cpa

cpa is an agent for Claude Code from Everyone-Needs-A-Copilot/claude-copilot. It costs 43 tokens per session (2,342 once invoked), scanned A, original, MIT.

Financial analysis, tax strategy, owner compensation, cash flow forecasting, hiring economics, distribution planning. Use PROACTIVELY when pricing economics, tax implications, business finance, or compensation modeling is needed.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/everyone-needs-a-copilot/claude-copilot/cpa
Clone the repo
git clone --depth 1 https://github.com/Everyone-Needs-A-Copilot/claude-copilot

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.

agentmods badge for cpa

README.md
[![agentmods](https://agentmods.dev/badge/agents/everyone-needs-a-copilot/claude-copilot/cpa.svg)](https://agentmods.dev/agents/everyone-needs-a-copilot/claude-copilot/cpa)
Your own site
<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="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,342 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00043 $0.02342
Opus 5 $0.00022 $0.01171
Sonnet 5 $0.00009 $0.00468
Haiku 4.5 $0.00004 $0.00234

Measured today against content hash ff0f56ea1d07, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 today.

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.

.claude/agents/cpa.md · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 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.

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

  1. tc task get <taskId> --json -- verify task exists (if Task Copilot in use)
  2. eval "$(cc env)" -- hydrate shared docs / knowledge env
  3. cc memory search "tax compensation finance" -- recall prior financial decisions
  4. cc skill search "<topic>" -- load relevant skills
  5. Clarify question type (deductibility, timing, compliance, modeling)
  6. Model scenarios, present options with pros/cons
  7. 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

Read the full file on GitHub · 191 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.

  1. today First seen · 191 lines · 43 tokens per session scan A ff0f56ea1d07

Subscribe to this mod's changes

cpa is an agent published in the GitHub repository Everyone-Needs-A-Copilot/claude-copilot (13 stars, last pushed 10d ago), licensed MIT. It adds 43 tokens to every session and 2,342 once invoked, about $0.0002 per session on Opus 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.

Related

Other agents, from other repositories

44-investor-relations

You are the Head of Investor Relations. You own the ongoing narrative to the people who fund the company and the relationships behind it. Governance & IPO (Agent 26) builds the machinery of being a company investors can own; Finance (Agent 18) produces the numbers; you turn those numbers into a story investors…

ankitjha67/product-architect · 0 tokens

45-corporate-development

You are the Head of Corporate Development. You own inorganic growth - the things the company buys, invests in, or sells rather than builds: acquisitions, minority investments, joint ventures, and divestitures. Where BD & Partnerships (Agent 33) owns contractual growth (deals where two companies stay separate and…

ankitjha67/product-architect · 0 tokens

chrono

Temporal Pattern Expert analyzing time-of-day, day-of-week, and seasonality.

emerzon/mtdata-mcp · 17 tokens

stage-6-settlement

Agent "stage-6-settlement" from TelivityAI/otaip, covering stage 6 -- settlement agents, agent 6.1 -- refund processing, agent 6.2 -- adm prevention, agent 6.3 -- adm/acm processing and agent 6.4 -- customer communication.

TelivityAI/otaip · 0 tokens

quant-backtest-validator

Validates backtesting execution realism, transaction costs, and market microstructure modeling.

stefan-jansen/claude-code-toolkit · 15 tokens

token-economics-designer

Token economics and tier design specialist. Use when designing pricing models, access tiers, or token distribution strategies.

Matt-Dionis/claude-code-configs · 28 tokens