Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Aznatkoiny/zAI-Skills/plugin install consulting-toolkitWrote 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/commands/aznatkoiny/zai-skills/business-case)<a href="https://agentmods.dev/commands/aznatkoiny/zai-skills/business-case"><img src="https://agentmods.dev/badge/commands/aznatkoiny/zai-skills/business-case/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/commands/aznatkoiny/zai-skills/business-case"><img src="https://agentmods.dev/badge/commands/aznatkoiny/zai-skills/business-case.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 | $0.00009 | $0.00800 |
| Opus 5 | $0.00005 | $0.00400 |
| Sonnet 5 | $0.00002 | $0.00160 |
| Haiku 4.5 | $0.00001 | $0.00080 |
Grade A, and why
business-case 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 10d 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.
What it actually says
You are a senior consultant at a top-tier strategy firm building a business case for an investment committee or board audience. The business case must answer one question definitively: "Should we do this, and why?" It combines strategic logic, financial rigor, and implementation reality into a single decision document.
Build a business case for: $ARGUMENTS
-
OPTIONS ANALYSIS — Present 2-3 credible options PLUS the "do nothing" baseline:
- Option 0: Status quo / do nothing (this is the baseline everything else is measured against)
- Option 1-3: Each with a one-paragraph description, key pros, key cons, and order-of-magnitude financial impact
- The options must be genuinely different strategic paths, not slight variations of the same approach
-
RECOMMENDED OPTION — State your recommendation clearly and explain why it beats the alternatives. Address the strongest objection to your recommendation directly — don't ignore it.
-
FINANCIAL IMPACT — for the recommended option:
- Investment required (capex, opex, one-time costs) with phasing
- Expected returns: NPV, IRR, ROI, payback period
- Key assumptions driving the financial case (clearly separated and labeled)
- Scenario analysis: base case, upside (+20%), downside (-20%)
- Break-even analysis: what has to be true for this to return the cost of capital?
-
IMPLEMENTATION PLAN — high-level phases and timeline:
- Phase gates and decision points
- Key milestones
- Resource requirements
- Quick wins available in Phase 1
-
RISKS AND MITIGATIONS — the 5-7 most material risks:
- For each: description, likelihood, impact, mitigation plan
- Separate strategic risks from execution risks
- Identify any "deal-killer" risks that would change the recommendation
-
DECISION REQUEST — state precisely what needs to be approved:
- The specific commitment being asked for (funding, headcount, timeline, authority)
- What happens if the decision is delayed
- Proposed governance and reporting structure
<output_format> Create two deliverables:
-
Narrative document (business-case-[topic].md): The full business case following the structure above, written in clear prose suitable for a board pack. Target 3-5 pages.
-
Financial model skeleton (business-case-[topic]-model.md): Start from
${CLAUDE_PLUGIN_ROOT}/templates/financial-model-narrative.md— it prewires the assumptions, drivers, scenarios, and sensitivities sections. A structured outline of the financial model showing:- Assumptions sheet (all input variables with values and sources)
- Revenue/cost build-up logic
- Scenario definitions
- Output summary (NPV, IRR, payback by scenario)
- Sensitivity variables This skeleton should be detailed enough to hand to a financial modeler for build-out. </output_format>
<quality_standards>
- The "do nothing" option must be genuinely analyzed, not dismissed as a straw man.
- Financial projections must show assumptions transparently — no black-box numbers.
- The recommendation must directly address the strongest counterargument.
- Implementation plan must be realistic, not aspirational. Flag where scope or timeline tension exists. </quality_standards>
Save both files to the working directory.
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.
- 10d ago First seen · 65 lines · 9 tokens per session scan A 5ea907edd068
business-case is a command published in the GitHub repository Aznatkoiny/zAI-Skills (9 stars, last pushed 1mo ago), licensed MIT. It adds 9 tokens to every session and 800 once invoked, about $0.0000 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 commands, from other repositories
cost-optimize
You are a cloud cost optimization expert specializing in reducing infrastructure expenses while maintaining performance and reliability. Analyze cloud spending, identify savings opportunities, and implement cost-effective architectures across AWS, Azure, and GCP.
strip
This is the task-based stripper, not the always-on prior: a deliberate cleanup pass you asked for. Apply the fp-minify doctrine to the target and remove or compress comments that don't earn their place.
setup
A command that creates a Korean-language CLAUDE.md project guide from a template. CLAUDE.md is a file containing instructions and project context for the Claude coding assistant.
dock-chat
Dock the full conversation to Telegram — drive Claude from your phone.
conjure-agent
Creates or updates a Claude Code agent definition (/.claude/agents/ .md or project-local).
conjure-mcp
Create a Claude Code MCP (Model Context Protocol) server. Provide a description of what external system or data source you want Claude to connect to.