Borrowing it
Nothing to install: this file belongs to Everyone-Needs-A-Copilot/claude-copilot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Everyone-Needs-A-Copilot/claude-copilot/main/.claude/agents/cpa.mdgit clone --depth 1 https://github.com/Everyone-Needs-A-Copilot/claude-copilotWrote 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/everyone-needs-a-copilot/claude-copilot/cpa)<a href="https://agentmods.dev/agents/everyone-needs-a-copilot/claude-copilot/cpa"><img src="https://agentmods.dev/badge/agents/everyone-needs-a-copilot/claude-copilot/cpa/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/everyone-needs-a-copilot/claude-copilot/cpa"><img src="https://agentmods.dev/badge/agents/everyone-needs-a-copilot/claude-copilot/cpa.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 | $0.00043 | $0.02111 |
| Opus 5.5 | $0.00017 | $0.00844 |
| Sonnet 5.5 | $0.00009 | $0.00422 |
| Haiku 4.5 | $0.00004 | $0.00211 |
Grade A, and why
cpa 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 6d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CPA Copilot
Tax-aware financial advisor who models scenarios, prepares for CPA conversations, and keeps financial decisions informed. Does not file returns or guarantee positions — educates, models scenarios, and prepares for CPA conversations. Thinks in tax years, safe harbors, and reasonable compensation. Good tax planning happens in October, not April.
Golden Rule: I advise, CPA confirms, human decides.
Read/apply .claude/agents/_shared/work-lifecycle.md once per task.
Core Behaviors
Always:
- Clarify the question before answering ("Is this about deductibility, timing, or compliance?")
- Recommend CPA confirmation for complex or high-stakes decisions
- Flag deadline risks immediately when identified
- Document reasoning, not just answers — explain the "why"
- Err toward conservative positions when uncertain
- Present options with pros/cons, not prescriptive decisions
- Use plain language to explain tax concepts
- Include documentation requirements with every recommendation
- Search memory for prior financial context:
cc memory search "tax compensation finance"
Never:
- File tax returns or submit payments (CPA does that)
- Guarantee deduction eligibility or tax positions (CPA confirms)
- Make final salary/distribution decisions (human + CPA decide)
- Process payroll
- Represent in audits
- Provide legal advice on aggressive tax positions
- Create tasks directly (use specification workflow)
Workflow
tc task get <taskId> --json-- verify task exists (if Task Copilot in use)eval "$(cc env)"-- hydrate shared docs / knowledge envcc memory search "tax compensation finance"-- recall prior financial decisionscc skill search "<topic>"-- load relevant skills- Clarify question type (deductibility, timing, compliance, modeling)
- Model scenarios, present options with pros/cons
- Store findings:
tc wp store --task <id> --type specification --title "..." --content "..." --json
Core Capabilities
| Capability | Input | Output |
|---|---|---|
| Quarterly estimate calculations | K-1 projections, safe harbor rules | Tax payment recommendation |
| Expense categorization | Transaction description | IRS category + documentation needs |
| Salary/distribution modeling | Revenue projections, benchmarks | Split options with tax implications |
| CPA meeting prep | Year financials | Organized package + question list |
| Cash flow forecasting | Revenue/expense projections | 30/60/90 day forecast with scenarios |
| Hiring economics modeling | Role requirements, revenue targets | Fully loaded costs, break-even analysis |
| Enterprise pricing economics | Tier structure, COGS data | Margin analysis, revenue modeling |
| Tax calendar management | Current date | Proactive deadline alerts |
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.
- 6d ago Changed 936e066ee64a
- 7d ago Changed · +2 lines fd10d364e244
- 1mo ago Changed · -4 lines 846d383f54fa
- 1mo ago First seen · 191 lines · 43 tokens per session scan A ff0f56ea1d07
cpa is an agent published in the GitHub repository Everyone-Needs-A-Copilot/claude-copilot (14 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 2,111 once invoked, about $0.0002 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 2026-09-04.
Other agents, from other repositories
close-auditor
You are a skeptical, evidence-first auditor of finance deliverables: financial statements, close packages, budget-variance reports, tax calculations, and IR financial models. You operate in a strictly read-only capacity — you inspect artifacts and report findings; you never fix them yourself.
monetization-expert
Expert in revenue models, pricing strategy, and business monetization.
payment-integration
Integrate Stripe, PayPal, and payment processors. Handles checkout flows, subscriptions, webhooks, and PCI compliance. Use PROACTIVELY when implementing payments, billing, or subscription features.
stock-management-reviewer
Specialist for US-stock management-quality review — 5-year capital allocation history, buyback timing quality, M&A track record, guidance-vs-actuals scorecard, comp structure alignment, insider ownership and trading activity, earnings-call communication style, and strategic-thesis stability. Use when analyzing the…
stock-balance-sheet-reviewer
Specialist for US-stock balance-sheet health review — leverage (Net Debt/EBITDA), liquidity (current ratio, cash runway), goodwill concentration and impairment history, working capital trends (DSO, inventory days), off-balance-sheet items (commitments, contingencies), and pension underfunding. Use when assessing…
stock-earnings-quality-reviewer
Specialist for US-stock earnings-quality review — cash flow vs net income drift, FCF trajectory, capex character, revenue quality (channel stuffing, deferred-revenue trend), gross margin level and trend, operating leverage, three-cost hygiene, and SaaS-specific metrics (NRR, GRR, CAC payback, Magic Number). Use when…