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 fatihguner/foreman --skill ai-purpose-driven-questionsgit clone --depth 1 https://github.com/fatihguner/foremanWrote 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/fatihguner/foreman/ai-purpose-driven-questions)<a href="https://agentmods.dev/skills/fatihguner/foreman/ai-purpose-driven-questions"><img src="https://agentmods.dev/badge/skills/fatihguner/foreman/ai-purpose-driven-questions/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/fatihguner/foreman/ai-purpose-driven-questions"><img src="https://agentmods.dev/badge/skills/fatihguner/foreman/ai-purpose-driven-questions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00086 | $0.03375 |
| Opus 5 | $0.00043 | $0.01688 |
| Sonnet 5 | $0.00017 | $0.00675 |
| Haiku 4.5 | $0.00009 | $0.00337 |
Grade A, and why
ai-purpose-driven-questions 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 4d 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read runtime and advisory rules before applying this skill. Other Foreman layers and the catalog are in ../../content/, relative to this SKILL.md.
AI Purpose-Driven Questions
Most leaders ask the wrong first question about AI. They ask "Which AI tool should we use?" or "What can AI do for us?" -- questions that position technology as the starting point and the organisation as the beneficiary of whatever the algorithms happen to produce. Garry Kasparov, the chess grandmaster who lost to IBM's Deep Blue in 1997, offers a sharper frame. "Machines don't have understanding," he told a TechCrunch audience. "They don't have a purpose." Neither, it turns out, do most AI deployments. A large telecom company deployed AI to predict customer churn, then bombarded at-risk customers with advertising. Many left anyway. The AI had answered the wrong question. It identified who was likely to leave rather than who could be persuaded to stay -- a distinction no algorithm could make without a human defining the purpose of the analysis. The technology worked perfectly. The leadership failed entirely.
The Framework
Why Purpose Must Precede Technology
The second pillar of AI-savvy leadership rests on an uncomfortable observation: most business leaders cannot clearly articulate why their organisation exists. When asked what their company aims to achieve beyond making profits, they produce the same boilerplate values that appear on every corporate website. This vagueness is tolerable in ordinary operations. It becomes fatal when deploying AI, because AI systems require precise questions to produce useful answers, and those questions can only emerge from a clear understanding of organisational purpose.
The failure pattern is consistent:
- Leaders declare the company a "data company" and invest millions in data infrastructure.
- Data scientists amass enormous datasets and build sophisticated models.
- The models produce insights that are technically impressive but strategically meaningless -- answering questions nobody in leadership thought to ask.
- Leaders adopt the data scientists' conclusions as strategy, inverting the proper relationship between business leadership and technical analysis.
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.
- 4d ago Changed · +202 lines · +86 tokens per session 368de5ce3c41
- 10d ago First seen · 1 lines · 0 tokens per session scan A 08a0ebd069be
ai-purpose-driven-questions is a skill published in the GitHub repository fatihguner/foreman (50 stars, last pushed 5d ago), licensed MIT. It adds 86 tokens to every session and 3,375 once invoked, about $0.0004 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
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.
stss
Reduce defensive disclaimers, stacked hedging, and self-protective narration in proposals and decision-facing writing. Use when the user asks to rewrite or audit a proposal, plan, research contribution, executive summary, or similar text for directness. Do not use for ordinary code work or unrelated prose.
superloopy-frontend
Use only after explicit Codex $superloopy:superloopy-frontend or Claude Code /superloopy:superloopy-frontend invocation for supported screen-based application UI across browser-hosted Web, interactive deployed content-led Web, desktop, mobile/tablet, embedded/hybrid, Qt, custom-rendered, or mixed targets, such a task…