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 carnegie-win-friendsgit 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/carnegie-win-friends)<a href="https://agentmods.dev/skills/fatihguner/foreman/carnegie-win-friends"><img src="https://agentmods.dev/badge/skills/fatihguner/foreman/carnegie-win-friends/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/carnegie-win-friends"><img src="https://agentmods.dev/badge/skills/fatihguner/foreman/carnegie-win-friends.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 | $0.00085 | $0.03617 |
| Opus 5 | $0.00043 | $0.01809 |
| Sonnet 5 | $0.00017 | $0.00723 |
| Haiku 4.5 | $0.00009 | $0.00362 |
Grade A, and why
carnegie-win-friends 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 — 235 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.
Carnegie's How to Win Friends and Influence People
Published in 1936, Dale Carnegie's How to Win Friends and Influence People has sold over 30 million copies, been translated into dozens of languages, and remained continuously in print for nearly nine decades. A time-travel thought experiment clarifies why this matters: if you transported Carnegie's principles to a modern tech startup -- replacing "telegrams" with "Slack messages" and "salesmen" with "founders" -- the advice would require almost no adaptation. The principles work because they address something that has not changed in ninety years: human psychology. People still crave recognition. They still resist being told they are wrong. They still respond to genuine interest more readily than to polished pitches. The surface of business transforms every decade; the social operating system of human beings upgrades on evolutionary timescales. Carnegie mapped that operating system with a precision that keeps his Depression-era book selling in the age of AI.
The question is not whether these principles still apply. The question is why so few founders -- drowning in frameworks for product, growth, and fundraising -- bother to master the foundational skill that underlies all of them: the ability to make other people want to work with you.
The Framework
Carnegie organises his principles into four groups. Each group targets a different domain of interpersonal effectiveness. Below, the original principles are presented alongside modern entrepreneurial applications.
Group 1: Fundamental Techniques in Handling People
Principle 1: Never criticise, condemn, or complain.
Criticism triggers defensive behaviour, not behavioural change. Carnegie observed that even criminals rationalise their actions; direct criticism rarely produces the response the critic intends. The modern parallel: founders who publicly criticise team members, competitors, or investors create fear-based environments and reputational damage.
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 · +234 lines · +85 tokens per session 87865b233047
- 11d ago First seen · 1 lines · 0 tokens per session scan A 042cb402682c
carnegie-win-friends is a skill published in the GitHub repository fatihguner/foreman (50 stars, last pushed 5d ago), licensed MIT. It adds 85 tokens to every session and 3,617 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
stakeholder-alignment
Use when navigating organizational alignment — stakeholder mapping, influence analysis, coalition building, decision archaeology, cross-functional alignment, executive buy-in, or any situation where the path to a decision runs through multiple people with different interests. Produces a stakeholder alignment strategy…
stakeholder-alignment
Use when navigating organizational alignment — stakeholder mapping, influence analysis, coalition building, decision archaeology, cross-functional alignment, executive buy-in, or any situation where the path to a decision runs through multiple people with different interests. Produces a stakeholder alignment strategy…
Decision Helper
Make better decisions using structured frameworks and mental models.
apply-cross-functional-leadership
Use when a manager needs to lead a project or initiative that depends on team members or stakeholders they do not formally manage — to build voluntary cooperation, alignment, and momentum across organizational boundaries through influence rather than authority.
apply-change-leadership
Use when a manager's team is experiencing a significant organizational change — restructuring, strategy shift, leadership change, layoffs, or major process transition — and needs leadership that maintains team stability, preserves trust, and converts uncertainty into direction.
design-team-norms
Use when a team is forming, after a significant membership change, or when a recurring dysfunction suggests the team lacks shared agreements on how to work together — to co-create explicit norms covering communication, decision-making, conflict, and accountability.