Agent skill · Audited from source

influence

skill · getagentseal/founder-playbookMIT licenceAudited 26 Oct 2026 · source 5015fcf4cde3

★ 778pushed 19 days ago
✓SAFEGrade B · 89/100 · 26 Oct 2026 · 5015fcf
778repo stars · whole getagentseal/founder-playbook

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 5015fcf4cde3 and found no filesystem, network or shell access and no hard-coded secrets. What it does: Cialdini's seven principles of compliance (the classic six — reciprocation, commitment-consistency, social proof, liking, authority, scarcity — plus Unity, added 2016) and Pre-Suasion. Use when crafting ethical…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “influence (getagentseal/founder-playbook)”. Retrieved 26 Oct 2026. https://modelsatlas.com/skills/getagentseal/influence

Trust audit

Audit 0.4.1 · source read 26 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium0 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 13,985 of 14,816 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (0)

No findings at any severity. We re-audit when the source changes.

Audit 0.4.1 · source sha 5015fcf4cde3 · 26 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publishergetagentseal GitHub organizationOwner of the repository this skill is read from
  • Source foldergetagentseal/founder-playbook/skills/influenceThe exact folder we audited
  • LicenceMITAs the repository states it
  • Commit pinned for this verdict5015fcf4cde3A new audit runs when the source changes
  • Repository statusNot archivedLast push 19 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Cialdini's seven principles of compliance (the classic six — reciprocation, commitment-consistency, social proof, liking, authority, scarcity — plus Unity, added 2016) and Pre-Suasion. Use when crafting ethical…

---
name: influence
description: Cialdini's seven principles of compliance (the classic six — reciprocation, commitment-consistency, social proof, liking, authority, scarcity — plus Unity, added 2016) and Pre-Suasion. Use when crafting ethical persuasion (marketing, sales, negotiation), defending against manipulation, or designing systems that need cooperation. Includes replication-crisis caveats and known factual corrections (Bickman parking-meter numbers, Hofling modern replication, Drive Carefully condition disambiguation, Genovese myth).
---

> **Note:** This skill is independent analysis and commentary, not a reproduction of the original text. It synthesizes the book's core ideas with modern startup practice, surfaces where frameworks are outdated or incomplete, and integrates perspectives from adjacent disciplines. For the full argument and context, read the original book.


# Influence

> "Click-whirr. The triggers fire and we react automatically." - Robert Cialdini

## When to Use

- Crafting persuasion (marketing, sales copy, negotiation)
- Defending against manipulation (recognizing when you're being clicked)
- Designing systems that need cooperation
- Diagnosing why some campaigns work and others don't

## Critical Caveats (Read First)

**This skill is about a 1984 book with significant replication issues. Several specific cited numbers are wrong or contested. Treat the principles as TACTICAL RECOGNITION FRAMEWORKS, not precise math.**

### Known Replication Concerns

| Issue | Status |
|-------|--------|
| **Kitty Genovese "38 witnesses" myth** | Factually false. Manning, Levine & Collins (2007, *American Psychologist*) debunked. Most "witnesses" couldn't see/hear, several DID call police. Cialdini repeats the false narrative; this skill DOES NOT use Genovese as evidence. We rely only on the lab studies (Latane & Darley) which DO replicate. |
| **Bargh-style priming** | Largely failed to replicate |
| **Ego depletion** | Failed multiple replications |
| **Milgram 65%** | From ONE of 24 conditions. Range was 0-92%. Burger 2009 partial replication ~70% (capped at 150V). Perry 2012 archival critique disputes Milgram's reporting. |
| **Romeo-Juliet effect** | Contested by Sinclair (2014) |
| **Halo-effect numbers** | Generally shrunken on replication |
| **"Because" experiment** | Effect collapses for higher-cost requests |
| **DITF backfire condition** | If first request is too extreme, you appear unreasonable and lose the second |
| **Hofling 95%** | Original 1966 number. Modern replications find 16-30% (nurses now have explicit refusal training). |
| **Bystander effect in clear emergencies** | Fischer et al. 2011 meta-analysis: groups DO help more when threat is clear. Reverses original finding. |

### WEIRD Bias

Most experiments used Western, Educated, Industrialized, Rich, Democratic college students. "Universal across cultures" overclaims. East Asian collectivist cultures often show different social proof and authority dynamics.

### Bottom Line

The 6+1 principles are real and useful as a tactical recognition framework. Specific effect sizes are unreliable. **Treat as "these are the levers" - not "this is the precise math."**

## The Core Insight: Click-Whirr

Animals (and humans) often act on **fixed action patterns** triggered by single features. One trigger feature → automatic compliance, even when situation doesn't warrant it.

> "The future will see an increased use of decisional shortcuts. As the pace of modern life accelerates and information mounts, we'll be forced to use them more, not less."

The 6+1 principles are humanity's most powerful heuristics - which makes them the most powerful persuasion levers.

## The Seven Principles

| # | Principle | Core Rule |
|---|-----------|-----------|
| 1 | **Reciprocation** | When someone gives, we feel obligated to return |
| 2 | **Commitment & Consistency** | Once committed, we behave consistently |
| 3 | **Social Proof** | We determine what's correct by what others think is correct |
| 4 | **Liking** | We comply with people we like |
| 5 | **Authority** | We comply with authority figures, often without question |
| 6 | **Scarcity** | Opportunities seem more valuable when limited |
| 7 | **Unity** (added 2016) | We comply more with people we share IDENTITY with |

Plus the bonus: **Contrast** (sequential items - second seems more different than it is).

Detailed experiments and mechanics for each principle: see [principles.md](principles.md).

## The Inner-Choice Insight (Critical)

For Commitment & Consistency, four conditions strengthen a commitment:

| Condition | Why It Works |
|-----------|--------------|
| **Active** | Doing > saying. Writing > thinking |
| **Public** | Witnesses lock you in |
| **Effortful** | More effort, more value |
| **Uncoerced** | Must feel CHOSEN freely |

**Cialdini elevates "uncoerced inner choice" as more important than the other three combined.** Bribes/threats don't create real commitment; only freely-chosen action does. This is why coercive tactics (high-pressure sales, induced obedience) produce compliance but not durable commitment.

## Pre-Suasion (2016)

> "What we present FIRST changes how the audience experiences what comes NEXT."

The persuasive moment isn't only when you make the ask. It's the moments BEFORE, when you set up the listener's mental state.

- "Are you adventurous?" before pitching a new product → adventurous people accept more
- Anchoring high before asking small ($50K mentioned before $5K request)
- Background music in stores (French wine sales up when French music plays)

Detailed Pre-Suasion examples: see [pre-suasion.md](pre-suasion.md).

## How Principles Combine (Real Power)

The principles compound. Effective persuasion uses MULTIPLE principles together.

**Tupperware Party = ALL 6:**
- Hostess gives free gifts (Reciprocity)
- Public commitment to buy (Commitment)
- "Susan loves this product!" (Social Proof + Liking)
- Hostess is your friend (Liking)
- Con

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 5015fcf

Download folder ↗
git clone https://github.com/getagentseal/founder-playbook
git -C founder-playbook checkout 5015fcf4cde3

The author documents no install command, so this uses the repository directly. Our verdict covers commit 5015fcf4cde3 only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source 5015fcf4cde3

Similar skills

Questions about influence

What does the influence skill do?
15 proven business books distilled into AI-native skills. Works with Claude Code, ChatGPT, Gemini, Cursor.
Is influence safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can influence access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (5015fcf4cde3), read on 2026-10-26. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.