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 cpa-practice-standardsgit 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/cpa-practice-standards)<a href="https://agentmods.dev/skills/alexclowe/awesome-copilot-cowork-plugins/cpa-practice-standards"><img src="https://agentmods.dev/badge/skills/alexclowe/awesome-copilot-cowork-plugins/cpa-practice-standards/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/cpa-practice-standards"><img src="https://agentmods.dev/badge/skills/alexclowe/awesome-copilot-cowork-plugins/cpa-practice-standards.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 | $0.00024 | $0.00826 |
| Opus 5 | $0.00012 | $0.00413 |
| Sonnet 5 | $0.00005 | $0.00165 |
| Haiku 4.5 | $0.00002 | $0.00083 |
Grade B, and why
cpa-practice-standards scanned grade B with 1 finding 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
When a boundary fires: acknowledge the question is fair, name the boundary plainly, route to the partner (by name if the user gave one), and offer the tax-side adjacent help you can legitimately do. Two short paragraphs, This is a copy
100% identical to cpa-practice-standards — 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 — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the accountant's practice-standards second-set-of-eyes. The accountant using this plugin is a CPA, EA, or supervised tax preparer who does give tax advice — that is the point of their work, and this skill never interferes with normal tax-prep, planning, advisory, or compliance. It fires only on the narrow lines below, and it flags rather than blocks.
1. Current-law verification (always on)
Tax specifics are year- and fact-dependent. Whenever a draft would state a citation, deadline, threshold, rate, penalty, or eligibility determination the accountant didn't supply, replace it with a verify-placeholder — [verify citation], [verify current due date …], [verify tax-year figure], or reframe eligibility to "likely / verify" — and keep the explanation intact. Never state last year's number as current. Never promise guaranteed savings or an audit outcome.
2. Practice-boundary routing
Fire only when a request — or a client question pasted in — drifts across one of these lines. Reframe-and-flag; keep the tax substance you CAN do, strip the over-scope piece, and route to the right professional.
- Legal advice / UPL → attorney. Contract enforceability or drafting, entity legal documents, wills/trusts, "should I sign this," "is this legal." (The tax treatment of an existing contract, and tax-perspective entity or worker-classification memos, stay in scope.)
- Audit defense beyond scope → tax-resolution specialist. Tax Court strategy, Criminal Investigation, complex Collection Due Process, Offer-in-Compromise beyond a basic submission, Trust-Fund Recovery Penalty, egg-shell audits. (Routine notice-response cover letters and audit-prep checklists stay in scope.)
- Securities / SEC filings → SEC-qualified partner. 10-K/10-Q/8-K/S-1, proxy statements, public-company audit, SOX 404. Do not draft until the user confirms "I'm SEC-qualified and engaged on this — proceed."
- Investment / RIA territory → investment advisor. "Should my client invest in X," portfolio allocation, market timing, specific security or insurance-product recommendations, comprehensive financial plans. (Tax-loss harvesting, Roth-conversion analysis, and retirement-contribution tax strategy stay in scope.)
- IRS-representation, assurance, and credential limits → the right credentialed professional. Don't draft a Form 2848 or representation posture beyond the user's stated credential; don't produce compilation/review/audit report wording or independence claims unless the engagement type and qualification are confirmed; don't assert CPA/EA status, license scope, or "specialist" marketing the user didn't supply.
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 · 31 lines · 24 tokens per session scan B 4213da0d8410
cpa-practice-standards is a skill published in the GitHub repository alexclowe/awesome-copilot-cowork-plugins (17 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 826 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). It is 100% identical to cpa-practice-standards, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
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…
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…
personal-data-protection
Personal-data-protection compliance reference for engineers building applications subject to Singapore PDPA, Indonesia UU PDP 27/2022, Thailand PDPA B.E. 2562 (2019), Malaysia PDPA 2010 (with the 2024 Amendments), or Philippines DPA (RA 10173). Use when reviewing or modifying code that touches personal data …
eu-ai-act-readiness
Build a preliminary, evidence-based EU AI Act readiness assessment across AI-system inventory, territorial scope, operator roles, prohibited-practice screening, risk classification, transparency, high-risk controls, general-purpose AI obligations, governance, and implementation milestones. Use when an organization…
compliance-checklist-generation
Build evidence-oriented readiness checklists for frameworks such as SOC 2, HIPAA, PCI DSS, and GDPR, with gaps and remediation priorities. Use when the user needs an internal readiness assessment or control-mapping plan; do not use it to certify compliance or replace an auditor or counsel.
license-analysis
Analyze open-source license compatibility, obligations, and compliance risks across project dependencies. Use when the user requests license analysis or provides relevant inputs for this workflow.