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 chrisblattman/claudeblattman --skill tax-guidegit clone --depth 1 https://github.com/chrisblattman/claudeblattmanWrote 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/chrisblattman/claudeblattman/tax-guide)<a href="https://agentmods.dev/skills/chrisblattman/claudeblattman/tax-guide"><img src="https://agentmods.dev/badge/skills/chrisblattman/claudeblattman/tax-guide/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/chrisblattman/claudeblattman/tax-guide"><img src="https://agentmods.dev/badge/skills/chrisblattman/claudeblattman/tax-guide.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 | $0.00019 | $0.02381 |
| Opus 5.5 | $0.00008 | $0.00952 |
| Sonnet 5.5 | $0.00004 | $0.00476 |
| Haiku 4.5 | $0.00002 | $0.00238 |
Grade A, and why
tax-guide 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 today.
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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/tax-guide — Personalized Tax Prep Guide
A guided Q&A that assesses your tax situation and generates a personalized preparation plan. Outputs a recommendation (self-file, self-file with care, or hire a professional), a document checklist, a suggested workflow, and privacy guidance.
Phased Execution
Phase 0: Pre-checks
Before starting the Q&A, verify the environment:
- Confirm Claude Code is running (you're reading this, so it is)
- Check if a prior
/tax-guideoutput exists in the working directory — if so, note it and offer to update rather than re-run - Set the tax year to the most recent completed calendar year (e.g., if today is in 2026, the tax year is 2025)
Phase 1: Collect — The Q&A
Ask each question one at a time. Wait for the user's response before proceeding. Keep the tone conversational and concise.
Question 1: Primary income
What's your primary income source?
- (a) W-2 salary only — one employer
- (b) W-2 salary + side income (consulting, freelance, gig work)
- (c) Fully self-employed / independent contractor
- (d) Multiple income types (salary + rental + investment + other)
Store as income_type.
Question 2: 1099 forms
How many 1099 forms do you expect to receive this year? (1099-NEC, 1099-MISC, 1099-K, etc.)
- (a) None
- (b) 1-2
- (c) 3 or more
Store as num_1099s.
Question 3: Itemized deductions
Do you itemize deductions (or are you unsure)?
- (a) Yes, I itemize
- (b) No, I take the standard deduction
- (c) Not sure
If answer is (c), provide a one-sentence explanation: "You itemize if your mortgage interest + state/local taxes + charitable giving + medical expenses exceed the standard deduction. The standard deduction changes annually — check IRS.gov for the current year's amounts. Most homeowners with a mortgage itemize."
Store as itemize_status.
Question 4: Complexity flags
Do any of these apply to you? (Select all that apply, or "none")
- Foreign income (work, consulting, or investments abroad)
- Rental property
- K-1 from a partnership, S-corp, or trust
- Stock options (ISOs, NSOs) or significant RSU vests
- Cryptocurrency beyond simple buy/sell
- None of the above
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.
- today First seen · 229 lines · 19 tokens per session scan A 2f2ad4cec002
tax-guide is a skill published in the GitHub repository chrisblattman/claudeblattman (476 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 2,381 once invoked, about $0.0001 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 2026-11-06.
tax-guide compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| tax-guidechrisblattman/claudeblattman | Skill | 476 | yesterday | MIT | A | 19 | Claude Code, Codex |
| ma-playbookalirezarezvani/claude-skills | Skill | 29k | yesterday | MIT | A | 29 | Claude Code |
| sox-itgcSushegaad/Claude-Skills-Governance-Risk-and-Compliance | Skill | 1.0k | 27d ago | MIT | A | 202 | Claude Code |
| monetization-strategytravisjneuman/.claude | Skill | 107 | yesterday | MIT | A | 34 | Claude Code, Codex |
| payment-integrationtravisjneuman/.claude | Skill | 107 | yesterday | MIT | A | 40 | Claude Code, Codex |
| ai-policy-generatortravisjneuman/.claude | Skill | 107 | yesterday | MIT | A | 42 | Claude Code, Codex |
| contract-redlinertravisjneuman/.claude | Skill | 107 | yesterday | MIT | A | 41 | Claude Code, Codex |