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 sshh12/claude-plugins --skill freetaxusagit clone --depth 1 https://github.com/sshh12/claude-pluginsWrote 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/sshh12/claude-plugins/freetaxusa)<a href="https://agentmods.dev/skills/sshh12/claude-plugins/freetaxusa"><img src="https://agentmods.dev/badge/skills/sshh12/claude-plugins/freetaxusa/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/sshh12/claude-plugins/freetaxusa"><img src="https://agentmods.dev/badge/skills/sshh12/claude-plugins/freetaxusa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00055 | $0.01060 |
| Opus 5.5 | $0.00022 | $0.00424 |
| Sonnet 5.5 | $0.00011 | $0.00212 |
| Haiku 4.5 | $0.00006 | $0.00106 |
Grade A, and why
freetaxusa 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 1mo 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Disclaimers
- This skill is NOT affiliated with, endorsed by, or connected to FreeTaxUSA or TaxHawk Inc.
- This is NOT tax advice. This skill automates form filling based on user-provided documents.
- This skill will NEVER auto-submit a tax return. The user must review and submit manually.
- The user is solely responsible for the accuracy of their tax return.
- The agent's tax knowledge may be outdated or incomplete. Phase 3 fetches current-year rules to compensate, but always defer to IRS publications and FreeTaxUSA's built-in guidance over the agent's assumptions.
- Sensitive data (SSNs, bank account numbers, IP PINs) must be entered by the user directly into the browser — the agent must not handle these values.
Prerequisites
- Browser automation capability — brw skill strongly recommended (loaded in Phase 1); alternatives like Claude for Chrome, Playwright MCP, or Chrome DevTools MCP also work
- Node.js 18+
- A FreeTaxUSA account (free to create at freetaxusa.com)
- Tax documents (W-2s, 1099s, etc.)
Phase Overview
Phase 1: Setup & Consent
See references/PHASE-1-SETUP.md
- Explain risks of tax inaccuracy
- Load browser automation (brw skill preferred; detect alternatives if unavailable)
- Review data privacy implications
- Get explicit user consent
Phase 2: Document Discovery
See references/PHASE-2-DISCOVERY.md
- Set up secure working folder
- Collect and extract all tax documents
- Build consolidated document summary
- Front-load ALL questions before filing
- Generate tax outcome guesstimate
Phase 3: Tax Research
See references/PHASE-3-RESEARCH.md
- Fetch current tax brackets and rules
- Run life change questionnaire
- Flag complexity items needing professional help
- Build section-by-section filing plan
Phases 2-3 are iterative. The life change questionnaire or filing plan review may reveal missing documents or new questions. Loop back to Phase 2 as needed — request additional docs, re-extract, update the summary, and revise the filing plan. Do NOT proceed to Phase 4 until all documents are accounted for and the filing plan is approved.
What ships with it
9 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.
- references/BROWSER-TIPS.md 3.6 KB
- references/GOTCHAS.md 6.8 KB
- references/PHASE-1-SETUP.md 6.1 KB
- references/PHASE-2-DISCOVERY.md 7.5 KB
- references/PHASE-3-RESEARCH.md 5.7 KB
- references/PHASE-4-FILING.md 13 KB
- references/PHASE-5-REVIEW.md 5.3 KB
- scripts/extract-pdf.js 400 KB runs code
- scripts/pdf.worker.mjs 2291 KB runs code
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.
- 1mo ago First seen · 114 lines · 55 tokens per session scan A dc2db04cf717
freetaxusa is a skill published in the GitHub repository sshh12/claude-plugins (24 stars, last pushed 3mo ago), licensed MIT. It adds 55 tokens to every session and 1,060 once invoked, about $0.0002 per session on Opus 5.5. 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
x402
Set up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key. Two setups it works out up front — "just use it" (set up a wallet so you or Claude Code can run cloud browser tasks paid from the wallet — Claude writes and runs throwaway scripts, nothing…
american-airlines
Check American Airlines AAdvantage balance, elite status, and loyalty points via Patchright. Handles email 2FA with 6-box code entry. Uses persistent browser profiles to skip 2FA on subsequent runs.
find-my-bookings-and-balances
Uses your own email and browser connectors together to find booking confirmations and points balances, then saves them to Award Travel Finder. Use when the user asks to find, sync or set up all their trips and balances and an email connector (Gmail, Outlook, Apple Mail) or browser control (Claude in Chrome, computer…
Agentic Commerce Protocol (ACP)
Modular agentic commerce skill for implementing OpenAI & Stripe's Agentic Commerce Protocol. Enables AI agents to negotiate capabilities, initiate checkout sessions, handle secure Stripe Payment Token (SPT) delegation, and process fulfillment events.
obo
Control the user's real Chrome browser with their logged-in sessions, cookies, and extensions. Triggers include "open a website", "click a button", "fill a form", "take a screenshot", "check my email", "browse as me", or any task requiring the user's authenticated browser.
firecrawl-mcp
Auto-generated skill for firecrawl-mcp tools via OneKey Gateway.