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/company-profile)<a href="https://agentmods.dev/commands/aznatkoiny/zai-skills/company-profile"><img src="https://agentmods.dev/badge/commands/aznatkoiny/zai-skills/company-profile/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/company-profile"><img src="https://agentmods.dev/badge/commands/aznatkoiny/zai-skills/company-profile.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 | $0.00603 |
| Opus 5 | $0.00005 | $0.00302 |
| Sonnet 5 | $0.00002 | $0.00121 |
| Haiku 4.5 | $0.00001 | $0.00060 |
Grade A, and why
company-profile 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 preparing a company profile for a partner briefing. The profile must be fact-dense, sourced, and opinionated — not a Wikipedia summary. A good profile tells the reader what this company is, what it's doing, and what to watch for.
Create a company profile for: $ARGUMENTS
Data sourcing: if this is a US public company, first pull fundamentals with mcp__financial-intelligence__fin_get_company_financials, market cap and price context with mcp__financial-intelligence__fin_get_stock_data, and risk factors from the latest 10-K with mcp__financial-intelligence__fin_get_filing_text; cite as [SEC EDGAR, date]. Use WebSearch for private companies and market estimates. If the MCP tools are unavailable, fall back to WebSearch and state so.
-
BUSINESS MODEL — how they make money. Revenue streams, customer segments, pricing model, unit economics if available. Be specific: "SaaS subscription revenue from mid-market enterprises" not "sells software."
-
COMPETITIVE POSITION — where they sit in their market. Market share if available. Key differentiators vs. top 2-3 competitors. Defensibility of their position (network effects, switching costs, scale advantages, IP).
-
STRATEGIC TRAJECTORY — recent moves that signal direction: M&A, partnerships, product launches, geographic expansion, leadership changes. What story do these moves tell about where the company is heading?
-
KEY RISKS — the 3-5 things that could derail the thesis. Be specific and non-obvious: not "competition" but "Customer concentration: top 3 clients represent ~40% of revenue [Source]."
-
BOTTOM LINE — one paragraph with your assessment: what is this company, strategically? Is it a growth story, a turnaround, a cash cow, a platform play? What is the single most important thing to understand about this business?
<quality_standards>
- Every quantitative data point must have a bracketed source: [Source, Date].
- When data is unavailable, say so explicitly — never fabricate.
- Keep total length to approximately one page (600-800 words).
- Write in clear, direct prose. This is a briefing document, not an essay.
- Lead with insight, not description. </quality_standards>
Save output as company-profile-[name].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 · 39 lines · 9 tokens per session scan A 09bcbfad8e77
company-profile 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 603 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
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.