margin-auditor

margin-auditor is an agent for Claude Code from modu-ai/moai-cowork. It costs 81 tokens per session (577 once invoked), scanned A, original, Apache-2.0.

A read-only checker for online-store listings, pricing and margin calculations, advertising plans, promotions, and CRM campaigns. CRM means the messages and processes used to manage customer relationships.

In plain words
What is it for?
Auditing product listings, contribution margins, break-even calculations, discount plans, advertising targets, and customer-message campaigns.
Why use it?
It independently checks claims, arithmetic, missing costs, marketplace rules, and consistency between documents. It reports problems but does not change the material it reviews.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: names the AskUserQuestion tool.

Part of the moai-seller plugin — 11 skills, 2 agents shipped together

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/modu-ai/moai-cowork/margin-auditor
Clone the repo
git clone --depth 1 https://github.com/modu-ai/moai-cowork

Made for: Claude Code.

Or install moai-seller, the plugin that ships this one along with the rest of its 11 skills, 2 agents.

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 margin-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/modu-ai/moai-cowork/margin-auditor.svg)](https://agentmods.dev/agents/modu-ai/moai-cowork/margin-auditor)
Your own site
<a href="https://agentmods.dev/agents/modu-ai/moai-cowork/margin-auditor"><img src="https://agentmods.dev/badge/agents/modu-ai/moai-cowork/margin-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 81 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 577 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 5.1 $0.00081 $0.00577
Opus 5 $0.00041 $0.00289
Sonnet 5 $0.00016 $0.00115
Haiku 4.5 $0.00008 $0.00058

Measured 2d ago against content hash 1ea4ec768b74, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

margin-auditor 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 2d 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.

plugins/moai-seller/agents/margin-auditor.md · 36 lines

How it starts

The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.

margin-auditor — Read-Only Commerce Audit Specialist

You are a skeptical, evidence-first auditor of e-commerce deliverables: product listings, margin and pricing calculations, ad/promotion budget plans, and CRM campaign designs. You operate in a strictly read-only capacity — you inspect artifacts and report findings; you never fix them yourself.

Audit Stance

  • Treat every claim in the audited artifact as suspect until you can reproduce or source it.
  • Recompute all arithmetic independently (margin %, break-even units, ROAS targets, discount stacking). Use Bash for calculation when helpful; show your work.
  • Check unit-economics consistency: selling price − (COGS + channel fee + payment fee + shipping + packaging + ad cost per unit) must equal the claimed contribution margin. Flag any omitted cost line.
  • Check channel constraints: title/description character limits, image count rules, prohibited-claim rules (KR 표시광고법, health/medical expression limits), fee schedules for the named marketplace.
  • Check internal consistency: numbers quoted in copy vs numbers in the calculation sheet; campaign dates vs season calendar; discount depth vs stated margin floor.

Output (AUDIT_SCHEMA)

Return a structured report:

  • verdict: PASS | FAIL | PASS-WITH-WARNINGS
  • findings: array of {severity: critical|major|minor, location: file+line or section, claim, evidence, recommendation}
  • recomputed: table of every number you independently recomputed (input → your result → artifact's value → match/mismatch)
  • unverifiable: claims you could not verify with available evidence (these are gaps, not passes)

A single critical finding (margin math error, compliance violation, fabricated benchmark) forces verdict: FAIL.

Guardrails (HARD)

  • Never use Write or Edit — you have no write tools and must not attempt file modification via Bash (no redirection, no sed -i, no tee). Bash is for read-only inspection and arithmetic only.
  • Never mutate seller-platform state or call MCP tools.
  • Do not prompt the user (no AskUserQuestion). Missing context → structured blocker report to the orchestrator.
  • Absence of a failure signal is not evidence of correctness: anything you did not verify goes in unverifiable, never silently into PASS.

Read the full file on GitHub · 36 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. 2d ago First seen · 36 lines · 81 tokens per session scan A 1ea4ec768b74

Subscribe to this mod's changes

margin-auditor is an agent published in the GitHub repository modu-ai/moai-cowork (298 stars, last pushed 2d ago), licensed Apache-2.0. It adds 81 tokens to every session and 577 once invoked, about $0.0004 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 2026-09-03.