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/so-what)<a href="https://agentmods.dev/commands/aznatkoiny/zai-skills/so-what"><img src="https://agentmods.dev/badge/commands/aznatkoiny/zai-skills/so-what/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/so-what"><img src="https://agentmods.dev/badge/commands/aznatkoiny/zai-skills/so-what.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 | $0.00014 | $0.00679 |
| Opus 5.5 | $0.00006 | $0.00272 |
| Sonnet 5.5 | $0.00003 | $0.00136 |
| Haiku 4.5 | $0.00001 | $0.00068 |
Grade A, and why
so-what 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 1mo 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. The "so what" is the single most important consulting skill — it separates insight from observation. Data tells you what happened. The "so what" tells you why it matters. The "now what" tells you what to do about it. Most analysis fails at the partner level because it stops at data.
Take this analysis and extract the strategic implications: $ARGUMENTS
-
DATA — What does the evidence show? State it in one factual sentence. No interpretation yet.
- Example: "Revenue grew 12% YoY but gross margin declined 300bps to 42%"
-
SO WHAT — Why does this matter strategically? This is the insight layer. Connect the data to a business implication that changes how someone should act or decide.
- Bad "so what" (just restating the data): "Margins are declining" — this is observation, not insight
- Good "so what": "The company is buying growth through pricing concessions, and at current trajectory will hit a margin floor that makes the business model uneconomic within 18 months"
-
NOW WHAT — What specific action does this imply? Who should do what, by when?
- Example: "The CFO should commission a price-volume-mix analysis within 2 weeks to isolate whether the margin erosion is driven by mix shift, discounting, or input costs — each requires a fundamentally different response"
After processing each finding, synthesize into:
- GOVERNING THOUGHT — the single most important takeaway that ties all findings together. This is the sentence that would go on slide 1 of a board deck. It must be:
- A complete, assertive sentence (not a question or topic)
- Supported by the evidence analyzed
- Actionable — it should imply what needs to happen next
- Bad: "The company faces several challenges and opportunities"
- Good: "The company must pivot from volume-driven growth to margin-accretive growth within 12 months or risk a liquidity event as the credit facility reprices in Q3 2027"
<output_format> For each finding:
| Layer | Content |
|---|---|
| DATA | [one factual sentence] |
| SO WHAT | [the strategic insight] |
| NOW WHAT | [specific action, owner, timing] |
Then: GOVERNING THOUGHT: [single synthesizing sentence] IMPLICATIONS: 3-5 bullets on what this means for the overall strategy/engagement </output_format>
<anti_patterns>
- Restating data as insight ("revenue grew" is not a "so what")
- Weasel words: "might," "could potentially," "it is possible that" — take a position
- Generic actions: "further analysis needed" is not a "now what" — specify what analysis, by whom
- Missing the synthesis: individual "so whats" without a governing thought is analysis without conclusion </anti_patterns>
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.
- 1mo ago First seen · 52 lines · 14 tokens per session scan A f16b8b62eccf
so-what is a command published in the GitHub repository Aznatkoiny/zAI-Skills (10 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 679 once invoked, about $0.0001 per session on Opus 5.5. 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
budget
Manage the token budget for Claude Code sessions. Model-aware — picks the right effective context window and prices per model. The session's REAL model is read from the transcript by the budget hook; config.model is only the fallback. Everything from Sonnet 4.6 up is 1M; Haiku 4.5 is 200K.
orchestrate
Do this task as an orchestrator. The aim is the same result at a fraction of the cost: in a long session, every token in this conversation is re-read on each later request, while a subagent's reading is discarded when it returns. The plugin's subagents run on Haiku 5.5, about 40× cheaper per token than Opus 5.5.
conjure-agent
Creates or updates a Claude Code agent definition (/.claude/agents/ .md or project-local).
conjure
Use when you want to build a new Claude Code skill, agent, hook, or MCP server but aren't sure which — or when you want to describe what you want in plain language. Auto-detects the right artifact type, asks targeted questions, explains the reasoning, then builds it.
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.
conjure-help
Show help for the conjure toolkit — all commands, argument syntax, update modes, and decision guide. Use when you want to know which conjure command to use or how any conjure command works.