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/market-size)<a href="https://agentmods.dev/commands/aznatkoiny/zai-skills/market-size"><img src="https://agentmods.dev/badge/commands/aznatkoiny/zai-skills/market-size/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/market-size"><img src="https://agentmods.dev/badge/commands/aznatkoiny/zai-skills/market-size.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 | $0.00012 | $0.00764 |
| Opus 5 | $0.00006 | $0.00382 |
| Sonnet 5 | $0.00002 | $0.00153 |
| Haiku 4.5 | $0.00001 | $0.00076 |
Grade A, and why
market-size 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 producing partner-review-ready market sizing. Every number must be sourced or explicitly marked as an assumption. The output must be rigorous enough to anchor a board-level investment decision.
Perform a comprehensive market sizing for: $ARGUMENTS
Data sourcing: pull macro context (GDP, CPI, rates) with mcp__financial-intelligence__fin_get_macro_indicators, cited as [FRED, date], and US public players' revenues with mcp__financial-intelligence__fin_get_company_financials, cited as [SEC EDGAR, date], before web searching. Use WebSearch for market reports, private companies, and analyst estimates. If the MCP tools are unavailable, fall back to WebSearch and state so.
-
TOP-DOWN SIZING — start from the largest credible published figure and apply successive splits to narrow to the target market. Show each step as a chain:
- Total industry revenue (source) → applicable geography share → relevant segment share → target market
- Every split factor must have a source or be flagged as an estimate with stated rationale.
-
BOTTOM-UP SIZING — build from unit economics:
- Number of potential customers × average spend × purchase frequency
- Clearly state how you estimated each variable.
- This approach serves as a cross-check, not just a secondary number.
-
TRIANGULATE — compare the two approaches. If they diverge by more than 30%, investigate why. Common causes: different scope definitions, outdated top-down data, or overly optimistic bottom-up assumptions. Arrive at a defensible range, not a false-precision point estimate.
-
SIZE THE LAYERS:
- TAM: Total addressable market — the full revenue opportunity if 100% market share
- SAM: Serviceable addressable market — the portion reachable given business model and go-to-market constraints
- SOM: Serviceable obtainable market — realistic capture given competitive dynamics and ramp time
- Define each layer specifically for this market, not with generic definitions.
<output_format>
Start from the skeleton at ${CLAUDE_PLUGIN_ROOT}/templates/market-sizing.md — it prewires the sizing chains, the TAM/SAM/SOM table, and the assumptions table with its mandatory source column. Structure the deliverable as:
- Executive summary (3-5 bullets with the headline numbers)
- Market definition and scoping choices
- Top-down sizing (show the math step by step)
- Bottom-up sizing (show the math step by step)
- Triangulation and reconciliation
- TAM / SAM / SOM summary table
- Key assumptions table (assumption | value | source | confidence level)
- Sensitivity analysis on the 2-3 assumptions that most move the number
- Sources list </output_format>
<quality_standards>
- Use web search to find real, current data. Never fabricate or hallucinate numbers.
- Distinguish clearly between hard data, analyst estimates, and your own calculations.
- Flag data gaps explicitly rather than papering over them with false precision.
- Every quantitative claim must have a bracketed source: [Source, Date].
- Present ranges rather than point estimates where the data warrants it. </quality_standards>
Save output as market-sizing-[topic].md in 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 · 54 lines · 12 tokens per session scan A 778ea318ebf6
market-size is a command published in the GitHub repository Aznatkoiny/zAI-Skills (9 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 764 once invoked, about $0.0001 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
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.
conjure-config
Set, view, or remove conjure preferences. Asks questions to understand what you want, then writes plain-language instructions that conjure commands follow automatically.
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.
undock
Undock from Telegram — resume normal terminal replies and approvals.
dock-approvals
Route Claude Code permission prompts to Telegram — step away briefly.