Cialdini's seven principles of compliance (the classic six — reciprocation, commitment-consistency, social proof, liking, authority, scarcity — plus Unity, added 2016) and Pre-Suasion.

MITAuto-check passedDatabases

Install Influence

skills CLI
$ npx skills add getagentseal/founder-playbook --skill influence -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install getagentseal/founder-playbook influence --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/getagentseal/founder-playbook.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/influence .claude/skills/influence && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
influence
GitHub stars
721
Token cost
~3.8k tokens
SKILL.md length
1,816 words
Files
5
Skills in repo
16
Repo updated
First seen
Licence
MIT

At a glance

Cialdini's seven principles of compliance (the classic six — reciprocation, commitment-consistency, social proof, liking, authority, scarcity — plus Unity, added 2016) and Pre-Suasion.

  • Works in 10 steps: Confusing volume with quality of social… → Faking the principles - Manufactured… → Using one principle when multiple stack… → …
  • Crafting ethical persuasion (marketing
  • SKILL.md covers When to Use, Critical Caveats (Read First), The Core Insight: Click-Whirr and The Seven Principles, plus 14 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Influence is an agent skill from getagentseal/founder-playbook. 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).

Its SKILL.md is about 3.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files (for example `integration.md`, `pre-suasion.md` and `principles.md`).

It sits in Databases, covering Database administration and Marketing psychology. The repository describes itself as: 15 proven business books distilled into AI-native skills. Works with Claude Code, ChatGPT, Gemini, Cursor. The licence is MIT.

When your agent uses it

  • Crafting ethical persuasion (marketing
  • Defending against manipulation
  • Designing systems that need cooperation

Example prompts

  • “/influence”

Workflow steps

10 steps, taken from the first numbered list in SKILL.md.

  1. Confusing volume with quality of social proof - "10,000 customers" matters less than "10,000 customers SIMILAR to you"
  2. Faking the principles - Manufactured scarcity, paid reviews, fake authority - all eventually backfire
  3. Using one principle when multiple stack - Masters always combine 3+
  4. Forgetting reciprocity expects symmetry - Small gift triggers small reciprocity, not huge purchase
  5. Asking for commitment too big, too fast - Foot-in-the-door wins; door-in-the-face is a separate tactic with backfire risk
  6. Using authority you don't have - "We're the leaders" without proof = pushback
  7. Scarcity without specificity - "Limited time!" forever = no scarcity
  8. Liking without similarity - Generic friendliness < perceived similarity
  9. Forgetting the click-whirr is automatic - Don't over-explain; the trigger does the work
  10. Using these on smart, alert prospects - These work on shortcuts. Educated buyers know the moves and will feel reactance against obvious…

What it can do on your machine

Read from SKILL.md and the folder at commit e811e63. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Influence loads about 3.8k tokens when it runs. Until then it costs about 131 tokens; SKILL.md has 1,816 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~131
When it runs · the whole SKILL.md, loaded when a task matches
~3.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from getagentseal/founder-playbook at commit e811e63, republished under its MIT licence (© getagentseal). 1,816 words, ~3,834 tokens.

Download SKILL.mdSave it as .claude/skills/influence/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
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
IssueStatus
Kitty Genovese "38 witnesses" mythFactually 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 primingLargely failed to replicate
Ego depletionFailed 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 effectContested by Sinclair (2014)
Halo-effect numbersGenerally shrunken on replication
"Because" experimentEffect collapses for higher-cost requests
DITF backfire conditionIf 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 emergenciesFischer 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

#PrincipleCore Rule
1ReciprocationWhen someone gives, we feel obligated to return
2Commitment & ConsistencyOnce committed, we behave consistently
3Social ProofWe determine what's correct by what others think is correct
4LikingWe comply with people we like
5AuthorityWe comply with authority figures, often without question
6ScarcityOpportunities seem more valuable when limited
7Unity (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.

The Inner-Choice Insight (Critical)

For Commitment & Consistency, four conditions strengthen a commitment:

ConditionWhy It Works
ActiveDoing > saying. Writing > thinking
PublicWitnesses lock you in
EffortfulMore effort, more value
UncoercedMust 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.

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)
  • Consultant has credentials (Authority)
  • "Limited time at the party" (Scarcity)

Cult Recruitment = stacked principles:

  • Love bombing = Liking + Reciprocity
  • Public testimonials = Commitment + Social Proof
  • "We're chosen" = Scarcity (special)
  • Leader as authority = Authority

Decision Trees

Am I being manipulated?
Do I feel an unusual urgency to comply?
├─ YES → Likely Reciprocity, Commitment, or Scarcity
│        Stop. Apply the diagnostic question for that principle.
└─ NO → Do I feel oddly drawn to this person/product?
        ├─ YES → Likely Liking or Authority
        │        Separate the dealer from the deal.
        └─ NO → Probably legitimate
Which principle should I use in marketing?
What problem are you solving?
├─ "Why should they trust us?" → Authority + Social Proof
├─ "Why should they buy now?" → Scarcity (genuine, not manufactured)
├─ "Why should they pay premium?" → Liking + Authority
├─ "Why should they refer others?" → Reciprocity + Commitment
├─ "Why should they choose us over X?" → Social Proof from SIMILAR customers
└─ "Why should they not churn?" → Commitment + Consistency

Single-Person Bystander Defense (Critical Technique)

When in distress in a crowd, single out one person:

"YOU in the blue shirt - call 911."

This is one of the most important techniques in the book. Generic appeals to a crowd produce diffusion of responsibility (Latane & Darley lab studies). Direct appeal to a specific individual short-circuits the diffusion.

Critical Numbers (With Caveats)

NumberRuleCaveat
6+1Universal principlesUnity added in 2016
65%Milgram complianceFrom 1 of 24 conditions; range 0-92%
94%"Because" + meaningless reasonEffect collapses for higher-cost requests
76%Drive Carefully billboard agreementAfter agreeing to small 3-inch sign first. Petition-only condition was ~50%.
6xSales increase with scarcity + exclusivity (Knishinsky)Verified in source
35%DAV response with free address labels (vs 18%)Verified
92%Bickman parking-meter compliance in security uniformVerified in source
42%Bickman parking-meter compliance in street clothesVerified in source. (NOT 19% - that figure is unverified.)
3.5xSuit jaywalker followers vs sloppy clothesVerified
4Conditions strengthening commitmentInner choice / uncoerced is more important than other three combined

Common Mistakes

  1. Confusing volume with quality of social proof - "10,000 customers" matters less than "10,000 customers SIMILAR to you"
  2. Faking the principles - Manufactured scarcity, paid reviews, fake authority - all eventually backfire
  3. Using one principle when multiple stack - Masters always combine 3+
  4. Forgetting reciprocity expects symmetry - Small gift triggers small reciprocity, not huge purchase
  5. Asking for commitment too big, too fast - Foot-in-the-door wins; door-in-the-face is a separate tactic with backfire risk
  6. Using authority you don't have - "We're the leaders" without proof = pushback
  7. Scarcity without specificity - "Limited time!" forever = no scarcity
  8. Liking without similarity - Generic friendliness < perceived similarity
  9. Forgetting the click-whirr is automatic - Don't over-explain; the trigger does the work
  10. Using these on smart, alert prospects - These work on shortcuts. Educated buyers know the moves and will feel reactance against obvious stacking.
Show full SKILL.md (761 more words)Show less

Worked Example: Stacked Principles in Cold Outreach

A short B2B SaaS cold email that layers four principles in six sentences, then an anti-example showing the same message stripped of all of them.

The email:

Subject: quick resource on [their pain point]

Hi [Name], I put together a two-page breakdown of how teams like [similar company] cut their onboarding time by 40% - sending it to you no strings attached. ← Reciprocity: leads with concrete value before any ask

I noticed [their company] recently expanded the engineering team; that usually means onboarding overhead spikes. ← Liking (similarity/relevance): shows you've done homework, signals shared context

We've helped six companies in [their space] go from three-week ramp to under one week - the case studies are in the doc. ← Social Proof: peers in same industry, specific outcome

I'm [Name], co-founder of [Product] - we've been building onboarding tooling for four years and published the original research behind the 40% figure. ← Authority: real credential, not just a title

Would a 20-minute call this week make sense? ← Commitment & Consistency (small ask): low-cost first step keeps the foot-in-the-door sequence alive

Either way, the doc is yours.

Why it works: Every sentence does a job. The gift opens the loop (Reciprocity), relevance signals similarity (Liking), peers close the uncertainty gap (Social Proof), credentials justify trust (Authority), and the ask is deliberately small (Commitment entry point). No principle is faked - the doc is real, the case studies are real, the credentials are real.

Anti-example (no principles):

Subject: Increase your team's productivity

Hi [Name], I'm reaching out because I think our product could be a great fit for your company. We have a lot of happy customers and a proven track record. We offer a demo at your convenience. Let me know if you're interested in learning more about our solution.

The anti-example triggers nothing. There is no gift, no proof from similar companies, no credentials, no small commitment step, and no demonstrated knowledge of their situation. It reads like every other cold email in the inbox and gets deleted.

When NOT to Use This Skill (Ethically)

Honest application is fine:

  • Genuine reciprocity (real value first)
  • Real social proof from real customers
  • True authority (verifiable expertise)
  • Genuine scarcity ("I really do have only 3 spots")

Manipulation is not:

  • Fake scarcity ("limited time" forever)
  • Manufactured social proof (paid reviews, AI-generated testimonials)
  • False authority (fake credentials, actor-in-lab-coat)
  • Coerced commitment (high-pressure tactics)

"When practitioners use these principles to deceive, they're mining a deep social trust that makes us all worse off."

The book is partly a defense manual against bad-faith use.

Modern Application (2026)

Where StrongWhere Buyers Resist More
Sales conversationsSophisticated B2B buyers (know all 6)
Marketing copySoftware developers (resistant to obvious manipulation)
Negotiation (reciprocity of concessions)Repeated tactics lose power (100th "limited time" fades)
Online retail (review systems)Trust-erosion era (decades of fake reviews)
Social media (likes, FOMO)AI-generated reviews breaking social proof reliability

Defense Audit (When Buying)

  • Did someone give me something before asking? (Reciprocity)
  • Am I committing because I committed earlier? (Consistency)
  • Am I doing this because everyone else is? (Social Proof)
  • Am I influenced because I like the salesperson? (Liking)
  • Am I deferring to someone's "expert" status? (Authority)
  • Am I rushing because of artificial urgency? (Scarcity)

If 2+ are yes → step back, sleep on it, decide tomorrow.

Self-Audit (Marketing/Sales)

  • Trigger reciprocity (free value first)?
  • Social proof (from SIMILAR customers)?
  • Establish authority (real credentials, awards, experience)?
  • Liking layer (similarity, contact, association)?
  • Create commitment (small steps before big ask)?
  • Legitimate scarcity (real, not manufactured)?

The Big Idea

These 6+1 principles are humanity's most powerful psychological shortcuts. They evolved because they USUALLY serve us well - we'd be paralyzed without them. The same shortcuts can be weaponized.

The framework gives you:

  1. Awareness - Recognize when you're being clicked
  2. Defense - Stop the automatic response
  3. Application - Use the principles ethically
  4. Diagnosis - Understand WHY some campaigns work

The principles are amoral - they describe how influence WORKS, not how it SHOULD work. The ethical question is yours.

"Anywhere we do not have time, energy, or motivation to think carefully and analytically, we'll resort to shortcuts."

In a world drowning in information, shortcuts will only matter more.

Supporting Files

  • principles.md - Full 6+1 principles with experiments, sub-factors, manipulative tactics, defenses
  • pre-suasion.md - The 2016 update: framing, anchoring, priming questions, environmental cues
  • replication-notes.md - Specific failed/contested studies in detail (Bickman correction, Hofling modern replications, Milgram variations, Genovese debunked, Romeo-Juliet, Bargh, ego depletion, Drive Carefully condition disambiguation)
  • integration.md - How principles interact with Mom Test, SPIN Selling, $100M Offers, $100M Leads, Obviously Awesome, Crossing the Chasm, Blue Ocean Strategy, Monetizing Innovation; honest conflicts

© getagentseal, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files in skills/influence of getagentseal/founder-playbook.

  • SKILL.md
  • integration.md
  • pre-suasion.md
  • principles.md
  • replication-notes.md

Open the folder on GitHubat commit e811e63

Compare with similar skills

Influence next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Influence compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Influence this skillgetagentseal/founder-playbook721—~3.8kAutomated safety check: PassMIT
Hybrid Cloud Outboxesgetsentry/sentry45k—~4.8kAutomated safety check: PassCustom licence
Replicate Video AdJingyi-Wu-Richael/replicate-video-ad1061 repos~1.6kAutomated safety check: PassNone
Sea Orm 2FlyinPancake/yoink112—~2.9kAutomated safety check: PassApache-2.0
Pixel Perfect ReplicationYu-369/VibeCurb980—~8.7kAutomated safety check: PassMIT
Horse Database PoolingHashLoad/horse1.4k—~1.4kAutomated safety check: PassMIT

Similar skills

  • Hybrid Cloud Outboxes

    getsentry/sentry

    Official

    Guide for creating and maintaining outbox-based eventually consistent operations in Sentry.

    45k GitHub stars~4.8k tokensUpdated today
    DatabasesAuto-check passed
  • Replicate Video Ad

    Jingyi-Wu-Richael/replicate-video-ad

    Analyze a reference video frame by frame and turn its visual grammar, story beats, dialogue, product reveal, proof sequence, and conversion structure into a production-ready ecommerce story-ad…

    106 GitHub starsUsed in 1 repo~1.6k tokens
    DatabasesAuto-check passed
  • Sea Orm 2

    FlyinPancake/yoink

    Expert guidance for SeaORM 2.0, Rust's async ORM with strongly-typed columns, nested ActiveModels, Entity Loader API, and entity-first workflow.

    112 GitHub stars~2.9k tokensUpdated 3 days ago
    DatabasesAuto-check passed
  • Image-to-code replication pipeline. An agent skill from Yu-369/VibeCurb.

    980 GitHub stars~8.7k tokensUpdated 2 mo ago
    DatabasesAuto-check passed
  • Guide for setting up thread-safe database connection pooling (FireDAC / UniDAC) in multithreaded Horse applications.

    1.4k GitHub stars~1.4k tokensUpdated yesterday
    DatabasesAuto-check passed
  • Redis Clustering

    redis/agent-skills

    Official

    Redis Cluster and replication guidance covering hash tags for multi-key operations, avoiding CROSSSLOT errors, and reading from replicas to scale read-heavy workloads.

    165 GitHub starsUsed in 1 repo~1k tokens
    DatabasesAuto-check passed

More from getagentseal/founder-playbook

All 16 skills in this repo
  • 100m Leads

    getagentseal/founder-playbook

    Builds lead generation systems using Alex Hormozi's Core Four framework (warm outreach, content, cold outreach, paid ads), lead magnets, and Rule of 100.

    721 GitHub stars~2.3k tokensUpdated yesterday
    Auto-check passed
  • 100m Offers

    getagentseal/founder-playbook

    Designs irresistible Grand Slam Offers using Alex Hormozi's value equation, obstacle-solution mapping, value-cost trim/stack, and offer-naming patterns.

    721 GitHub stars~2.7k tokensUpdated yesterday
    Auto-check passed
  • Blue Ocean Strategy

    getagentseal/founder-playbook

    Frameworks from Kim & Mauborgne for creating uncontested market space and making competition irrelevant.

    721 GitHub stars~3.1k tokensUpdated yesterday
    Auto-check passed
  • Diagnose

    getagentseal/founder-playbook

    Startup diagnostic router. An agent skill from getagentseal/founder-playbook.

    721 GitHub stars~2.6k tokensUpdated yesterday
    Auto-check passed
  • Lean Startup

    getagentseal/founder-playbook

    Applies Eric Ries's Lean Startup methodology for building products under extreme uncertainty.

    721 GitHub stars~4.6k tokensUpdated yesterday
    Auto-check passed
  • Made To Stick

    getagentseal/founder-playbook

    Applies the SUCCESs Framework from Made to Stick by Chip Heath and Dan Heath.

    721 GitHub stars~4.1k tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Influence

What does Influence do?

Cialdini's seven principles of compliance (the classic six — reciprocation, commitment-consistency, social proof, liking, authority, scarcity — plus Unity, added 2016) and Pre-Suasion. Influence is an agent skill from getagentseal/founder-playbook. Cialdini's seven principles of compliance (the classic six — reciprocation, commitment-consistency, social proof, liking, authority, scarcity — plus Unity, added 2016) and Pre-Suasion.

When should I use Influence?

Influence fits situations like: crafting ethical persuasion (marketing; defending against manipulation; designing systems that need cooperation.

How do I install Influence in Claude Code?

Run `npx skills add getagentseal/founder-playbook --skill influence -a claude-code`. Or copy the skill folder (skills/influence in getagentseal/founder-playbook) into .claude/skills/influence in your project. Claude Code loads it when a task matches its description.

How do I install Influence in Codex?

Run `npx skills add getagentseal/founder-playbook --skill influence -a codex`. Or copy the skill folder (skills/influence in getagentseal/founder-playbook) into .agents/skills/influence in your project. Codex loads it when a task matches its description.

Can I use Influence in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add getagentseal/founder-playbook --skill influence -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/influence, .gemini/skills/influence, .github/skills/influence and .opencode/skills/influence in your project.

What does Influence need to run?

SKILL.md names no scripts, command-line tools or credentials: Influence is instructions for the agent only.

Does Influence access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Influence safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Influence use?

Influence is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Influence use?

About 3.8k tokens (SKILL.md is roughly 15k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Influence?

Skills that share tags, products or a category with Influence: Hybrid Cloud Outboxes (getsentry/sentry, 45k stars), Replicate Video Ad (Jingyi-Wu-Richael/replicate-video-ad, 106 stars), Sea Orm 2 (FlyinPancake/yoink, 112 stars) and Pixel Perfect Replication (Yu-369/VibeCurb, 980 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Influence?

getagentseal (a GitHub organization) maintains it in getagentseal/founder-playbook, which has 721 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on October 6, 2026.

Source: getagentseal/founder-playbook on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.