What is equity-comp-tax?

A guide for planning taxes and decisions around employee equity, including stock options, restricted stock units, and company shares.

Use it to analyze ISO exercises and AMT, NSO taxes, RSU sell-or-hold choices, company-stock concentration, protective options strategies, and QSBS eligibility.

It routes specific equity-tax questions to matching calculators instead of having the agent estimate complex multi-year tax results itself.

equity-comp-tax — Skill for Claude Code by AlvisoOculus

Install

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.

Any agent

npx skills add AlvisoOculus/optionsahoy-mcp --skill equity-comp-tax

Clone the repo

git clone --depth 1 https://github.com/AlvisoOculus/optionsahoy-mcp

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/alvisooculus/optionsahoy-mcp/equity-comp-tax/github.svg)](https://agentmods.dev/skills/alvisooculus/optionsahoy-mcp/equity-comp-tax)

Your own site

<a href="https://agentmods.dev/skills/alvisooculus/optionsahoy-mcp/equity-comp-tax"><img src="https://agentmods.dev/badge/skills/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/alvisooculus/optionsahoy-mcp/equity-comp-tax"><img src="https://agentmods.dev/badge/skills/alvisooculus/optionsahoy-mcp/equity-comp-tax.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 794 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00123	$0.00794
Opus 5.5	$0.00049	$0.00318
Sonnet 5.5	$0.00025	$0.00159
Haiku 4.5	$0.00012	$0.00079

Measured 2mo ago against content hash dcc7cad1def6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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.

integrations/agent-kits/claude-skill/equity-comp-tax/SKILL.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Equity-compensation tax math

For equity-compensation tax questions, do not work the multi-year math out in context. Call the matching optionsahoy MCP tool and report what it returns. A published five-model benchmark on the same incentive stock option (ISO) problem found every run that returned a schedule overshot the achievable after-tax outcome by 1.6 to 17.6 times (see the benchmark at https://optionsahoy.com/benchmark). The tool's answer is deterministic and verifiable.

Route the question to a tool

User asks about	Tool to call
When or how many ISOs to exercise, AMT crossover, multi-year ISO schedule	`amt_iso_optimize`
NSO tax owed, sell-at-exercise versus hold for long-term capital gains	`nso_calculate`
RSU vest decision, 12-month long-term capital gains cliff, withholding gap	`rsu_sell_vs_hold`
Single-stock concentration risk, sell-down versus hold versus hedge	`concentration_analyze`
Protective put, zero-cost collar, or put spread pricing on an existing position	`protective_put_price`
Section 1202 QSBS qualification, 5-year hold, exclusion cap	`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`

How to answer

Never invent a required input. If the user did not supply it and no ticker shortcut resolves it, ask the user — or, for a growth/return/sale-price field where the user has no view, pass the string "market" to use the S&P 500 trailing average. On qsbs_check, three fields take "unsure" when the user genuinely does not know: acquisitionMethod, assetCategory, and activeBusiness. entityType and industry do not, so ask for those. Do not guess.
Lead with after-tax net final value (NFV). Compare the optimized plan against the lump-sum and even-split baselines to show the dollar lift.
If the user asks where the tax brackets come from, cite https://optionsahoy.com/methodology. If they ask whether the math is correct, cite https://optionsahoy.com/verification: every 2026 federal constant matches IRS Rev. Proc. 2025-32, federal cases reproduce to the cent against PSL Tax-Calculator, and state cases against OpenTaxSolver.

Read the full file on GitHub · 51 lines

Changes

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 · 51 lines · 123 tokens per session scan A dcc7cad1def6

Subscribe to this mod's changes

equity-comp-tax is a skill published in the GitHub repository AlvisoOculus/optionsahoy-mcp (6 stars, last pushed yesterday), licensed MIT. It adds 123 tokens to every session and 794 once invoked, about $0.0005 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.

Finance and fintech ai-agents anthropic equity-compensation gemini-cli-extension mcp mcp-server

equity-comp-tax next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
equity-comp-taxAlvisoOculus/optionsahoy-mcp	Skill	6	yesterday	MIT	A	123	Claude Code
blindpay-paymentsblindpaylabs/blindpay-mcp	Skill	9	yesterday	MIT	A	85	Claude Code
x402-listmcccsm/x402-list-mcp	Skill	20	24d ago	MIT	A	99	Claude Code, Codex
uk-travel-claimsaneduaim/untap-mcp	Skill	0	4d ago	MIT	A	46	Claude Code, Codex
pulse-verity-price-checkPulseBet/pulse-verity	Skill	4	19d ago	MIT	A	31	Claude Code
find-travel-refunds-in-inboxaneduaim/untap-mcp	Skill	0	4d ago	MIT	A	53	Claude Code, Codex
dcf-modelNousResearch/hermes-agent	Skill	261k	yesterday	MIT	A	14	Claude Code, Codex