Borrowing it
Nothing to install: this file belongs to schwarztim/freetaxusa-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/schwarztim/freetaxusa-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/schwarztim/freetaxusa-mcpWrote 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/instructions/schwarztim/freetaxusa-mcp/claude-md)<a href="https://agentmods.dev/instructions/schwarztim/freetaxusa-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/schwarztim/freetaxusa-mcp/claude-md/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/instructions/schwarztim/freetaxusa-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/schwarztim/freetaxusa-mcp/claude-md.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 | $0.00390 | $0.00390 |
| Opus 5 | $0.00195 | $0.00195 |
| Sonnet 5 | $0.00078 | $0.00078 |
| Haiku 4.5 | $0.00039 | $0.00039 |
Grade B, and why
freetaxusa-mcp CLAUDE.md scanned grade B with 1 finding 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 9d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- Browser profile chmod 0700 What it actually says
FreeTaxUSA MCP Server
Browser automation MCP for FreeTaxUSA tax filing using Playwright.
Architecture
- Transport: stdio
- Browser: Playwright persistent Chromium context at
~/.freetaxusa-mcp/browser-profile/ - Navigation: SID-based URL parameters (
?sid=N), dynamically discovered from nav sidebar - Form interaction: Accessibility tree targeting (not CSS selectors)
- Security: PII filter on all outputs (SSN masking, account number masking)
- Concurrency: Async mutex prevents concurrent page operations
Commands
npm run build # TypeScript compile
npm run start # Run server (stdio)
npm run dev # Run with tsx (development)
npm test # Run unit tests
Tool Categories
Phase 1 (Implemented)
authenticate- Login with email/passwordget_session_status- Check session stateread_current_page- Read form fields on current pagesave_and_continue- Submit current pagenavigate_section- Jump to section by name or SIDfill_taxpayer_info- Fill personal infofill_filing_status- Set filing statusget_tax_summary- Return overviewget_refund_estimate- Refund/owed amount
Phase 2 (Stubbed)
fill_w2_income,fill_1099_income
Phase 3 (Stubbed)
fill_deductions,review_return,file_extension,get_form_status
Security
- Credentials never stored to disk
- PII filtered from all tool outputs
- Browser profile chmod 0700
- Anti-bot flags on browser launch
- Session expiry detected on every tool call
- State filing paywall detection
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.
- 9d ago First seen · 50 lines · 390 tokens per session scan B d0df85459f19
freetaxusa-mcp CLAUDE.md is an instructions file published in the GitHub repository schwarztim/freetaxusa-mcp (6 stars, last pushed 3d ago), licensed MIT. It adds 390 tokens to every session, about $0.0019 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.