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-vision-and-strategygit 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-vision-and-strategy)<a href="https://agentmods.dev/skills/fatihguner/foreman/ai-vision-and-strategy"><img src="https://agentmods.dev/badge/skills/fatihguner/foreman/ai-vision-and-strategy/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-vision-and-strategy"><img src="https://agentmods.dev/badge/skills/fatihguner/foreman/ai-vision-and-strategy.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 | $0.00119 | $0.04047 |
| Opus 5 | $0.00060 | $0.02024 |
| Sonnet 5 | $0.00024 | $0.00809 |
| Haiku 4.5 | $0.00012 | $0.00405 |
Grade A, and why
ai-vision-and-strategy 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 5d 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 — 234 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 Vision and Strategy
Ninety percent of organisations have experimented with AI. Only 17 percent have succeeded in scaling it. The gap between experimentation and institutionalisation is not a technology problem -- it is a vision problem. One CEO, upon deciding to adopt AI, told his leadership team that business strategies of the past would no longer be relevant, that organisations needed to "start thinking like machines," and that AI engineers would become "the voices of the future." The meeting erupted in chaos. Managers asked in near-despair what this meant for their own jobs and their teams. The CEO had presented AI as an inevitability without a human story -- a technology-first vision that offered efficiency but no meaning. Contrast this with a logistics company leader who articulated precisely why AI mattered for inventory management, acknowledged what it could and could not do, set realistic targets, and told her workforce: "We're not using AI simply to use AI. It needs to help and make a difference, or else we will not use it." A year later, the adoption was expanding at every level. The difference between these two leaders was not technical knowledge. It was vision.
The Framework
The Two Perspectives
The framework presents the entire AI leadership challenge as a choice between two fundamentally different perspectives:
Perspective 1: AI as Replacement
AI is an increasingly cheap way to replace people and achieve new levels of productivity and efficiency. Under this view, the primary focus is using AI to make the best use of data and, eventually, to delegate decision-making and thinking to the technology. Leaders who adopt this perspective are, ironically, making themselves redundant. If the logic holds -- if AI can think as well as humans but cheaper -- then leadership itself becomes dispensable.
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.
- 5d ago Changed · +233 lines · +119 tokens per session ac5113736922
- 11d ago First seen · 1 lines · 0 tokens per session scan A 3cd599d0c0d2
ai-vision-and-strategy is a skill published in the GitHub repository fatihguner/foreman (50 stars, last pushed 5d ago), licensed MIT. It adds 119 tokens to every session and 4,047 once invoked, about $0.0006 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
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
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.
corezoid-git-context
Analyzes the current session and updates ext/docs/.md in the Corezoid git mirror for the active stage. Use after corezoid-edit, corezoid-create, or corezoid-review when the session was substantial (processes deployed, new external dependencies discovered, architectural decisions made, issues found or resolved).…
image-context-runtime
Use for image-heavy Codex work when generated or inspected media should stay behind a bounded MCP boundary and the controlling task should receive only durable Job IDs, hashes, relative references, and compact text handoffs.
sprint-plan
Generates a new sprint plan or updates an existing one based on the current milestone, completed work, and available capacity. Pulls context from production documents and design backlogs.