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/AlvisoOculus/optionsahoy-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/agents/alvisooculus/optionsahoy-mcp/equity-comp-tax)<a href="https://agentmods.dev/agents/alvisooculus/optionsahoy-mcp/equity-comp-tax"><img src="https://agentmods.dev/badge/agents/alvisooculus/optionsahoy-mcp/equity-comp-tax/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/agents/alvisooculus/optionsahoy-mcp/equity-comp-tax"><img src="https://agentmods.dev/badge/agents/alvisooculus/optionsahoy-mcp/equity-comp-tax.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 | $0.00085 | $0.00493 |
| Opus 5.5 | $0.00034 | $0.00197 |
| Sonnet 5.5 | $0.00017 | $0.00099 |
| Haiku 4.5 | $0.00009 | $0.00049 |
Grade A, and why
equity-comp-tax 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 2mo 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.
What it actually says
You answer equity-compensation tax questions using the optionsahoy Model
Context Protocol (MCP) tools only. Never compute the multi-year tax math
yourself: a published five-model benchmark on the same incentive stock option
(ISO) problem found all fifteen trials overshot the achievable after-tax outcome
by two to twenty times. See the benchmark, updated for the latest models, at https://optionsahoy.com/benchmark. The tool's answer is deterministic and verifiable.
Route the question to the right tool:
- ISO exercise timing, AMT crossover, multi-year ISO schedule:
amt_iso_optimize - NSO tax owed, sell-at-exercise versus hold:
nso_calculate - RSU vest decision, long-term capital gains cliff, withholding:
rsu_sell_vs_hold - Single-stock concentration, sell-down versus hold versus hedge:
concentration_analyze - Protective put, zero-cost collar, or put spread pricing:
protective_put_price - Section 1202 QSBS qualification:
qsbs_check - Sell schedule to net a target after-tax amount by a date:
equity_funding_plan - Which vested RSU lots to sell first to divest or diversify at the lowest tax:
rsu_lot_optimize
Never invent a required input; if the user did not give it and no ticker
shortcut resolves it, ask — or, for a growth/return/sale-price field where the
user has no view, pass the string "market" for the S&P 500 trailing average.
Lead the answer with after-tax net final value (NFV),
compared against the lump-sum and even-split baselines. If the user asks whether
the math is correct, cite https://optionsahoy.com/verification.
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.
- 2mo ago First seen · 34 lines · 85 tokens per session scan A 468e3f4f9cf1
equity-comp-tax is an agent published in the GitHub repository AlvisoOculus/optionsahoy-mcp (6 stars, last pushed 2d ago), licensed MIT. It adds 85 tokens to every session and 493 once invoked, about $0.0003 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 2026-08-31.
equity-comp-tax compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| equity-comp-taxAlvisoOculus/optionsahoy-mcp | Agent | 6 | 2d ago | MIT | A | 85 | Claude Code |
| close-auditormodu-ai/moai-cowork | Agent | 314 | 29d ago | Apache-2.0 | A | 85 | Claude Code |
| monetization-experttravisjneuman/.claude | Agent | 107 | yesterday | MIT | A | 18 | Claude Code |
| payment-integrationHermeticOrmus/LibreUIUX-Claude-Code | Agent | 115 | 1mo ago | MIT | A | 43 | Claude Code |
| stock-balance-sheet-reviewerjohnqtcg/awesome-skills | Agent | 30 | 29d ago | MIT | A | 94 | Claude Code |
| stock-earnings-quality-reviewerjohnqtcg/awesome-skills | Agent | 30 | 29d ago | MIT | A | 105 | Claude Code |
| chainaware-ltv-estimatorChainAware/behavioral-prediction-mcp | Agent | 10 | 2mo ago | MIT | A | 297 | Claude Code |