clone the repo
git clone --depth 1 https://github.com/Esonhugh/ibkr-trade-analyzer

Made for: Claude Code.

Or install ibkr-trade-analyzer, the plugin that ships this one along with the rest of its 2 skills, 7 commands, 1 MCP server.

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-tax

README.md
[![agentmods](https://agentmods.dev/badge/skills/esonhugh/ibkr-trade-analyzer/china-tax/github.svg)](https://agentmods.dev/skills/esonhugh/ibkr-trade-analyzer/china-tax)
Your own site
<a href="https://agentmods.dev/skills/esonhugh/ibkr-trade-analyzer/china-tax"><img src="https://agentmods.dev/badge/skills/esonhugh/ibkr-trade-analyzer/china-tax/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-tax

Your own site · 80×15
<a href="https://agentmods.dev/skills/esonhugh/ibkr-trade-analyzer/china-tax"><img src="https://agentmods.dev/badge/skills/esonhugh/ibkr-trade-analyzer/china-tax.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 120 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,578 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 $0.00120 $0.01578
Opus 5 $0.00060 $0.00789
Sonnet 5 $0.00024 $0.00316
Haiku 4.5 $0.00012 $0.00158

Measured 12d ago against content hash 671e3dbc11b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

china-tax 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/china_tax_self_check.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/china-tax/SKILL.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

China Tax Reference and Planning for Overseas Brokerage Data

Prepare official-source evidence reviews, informational annual China individual income tax estimates, and year-end planning reviews for China tax residents using IBKR/Flex data first. Focus on overseas income management, foreign tax credit, treaty withholding sanity checks, RMB conversion assumptions, filing evidence, and tax-planning review items.

Safety Boundary

  • Provide informational estimates, evidence organization, and planning checklists only; never state a final tax payable amount or filing position as definitive.
  • Recommend confirmation with a qualified tax professional or competent tax authority before filing.
  • Do not determine China tax residency conclusively; use only explicit user-provided residency assumptions and mark them for review.
  • Recheck official sources and effective dates for the relevant tax year before relying on rules or forms.
  • Treat default rates such as 20% for dividend estimates as configurable assumptions, not final law application.
  • Do not invent missing 1042-S amounts, brokerage gross income, withholding tax, country allocation, income category, cost basis, realized gains, or RMB exchange rates.
  • Keep U.S. treaty withholding checks separate from China IIT calculation.
  • Mark ambiguous or unsupported tax treatment as review_required.
  • Do not provide tax evasion, concealment, false reporting, or illegal avoidance advice.

Reference First

Consult references/official-tax-rules-and-implementation-plan.md before answering detailed calculation, treaty, overseas-income management, CRS, foreign-tax-credit, or implementation questions. It contains official-source links, rule summaries, formulas, output tables, a web-app pattern review, and a staged implementation plan.

Current Capability

Handle these tasks as research, design, evidence preparation, and manual estimate workflows:

  1. Explain how Form 1042-S, brokerage data, China resident IIT, treaty withholding, and foreign tax credit fit together.
  2. Build evidence tables from loaded IBKR Flex cash transactions.
  3. Draft annual filing calculation workflows for dividends, withholding tax, opt-in STK realized-gain evidence, and later-phase 1042-S reconciliation.
  4. Produce year-end planning reviews that identify evidence gaps, possible withholding-rate issues, tax-lot/cost-basis issues, currency assumptions, and timing considerations.
  5. Produce implementation plans for deterministic code and tests.

Read the full file on GitHub · 105 lines

Files

What ships with it

2 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.

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 · 105 lines · 120 tokens per session scan A 671e3dbc11b3

Subscribe to this mod's changes

china-tax is a skill published in the GitHub repository Esonhugh/ibkr-trade-analyzer (18 stars, last pushed 3mo ago), licensed MIT. It adds 120 tokens to every session and 1,578 once invoked, about $0.0006 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 skills, from other repositories

expense-review-policy

Review invoices and contracts against accounts-payable policy before human approval.

openai/openai-cookbook · 17 tokens

audit-support

Support SOX 404 compliance with control testing methodology, sample selection, and documentation standards. Use when generating testing workpapers, selecting audit samples, classifying control deficiencies, or preparing for internal or external audits.

anthropics/knowledge-work-plugins · 45 tokens

kyc-doc-parse

Parse an investor or client onboarding packet into structured KYC fields — identity, ownership, control, source of funds, and document inventory. Use as the first step of KYC screening; output feeds the rules engine.

anthropics/financial-services · 49 tokens

fiscaliste

Fiscaliste IA pour la fiscalité personnelle des particuliers français : optimisation et déclaration de l'impôt sur le revenu, IFI, revenus du capital, revenus fonciers, equity salarial, crypto-actifs et PER. Couvre le calcul de l'IR (barème, quotient familial, décote, PAS, CEHR, revenus exceptionnels), la déclaration…

romainsimon/paperasse · 302 tokens

regulatory-analysis

Analyzes documents and processes against FINRA, SEC, Federal Reserve, and CFPB regulatory frameworks. Identifies compliance gaps, classifies findings by severity, and recommends remediation. Use when performing compliance audits, regulatory reviews, gap analyses, or verifying policy adherence to financial regulations.

open-gitagent/opengap · 59 tokens

subcontractor-payment-tracker

Track subcontractor payments, lien waivers, and compliance. Manage payment schedules and documentation.

datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction · 25 tokens