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 nirholas/three.ws --skill tax-loss-harvestinggit clone --depth 1 https://github.com/nirholas/three.wsWrote 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/nirholas/three.ws/tax-loss-harvesting)<a href="https://agentmods.dev/skills/nirholas/three.ws/tax-loss-harvesting"><img src="https://agentmods.dev/badge/skills/nirholas/three.ws/tax-loss-harvesting/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/nirholas/three.ws/tax-loss-harvesting"><img src="https://agentmods.dev/badge/skills/nirholas/three.ws/tax-loss-harvesting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00032 | $0.01023 |
| Opus 5 | $0.00016 | $0.00511 |
| Sonnet 5 | $0.00006 | $0.00205 |
| Haiku 4.5 | $0.00003 | $0.00102 |
Grade A, and why
tax-loss-harvesting 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 7d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tax-Loss Harvesting
When to use this skill
Use when the user asks about:
- Reducing crypto tax obligations
- Finding unrealized losses in their portfolio
- Tax-loss harvesting strategies for crypto
- Wash sale rules and crypto (jurisdiction-dependent)
- Year-end tax planning for crypto holdings
Harvesting Framework
1. Identify Loss Positions
Scan the portfolio for unrealized losses:
- List all holdings with cost basis and current market value
- Calculate unrealized P&L for each position (current value - cost basis)
- Categorize by holding period: Short-term (held < 1 year) vs long-term (held > 1 year)
- Sort by loss magnitude: Largest absolute losses first
| Asset | Cost Basis | Current Value | Unrealized P&L | Holding Period |
|---|---|---|---|---|
| Token A | $10,000 | $6,000 | -$4,000 | 8 months (ST) |
| Token B | $5,000 | $3,500 | -$1,500 | 14 months (LT) |
2. Tax Impact Calculation
Estimate the value of harvesting each loss:
- Short-term losses offset short-term gains (taxed at ordinary income rate, up to 37% in the US)
- Long-term losses offset long-term gains (taxed at 0/15/20% depending on bracket)
- Net losses can offset up to $3,000 of ordinary income per year (US), remainder carries forward
- Calculate tax savings: Loss amount * marginal tax rate = estimated tax reduction
- Prioritize short-term losses harvested against short-term gains for maximum benefit
3. Wash Sale Considerations
Address wash sale rules (jurisdiction-dependent):
- US crypto status: As of the user's tax year, check current IRS guidance on wash sale applicability to crypto. The 2025 infrastructure bill may have changed rules.
- Traditional wash sale rule (stocks): Cannot buy back substantially identical asset within 30 days before or after the sale
- If crypto wash sales apply: Suggest waiting 31 days or swapping into a correlated but different asset
- If wash sales do NOT apply: Can sell and immediately rebuy (preserving exposure while capturing the loss)
- Other jurisdictions: Rules vary significantly — UK (30-day rule), EU, Australia, etc. Always advise consulting a local tax professional
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.
- 7d ago First seen · 96 lines · 32 tokens per session scan A 210a231d88ab
tax-loss-harvesting is a skill published in the GitHub repository nirholas/three.ws (114 stars, last pushed yesterday), licensed Apache-2.0. It adds 32 tokens to every session and 1,023 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
wallet-verwahrung-haftungsfragen
Prueft Haftungsfragen bei der Verwahrung von Kryptowerten durch einen Drittverwahrer einschliesslich Verlust oder Diebstahl. Methodik Vertragstypqualifikation Sorgfaltsmassstab Aussonderungsrecht. Output ausformulierte Pruefung mit Haftungs und Insolvenzrisiko.
bilanzierung-unternehmen-krypto-bewertung
Pruefung der bilanziellen Behandlung von Kryptowerten im Betriebsvermoegen bilanzierender Unternehmen. Methodik Ansatz als Wirtschaftsgut Bewertungsmassstab Wertminderung. Output ausformulierte Pruefung mit Ansatz- und Bewertungsempfehlung fuer den Jahresabschluss.
bmf-schreiben-krypto-checkliste
Strukturierte Checkliste zur Anwendung des aktuellen BMF-Schreibens zur ertragsteuerlichen Behandlung von virtuellen Waehrungen und sonstigen Token auf einen konkreten Sachverhalt. Methodik Abgleich Sachverhalt mit Verwaltungsauffassung. Output ausformulierte Pruefung mit Fundstellenhinweisen.
mining-gewerblich-oder-privat
Abgrenzung ob Mining von Kryptowaehrungen eine gewerbliche Taetigkeit nach Paragraf 15 EStG oder private Vermoegensverwaltung darstellt. Methodik Kriterien Nachhaltigkeit Gewinnerzielungsabsicht Kapitaleinsatz. Output ausformulierte Abgrenzungspruefung mit Einkunftsart.
staking-rewards-besteuerung
Pruefung der ertragsteuerlichen Behandlung von Staking-Rewards im Privatvermoegen. Methodik Zuflusszeitpunkt Bewertung in Euro Einkunftsart Abgrenzung gewerblich. Output ausformulierte Einordnung je Reward-Zufluss mit Wertansatz.
verlustverrechnung-krypto
Pruefung der Verlustverrechnungsmoeglichkeiten bei Verlusten aus privaten Veraeusserungsgeschaeften mit Kryptowerten. Methodik Verrechnungskreis Verlustvortrag Verlustruecktrag. Output ausformulierte Pruefung mit Berechnung des verbleibenden Verlustvortrags.