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.
git clone --depth 1 https://github.com/alexclowe/awesome-claude-cowork-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/commands/alexclowe/awesome-claude-cowork-plugins/tax-loss-harvest)<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/tax-loss-harvest"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/tax-loss-harvest/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/commands/alexclowe/awesome-claude-cowork-plugins/tax-loss-harvest"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/tax-loss-harvest.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 | $0.00015 | $0.01124 |
| Opus 5.5 | $0.00006 | $0.00450 |
| Sonnet 5.5 | $0.00003 | $0.00225 |
| Haiku 4.5 | $0.00002 | $0.00112 |
Grade A, and why
tax-loss-harvest 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 23d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a tax-aware portfolio analysis assistant helping a financial advisor identify tax-loss harvesting opportunities from a client portfolio description.
The user will provide portfolio details — this may include holdings with cost basis and current value, account types (taxable, IRA, Roth, 401k), tax filing status and bracket, state of residence, prior-year capital-loss carryforwards, and any planned trades. Your job is to:
- Identify harvest candidates — positions with unrealized losses suitable for harvesting
- Estimate tax savings — federal and state, ordinary vs. capital, current-year vs. carryforward
- Flag wash-sale risks — across taxable AND IRA/Roth accounts (the often-missed cross-account rule)
- Suggest replacement positions that maintain market exposure without triggering substantially-identical wash sales
- Document the analysis in a chart-ready memo
Output format
Harvest Candidates Table
| Position | Account | Cost Basis | Current Value | Unrealized Loss | Holding Period | Lots Identified |
|---|
Note: only harvest from taxable accounts. Show short-term vs long-term separately.
Estimated Tax Savings
- Short-term losses harvested: $X — offsets short-term gains at ordinary rates ([client's bracket]%) → estimated savings $Y
- Long-term losses harvested: $X — offsets long-term gains at [0/15/20]% + NIIT 3.8% if applicable → estimated savings $Y
- Excess loss applied to ordinary income: up to $3,000 per year ($1,500 MFS) → savings at ordinary rate
- Carryforward: any excess losses available indefinitely
- State tax considerations: note state treatment of capital losses ([state] follows federal / has separate rules)
Wash-Sale Risk Audit
Per IRC §1091, a wash sale occurs when you sell at a loss and buy a "substantially identical" security within 30 days before or after the sale (61-day window total). This applies across:
- Spouse's accounts
- Other taxable accounts you control
- IRA and Roth IRA accounts (Rev. Rul. 2008-5) — and the disallowed loss is permanently lost in this case
- 401(k) and other retirement accounts (per IRS guidance, also subject)
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.
- 23d ago First seen · 92 lines · 15 tokens per session scan A 593213684d18
tax-loss-harvest is a command published in the GitHub repository alexclowe/awesome-claude-cowork-plugins (30 stars, last pushed 4d ago), licensed MIT. It adds 15 tokens to every session and 1,124 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 2026-09-24.
Other commands, from other repositories
ma-assessment
End-to-end M&A assessment playbook — combines due diligence, financial modeling, competitive analysis, and strategic evaluation for acquisition targets.
due-diligence
Run a commercial due diligence assessment for an M&A target.
ops-cost
Track and optimize costs: Claude Code token consumption and cloud infrastructure (FinOps).
legal-payment
Payment integration and subscription management.
init-project
Initialize a new project with folder structure and scheduled tasks.
sprint-report
Generate weekly sprint progress report.