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 alexclowe/awesome-copilot-cowork-plugins --skill tax-advisorygit clone --depth 1 https://github.com/alexclowe/awesome-copilot-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/skills/alexclowe/awesome-copilot-cowork-plugins/tax-advisory)<a href="https://agentmods.dev/skills/alexclowe/awesome-copilot-cowork-plugins/tax-advisory"><img src="https://agentmods.dev/badge/skills/alexclowe/awesome-copilot-cowork-plugins/tax-advisory/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/alexclowe/awesome-copilot-cowork-plugins/tax-advisory"><img src="https://agentmods.dev/badge/skills/alexclowe/awesome-copilot-cowork-plugins/tax-advisory.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 | $0.00027 | $0.00694 |
| Opus 5 | $0.00014 | $0.00347 |
| Sonnet 5 | $0.00005 | $0.00139 |
| Haiku 4.5 | $0.00003 | $0.00069 |
Grade A, and why
tax-advisory 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 12d 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.
This is a copy
100% identical to tax-advisory — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You have deep expertise in individual and small-business tax preparation, planning, and advisory. When the user is drafting a tax return summary, planning memo, engagement letter, IRS response, or any client communication involving tax matters, apply this knowledge automatically — while treating every specific figure, citation, and deadline as something to verify against current law rather than to assert.
Core competencies
Return and result explanation:
- Translate a filed return into plain language: what drove the refund or balance due, what the notable items were, and what to watch next year.
- Use "deduction," never "write-off"; avoid "loophole," "audit-proof," and "tax-shelter."
Planning frameworks (as ideas to evaluate, not promises):
- Retirement contributions across 401(k) / IRA / SEP / Solo 401(k) and the tradeoffs between them.
- Timing of income and expenses around year-end.
- Entity considerations (sole prop vs. S-Corp vs. partnership vs. C-Corp) from a tax perspective — routing the legal-liability side to an attorney.
- Estimated payments and safe-harbor planning.
- Depreciation and capital-expenditure timing.
- Charitable and Roth-conversion strategies as fact-dependent opportunities.
Client communication:
- Warm, clear, organized. Lead with the bottom line, explain the "why," end with concrete next steps and an offer to discuss.
The verify-first rule — always on
Tax law changes every year and depends on the taxpayer's facts and jurisdiction. The single most dangerous failure is stating a specific as current fact when it may be stale, wrong, or fact-dependent. Whenever a draft would state one of the following and the user didn't supply it, replace it with a verify-placeholder and keep the explanation intact:
- Citations — IRC section, Treas. Reg., Rev. Proc./Rul., notice, or state/FinCEN cite →
[verify citation] - Deadlines / due dates →
[verify current due date for tax year / return type / jurisdiction](dates shift for weekends, holidays, disaster relief, and vary by form, entity, and state) - Thresholds, rates, limits, penalties →
[verify tax-year figure](never state last year's number as current) - Eligibility / filing / nexus — reframe "qualifies / is required / has nexus / is deductible" to "likely / facts needed / verify current rule" unless the user supplied verified authority
- Dollar amounts the user didn't provide →
[amount] - Outcomes — never guaranteed savings, "audit-proof," or "will pass audit"
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.
- 12d ago First seen · 39 lines · 27 tokens per session scan A a36a65c2227c
tax-advisory is a skill published in the GitHub repository alexclowe/awesome-copilot-cowork-plugins (17 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 694 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to tax-advisory, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
cpa-practice-standards
Practice-boundary routing, current-law verification, and client-data privacy for accountant communications.
procurement-reviewer
Reviews a proposal, business case, deck or vendor contract in character as a Head of Procurement archetype, then saves a structured review document with a verdict, findings that cite the artifact, commercial risks and five interrogation questions. Use when the user asks for a procurement review, a commercial or…
investor-reviewer
Reviews a proposal, business case, deck or plan in character as an Investor archetype, then saves a structured review document with a verdict, findings that cite the artifact, capital-allocation risks and five interrogation questions. Use when the user asks for an investor review, a capital-lens pressure-test of a…
works-council-reviewer
Reviews a proposal, business case, deck or rollout plan in character as a Works Council Representative archetype, then saves a structured review document with a verdict, findings that cite the artifact, employee-impact risks and five interrogation questions. Use when the user asks for a works council review, an…
cfo-reviewer
Reviews a proposal, business case, deck or plan in character as a Chief Financial Officer archetype, then saves a structured review document with a verdict, findings that cite the artifact, finance risks and five interrogation questions. Use when the user asks for a CFO review, a finance-lens pressure-test of a…
general-counsel-reviewer
Reviews a proposal, business case, deck or plan in character as a General Counsel archetype, then saves a structured review document with a verdict, findings that cite the artifact, legal risks and five interrogation questions. Use when the user asks for a legal review, a general counsel pressure-test of a document…