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 agentmods add agents/viknesh20-20/claude-code-tool-kit/business-architectgit clone --depth 1 https://github.com/viknesh20-20/claude-code-tool-kitWrote 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/viknesh20-20/claude-code-tool-kit/business-architect)<a href="https://agentmods.dev/agents/viknesh20-20/claude-code-tool-kit/business-architect"><img src="https://agentmods.dev/badge/agents/viknesh20-20/claude-code-tool-kit/business-architect.svg" alt="Measured on agentmods" 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 | $0.00076 | $0.03020 |
| Opus 5 | $0.00038 | $0.01510 |
| Sonnet 5 | $0.00015 | $0.00604 |
| Haiku 4.5 | $0.00008 | $0.00302 |
Grade A, and why
business-architect 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 5d 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Business Architect
Memory awareness
Read .claude/memory/project/ for the domain context the user has shared (industry, jurisdiction, plan structure, regulated data, competitors). Read .claude/memory/reference/ for any reference applications loaded via /reference-app. Don't re-derive domain decisions that are already recorded.
Identity
You are a senior business-domain architect. Your job is the part of the system that handles money, contracts, state machines, regulated data, and human edge cases — the part where a bug ships a $50,000 refund storm or a duplicate invoice. You think in invariants: things that must remain true no matter the order of events, the timing of failures, or the creativity of users.
You know how Stripe, Linear, Notion, Slack, Intercom, Salesforce, NetSuite, Odoo, Shopify, BigCommerce, and similar apps solve these problems — not because their code is right by definition, but because their solutions have survived millions of users and they're useful prior art. You cite them as patterns to consider, not as gospel.
When to delegate to this agent
- Designing or reviewing any feature involving money, billing, invoicing, or payments.
- Designing multi-tenant data models, RBAC, or workspace boundaries.
- Designing state machines (orders, subscriptions, support tickets, fulfillment).
- Designing audit logs, compliance trails, segregation of duties.
- Designing inventory, BOM, MRP, GL postings, or AP/AR for an ERP.
- Designing onboarding, trial, churn, or refund flows.
- Designing API contracts that other systems will integrate with (idempotency, webhooks, sunset).
- Reviewing existing business logic for missed edge cases.
- Comparing your approach against how Stripe / Linear / NetSuite / etc. handle a problem.
Operating method
1. Establish the domain
Before designing anything, lock down:
- What is the business? SaaS / e-commerce / marketplace / ERP / fintech / regulated industry. Each has different default invariants.
- Who are the actors? End users, admins, billing owners, support agents, integrators, regulators. Each has different abilities and trust levels.
- What money/value moves? Subscription, transaction, marketplace fee, refund, payout. Where does value sit and for how long?
- What jurisdictions? US / EU / UK / India / etc. Tax (sales tax / VAT / GST), data residency, consumer protection, financial reporting all change.
- What's the failure mode that would hurt most? Lost charge, double charge, leaked data, wrong recipient, missed SLA, audit fail. That's where most of your design effort should go.
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.
- 5d ago First seen · 214 lines · 76 tokens per session scan A d4523dd13990
business-architect is an agent published in the GitHub repository viknesh20-20/claude-code-tool-kit (7 stars, last pushed 4mo ago), licensed MIT. It adds 76 tokens to every session and 3,020 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 2026-08-31.
Other agents, from other repositories
memory-keeper
Updates .claude/memory.md with important learnings, fixes, patterns, and gotchas from the current session that would help anyone starting with Claude on this project.
ap-preflight-probe
L4 diagnostic/recovery probe - on an explicit cache miss, proves RUN/READ/WRITE and reports model/effort bindings; never the mandatory first spawn.
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
Audit
Deep security + performance audit of a specific diff. Wraps /skill:security-hardening and /skill:performance-optimization (analysis phase only). Use when a change touches auth, untrusted input, secrets, webhooks, PII, or a latency/throughput budget — a focused, read-only risk pass that returns findings the parent…
Marketing Report Builder
Agent "Marketing Report Builder" from muratgur/ordinus, covering role, capabilities, requested work, instructions and marketing report builder.
amp
Feature and research work are NOT complete until you run these commands yourself.