influencing-and-persuading

influencing-and-persuading is a skill for Claude Code from fatihguner/foreman. It costs 125 tokens per session (4,030 once invoked), scanned A, original, MIT.

A guide to persuading stakeholders through careful questions, listening, patience, and techniques that help people reach a decision without a hard sales pitch.

In plain words
What is it for?
Use it in sales conversations, fundraising, partnership discussions, and efforts to gain support for a proposal.
Why use it?
It helps when talking too much or pushing an idea directly causes resistance instead of agreement.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the foreman plugin — 142 skills, 60 commands, 7 agents shipped together

Good fit Use it in sales conversations, fundraising, partnership discussions, and efforts to gain support for a proposal.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/fatihguner/foreman/influencing-and-persuading
Install

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.

Any agent
npx skills add fatihguner/foreman --skill influencing-and-persuading
Clone the repo
git clone --depth 1 https://github.com/fatihguner/foreman

Made for: Claude Code.

Or install foreman, the plugin that ships this one along with the rest of its 142 skills, 60 commands, 7 agents.

Wrote 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.

agentmods badge for influencing-and-persuading

README.md
[![agentmods](https://agentmods.dev/badge/skills/fatihguner/foreman/influencing-and-persuading/github.svg)](https://agentmods.dev/skills/fatihguner/foreman/influencing-and-persuading)
Your own site
<a href="https://agentmods.dev/skills/fatihguner/foreman/influencing-and-persuading"><img src="https://agentmods.dev/badge/skills/fatihguner/foreman/influencing-and-persuading/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.

agentmods 80×15 button for influencing-and-persuading

Your own site · 80×15
<a href="https://agentmods.dev/skills/fatihguner/foreman/influencing-and-persuading"><img src="https://agentmods.dev/badge/skills/fatihguner/foreman/influencing-and-persuading.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 125 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,030 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00125 $0.04030
Opus 5 $0.00063 $0.02015
Sonnet 5 $0.00025 $0.00806
Haiku 4.5 $0.00013 $0.00403

Measured 6d ago against content hash fb02d8e4feaa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

influencing-and-persuading 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 6d 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.

plugins/foreman/skills/influencing-and-persuading/SKILL.md · 260 lines

How it starts

The opening of the file, as written. The whole thing — 260 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.

Influencing and Persuading

SHUT UP. The most powerful persuasion tool is not a pitch deck, not a compelling argument, not even a brilliant idea. It is silence. The discipline to close one's mouth, ask a question, and wait -- genuinely wait -- while the other person fills the void with their own reasoning, their own objections, and eventually their own path to the conclusion you wanted them to reach all along. A Radio Disney sales rep once closed the largest contract of his career without demoing the product. He asked questions for twenty-five minutes. The buyer interrupted him to say: "Let's get started. Just let me know how billing works." Almost nobody can do this. Founders, by temperament, are talkers -- passionate, enthusiastic, overflowing with conviction. That enthusiasm is both their greatest asset and their most reliable saboteur.

Carnegie documented the principle in 1936. What follows is not a repetition of those timeless rules (see carnegie-win-friends for the canonical framework) but a complementary set of tactical behaviours -- specific, modern, and suited to the asymmetric power dynamics that founders navigate daily: pitching people with more money, persuading people with more authority, and influencing people who have no obligation to listen.


The Framework

Influence, practised well, operates through ten interlocking techniques. They are not sequential steps but a repertoire -- deployed situationally, combined as context demands.

Technique 1: Socratic Idea-Seeding

The most effective way to get someone to adopt your idea is to make them believe they invented it. The mechanism is straightforward:

  1. Never say "I have an idea." Remove the first-person pronoun from the equation entirely.
  2. Paint the broad strokes. Describe the desired outcome or the problem's contours. Let the other person colour inside the lines.
  3. Alternatively, paint the negative. Describe what happens if the idea is not adopted. The listener's mind will generate a solution to prevent that outcome -- your solution.
  4. Embrace instantly. The moment the other person articulates anything resembling your idea, praise it as theirs. Enthusiastically.
  5. Refine gently. If their version is not quite right, suggest additions to "their" idea, reinforcing ownership throughout.

Read the full file on GitHub · 260 lines

Changes

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.

  1. 6d ago First seen · 260 lines · 125 tokens per session scan A fb02d8e4feaa

Subscribe to this mod's changes

influencing-and-persuading is a skill published in the GitHub repository fatihguner/foreman (50 stars, last pushed 7d ago), licensed MIT. It adds 125 tokens to every session and 4,030 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 2026-09-06.