tax-situation-analyzer

tax-situation-analyzer is an agent for coding agents from austinfox/claude-plugins. It costs 22 tokens per session (3,520 once invoked), scanned C, original, MIT.

An agent for analyzing U.S. tax situations, including state, international, and Sweden-related issues when relevant.

In plain words
What is it for?
Building a tax fact model, researching applicable authorities, and producing a ranked report of tax issues and possible actions.
Why use it?
It organizes taxpayer facts and identifies compliance, treaty, and planning questions that may otherwise be missed.

Agent

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the tax-advisor plugin — 1 skill, 1 command, 4 agents shipped together

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.

agentmods
npx agentmods add agents/austinfox/claude-plugins/tax-situation-analyzer
Clone the repo
git clone --depth 1 https://github.com/austinfox/claude-plugins

Or install tax-advisor, the plugin that ships this one along with the rest of its 1 skill, 1 command, 4 agents.

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 tax-situation-analyzer

README.md
[![agentmods](https://agentmods.dev/badge/agents/austinfox/claude-plugins/tax-situation-analyzer.svg)](https://agentmods.dev/agents/austinfox/claude-plugins/tax-situation-analyzer)
Your own site
<a href="https://agentmods.dev/agents/austinfox/claude-plugins/tax-situation-analyzer"><img src="https://agentmods.dev/badge/agents/austinfox/claude-plugins/tax-situation-analyzer.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,520 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. Scan, not verified.
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 $0.00022 $0.03520
Opus 5 $0.00011 $0.01760
Sonnet 5 $0.00004 $0.00704
Haiku 4.5 $0.00002 $0.00352

Measured 5d ago against content hash 33cbf9dd24e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade C, and why

tax-situation-analyzer scanned grade C with 2 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 5d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

If bun is not installed, tell the user to install it: `curl -fsSL https://bun.sh/install | bash`

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

If bun is not installed, tell the user to install it: `curl -fsSL https://bun.sh/install | bash`
plugins/tax-advisor/agents/tax-situation-analyzer.md · 229 lines

How it starts

The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tax Situation Analyzer

You are a comprehensive U.S. tax situation analyst. Build a fact-supported taxpayer model, then produce an actionable report ranked by net dollar impact, implementation burden, and authority. Include international compliance and treaty issues whenever the facts involve foreign residence, income, tax, accounts, assets, pensions, entities, or trusts.

Step 1: Verify Tax Knowledge Base

Before beginning, confirm the tax knowledge base is bootstrapped and current.

  • Check for the file ${CLAUDE_PLUGIN_ROOT}/tax-knowledge/.last-updated
  • If the file is missing or older than 30 days, run the bootstrap automatically:
    cd "${CLAUDE_PLUGIN_ROOT}/scripts" && bun install && bun run bootstrap-knowledge.ts
    
    If bun is not installed, tell the user to install it: curl -fsSL https://bun.sh/install | bash
  • Do not block the analysis if bootstrap fails. Use official IRS, Treasury, FinCEN, SSA, state, or foreign tax-authority sources and identify any unresolved source gap.

Step 2: Build the fact base

Parse the user's goal and tax year first. Load a profile only if the user selects it, and follow ${CLAUDE_PLUGIN_ROOT}/skills/tax-advisor/references/profiles-and-privacy.md. Offer document review when it would reduce uncertainty; do not require an upload before beginning.

If documents are provided:

  1. Read the relevant files and identify document type, taxpayer, tax year, original/amended status, currency, and completeness.
  2. Extract supported facts, including income, withholding, contributions, carryovers, deductions, investments, and jurisdiction.
  3. For foreign documents, also capture original currency, payment/withholding dates, whether tax is preliminary or final, refunds/additional assessments, and the U.S. form/category to which each item may relate.
  4. Present a structured extraction summary and list conflicts or ambiguities. Do not infer filing status solely from a mailing address or overwrite a profile without consent.

Interview only for material gaps; skip facts already established.

Read the full file on GitHub · 229 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. 5d ago First seen · 229 lines · 22 tokens per session scan C 33cbf9dd24e8

Subscribe to this mod's changes

tax-situation-analyzer is an agent published in the GitHub repository austinfox/claude-plugins (4 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 3,520 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

regulated-reviewer

Regulated-industry specialist pre-implementation reviewer for fintech / regulated archetypes. Outputs threat model TM-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.

avelikiy/great_cto · 42 tokens

tax-reviewer

Tax preparation / filing specialist pre-implementation reviewer for the fintech archetype. Outputs threat model TM-tax-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.

avelikiy/great_cto · 42 tokens

rcm-reviewer

Healthcare Revenue Cycle Management (RCM) / medical-billing specialist pre-implementation reviewer for the healthcare archetype. Outputs threat model TM-rcm-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.

avelikiy/great_cto · 53 tokens

tax-optimizer

Use this agent when the user asks about tax benefits of real estate, depreciation strategies, 1031 exchanges, cost segregation, entity structure selection, or tax optimization. Trigger when the user needs tax strategy analysis for property investments. Also invoked by the /exit-analysis command for sale-vs-exchange…

Aznatkoiny/zAI-Skills · 276 tokens

fintech-pm-reviewer

PM-side reviewer for fintech initiatives — money movement, lending, payments, insurance, neobank, BNPL. Stress-tests compliance scope, customer-money handling, fraud loss vs growth trade-off, KYC/AML readiness, jurisdiction strategy. Pairs with engineering's lending-credit-reviewer + pci-reviewer +…

VandanaAjayDubey111/great-pm · 76 tokens

healthcare-admin

Use when working on healthcare administration tasks including revenue cycle management, HIPAA/compliance auditing, medical coding (ICD-10, CPT, DRGs), CMS cost reports, payer contract analysis, quality improvement, clinical operations, health IT/interoperability, population health, and pharmacy benefits.

alexmmatos/essentials-claude-code · 62 tokens