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.
npx skills add ConrayGambit/Strategy-Consultant-5-Consulting-Frameworks --skill so-what-testgit clone --depth 1 https://github.com/ConrayGambit/Strategy-Consultant-5-Consulting-FrameworksWrote 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/skills/conraygambit/strategy-consultant-5-consulting-frameworks/so-what-test)<a href="https://agentmods.dev/skills/conraygambit/strategy-consultant-5-consulting-frameworks/so-what-test"><img src="https://agentmods.dev/badge/skills/conraygambit/strategy-consultant-5-consulting-frameworks/so-what-test/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/skills/conraygambit/strategy-consultant-5-consulting-frameworks/so-what-test"><img src="https://agentmods.dev/badge/skills/conraygambit/strategy-consultant-5-consulting-frameworks/so-what-test.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 | $0.00050 | $0.01017 |
| Opus 5 | $0.00025 | $0.00508 |
| Sonnet 5 | $0.00010 | $0.00203 |
| Haiku 4.5 | $0.00005 | $0.00102 |
Grade A, and why
so-what-test 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The "So What?" Test
Concept
Most analyses fail at the last step. People surface findings, lay out data, and stop — leaving the reader to figure out what it means and what to do. The "So What?" test forces you to close the loop: every finding must lead to an action specific enough to assign.
A finding without a "so what" is trivia. A finding with a "so what" is a recommendation.
Required output format
Three explicitly labeled sections, in this order:
**Process:** [What specific data, workflow, or factor was analyzed.]
**Result:** [The objective outcome — numbers, signals, observations.]
**Insight:** [The underlying reason this matters + the immediate action. Specific enough to assign to a person with a deadline.]
Defaults & flex points
| Default | When to flex |
|---|---|
| Process is one or two clauses | Don't flex — long preamble buries the answer. |
| Result has numbers or specific observations | Don't flex — vague Results undermine the Insight. |
| One Insight per block | If multiple actions are warranted, write multiple So What blocks rather than one Insight with three bullets. |
| Insight names who, what, and by when | Don't flex — that's the test. |
The assignability test: could you copy your Insight into an assignment to a named person with a deadline, and would they know what to do? If not, rewrite it.
Example — HR / people analytics
Problem: Mid-level engineering attrition has risen for three consecutive quarters. The VP of Engineering wants to know why and what to do.
Bad
Process: Looked at attrition data.
Result: Attrition went up.
Insight: We should focus on retention.
(Process is too vague. Result has no number. Insight is unassignable. Three failures.)
Better
Process: Joined exit-interview transcripts (n=24) with promotion-cycle data, comp-band placement, and manager-tenure data for all mid-level engineers (L4–L5) who left between Q2 of last year and Q1 of this year. Compared to a control cohort of L4–L5 engineers who stayed.
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.
- 12d ago First seen · 78 lines · 50 tokens per session scan A 0e70ce3b743e
so-what-test is a skill published in the GitHub repository ConrayGambit/Strategy-Consultant-5-Consulting-Frameworks (23 stars, last pushed 3mo ago), licensed MIT. It adds 50 tokens to every session and 1,017 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
thinking-theory-of-constraints
When throughput or latency is pipeline-limited, identify the single binding constraint and exploit, subordinate, elevate, then recheck—ignore non-constraints.
Vizra ADK Memory System
Implement persistent memory, session context, and vector memory (RAG) for AI agents.
foundation-models
On-device LLM integration using Apple's Foundation Models framework. Use when implementing AI text generation, structured output, or tool calling.
analytics-interpretation
Interpret app metrics and make data-driven decisions. Covers DAU/MAU, retention, LTV, ARPU, App Store Connect analytics, AARRR funnel analysis, cohort analysis, and diagnostic decision trees. Use when user wants to understand their metrics, diagnose problems, or build a data-driven growth plan.
app-namer
Turn an app idea into validated, App-Store-ready name candidates. Use when the user says "name my app", "what should I call it", "app name ideas", "help me name this app", "is this name available", or needs to pick a brandable, ownable name before reserving it in App Store Connect.
in-app-events
Generates In-App Event metadata templates for App Store Connect — event names, descriptions, badge types, image specs, and deep link configuration. Use when creating events for App Store visibility, engagement campaigns, or seasonal promotions.