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.
git clone --depth 1 https://github.com/Aznatkoiny/zAI-SkillsWrote 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/size-the-prize)<a href="https://agentmods.dev/commands/aznatkoiny/zai-skills/size-the-prize"><img src="https://agentmods.dev/badge/commands/aznatkoiny/zai-skills/size-the-prize/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/size-the-prize"><img src="https://agentmods.dev/badge/commands/aznatkoiny/zai-skills/size-the-prize.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 | $0.00743 |
| Opus 5 | $0.00005 | $0.00371 |
| Sonnet 5 | $0.00002 | $0.00149 |
| Haiku 4.5 | $0.00001 | $0.00074 |
Grade A, and why
size-the-prize 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 11d 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 sizing the financial impact for a CFO or investment committee audience. The output must be rigorous enough to anchor a go/no-go decision. Show your math transparently — credibility comes from methodology, not precision.
Size the financial impact of: $ARGUMENTS
Data sourcing: ground baselines in real data — for US public companies call mcp__financial-intelligence__fin_get_company_financials (baseline revenue and cost structure) and mcp__financial-intelligence__fin_get_industry_benchmarks (peer performance benchmarks), cited as [SEC EDGAR, date]; pull discount-rate and inflation context with mcp__financial-intelligence__fin_get_macro_indicators, cited as [FRED, date]. Use WebSearch for private companies and market estimates. If the MCP tools are unavailable, fall back to WebSearch and state so.
-
SIZE EACH DRIVER — for each material value driver:
- State the baseline (current state)
- Define the improvement opportunity (target state)
- Show the math: baseline × improvement % = impact, or bottom-up unit calculation
- Assign a confidence level (High: >70% certainty / Medium: 40-70% / Low: <40%)
- List key assumptions that drive the estimate
- Specify the time horizon for realization (Year 1, Year 2, steady state)
-
RISK-ADJUST — apply realization factors:
- Historical capture rates for similar initiatives (typically 50-70% of identified value)
- Implementation risk discount
- Confidence-weighted aggregate: weight each driver by its confidence level
-
AGGREGATE — present total addressable value, expected realized value, and the range (P10 to P90 if possible). Show both annual run-rate and NPV over 3-5 years.
-
SENSITIVITY — identify the 2-3 assumptions that most swing the total. Show what happens to the bottom line if each moves ±20%.
<output_format> Structure as a one-page-ready deliverable:
HEADLINE: [Total addressable value] with [expected realized value] after risk adjustment
Value driver summary table:
| Driver | Annual Impact | Confidence | Realization Factor | Risk-Adjusted |
|---|
Detailed sizing (one section per material driver with the math shown)
Sensitivity analysis: What moves the number most
Key assumptions and risks: What has to be true for this to work
Recommendation: Given the sizing, is this worth pursuing? What's the decision threshold? </output_format>
<quality_standards>
- Show all math transparently. No black-box numbers.
- Every assumption must be stated and sourced where possible.
- Use ranges, not false-precision point estimates.
- Distinguish between one-time and recurring impact.
- Always include the "do nothing" counterfactual as baseline. </quality_standards>
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.
- 11d ago First seen · 62 lines · 9 tokens per session scan A 30867e3e2f7b
size-the-prize 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 743 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.