social-proof

social-proof is a skill for Claude Code, Codex from deciqAI/knowledge-skills. It costs 101 tokens per session (2,252 once invoked), scanned B, original, MIT.

A framework for judging whether other people's choices are reliable evidence that something is correct, popular, or worth doing. It also covers how group pressure and fake agreement can distort that judgment.

In plain words
What is it for?
Use it to assess trends, customer reviews, hiring or investment choices, and claims such as “everyone is adopting this.” It also helps design testimonials and other user experiences that use social proof honestly.
Why use it?
It helps separate genuine demand or consensus from herd behaviour, paid reviews, bots, or pressure to conform. This reduces the risk of copying a crowd without checking the underlying evidence.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to assess trends, customer reviews, hiring or investment choices, and claims such as “everyone is adopting this.” It also helps design testimonials and other user experiences that use social proof honestly.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/deciqai/knowledge-skills/social-proof
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 deciqAI/knowledge-skills --skill social-proof
Clone the repo
git clone --depth 1 https://github.com/deciqAI/knowledge-skills

Made for: Claude Code, Codex.

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 social-proof

README.md
[![agentmods](https://agentmods.dev/badge/skills/deciqai/knowledge-skills/social-proof/github.svg)](https://agentmods.dev/skills/deciqai/knowledge-skills/social-proof)
Your own site
<a href="https://agentmods.dev/skills/deciqai/knowledge-skills/social-proof"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/social-proof/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 social-proof

Your own site · 80×15
<a href="https://agentmods.dev/skills/deciqai/knowledge-skills/social-proof"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/social-proof.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,252 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00101 $0.02252
Opus 5 $0.00051 $0.01126
Sonnet 5 $0.00020 $0.00450
Haiku 4.5 $0.00010 $0.00225

Measured 9d ago against content hash a0732ea2d80b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade B, and why

social-proof scanned grade B with 1 finding 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 9d 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.

Strips warnings and disclaimersmediumAnti-refusal

Omitting safety caveats hides risk from the user and is a common jailbreak preamble.

- **Coach mode:** user is unfamiliar or has no concrete case → guide, don't lecture.
social-proof/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Social Proof

Overview

Social proof: we judge what is correct, normal, or worth doing by observing what others — especially similar others — are doing. Usually efficient; failure mode is severe: under unanimous consensus, people publicly endorse answers they privately know are wrong (Asch 1951–56: error rate <1% alone, ~37% under group pressure). Two amplifiers: uncertainty (social proof fills the vacuum) and similarity (same-type peers drive far stronger conformity than generic crowds).

Composes with reciprocity (Cialdini's two primary levers), anchoring (price tiers often function as quasi-social-proof), and critical-thinking (structured fallback when consensus has been engineered).

When to Use

Use when: purchase/hiring/investment decision leaning on what others chose; proposal cites "everyone is doing this"; designing growth/marketing/UX with social-proof patterns; decision feels unsafe alone without a clear reason; suspecting manufactured consensus (bots, paid reviews, astroturf); a trend is accelerating and private doubt is being suppressed by the fact everyone is on board; a "we must adopt AI because every competitor is deploying it" mandate is driving procurement or a pilot ahead of any validated ROI (AI hype / FOMO buying).

Do NOT use when: decision is low-stakes and reversible; you have direct measured evidence stronger than any consensus; the "consensus" is from verified domain experts with better epistemic position; you want to rationalize a contrarian position that lacks independent evidence.

Coaching Novices (Adaptive Front Door)

  • Engine mode: user has a concrete case → run The Process directly.
  • Coach mode: user is unfamiliar or has no concrete case → guide, don't lecture.

In Coach mode, respond one step at a time. Each [WAIT] is a hard stop — output only that step's question, then stop.

  1. One-line what-it-is. We judge what's correct by looking at what others do — useful most of the time, but under enough unanimous consensus, people will publicly agree with answers they privately know are wrong, even on obvious questions.
  2. Check fit against When to Use / When NOT to use. If direct evidence is stronger, point there.
  3. Elicit the real situation. A concrete decision shaped by what others are doing, or a design problem deploying social proof. Never run on hypotheticals.

[WAIT — do not advance until user responds]

  1. One element at a time. Walk through: what's the consensus, who are the consensus-makers, are they similar to you / informed, would you decide the same way if alone — wait for input.

[WAIT — do not advance until user responds]

  1. Close by naming the payoff. The one move — accept the consensus, reject it, or seek independent evidence — that fits their situation.

[WAIT — do not advance until user responds]

Read the full file on GitHub · 123 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 123 lines · 101 tokens per session scan B a0732ea2d80b

Subscribe to this mod's changes

social-proof is a skill published in the GitHub repository deciqAI/knowledge-skills (10 stars, last pushed 11d ago), licensed MIT. It adds 101 tokens to every session and 2,252 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

edge-tts

Text-to-speech conversion using uvx edge-tts for generating audio from text. Use when (1) User requests audio/voice output with the "tts" trigger or keyword. (2) Content needs to be spoken rather than read (multitasking, accessibility, driving, cooking). (3) User wants a specific voice, speed, pitch, or format for TTS…

aahl/skills · 85 tokens

mcp-deepwiki

Skills for accessing and searching docs in DeepWiki/GitHub’s public code repositories can help users understand open-source project source codes, and users can also ask questions directly about the code docs.

aahl/skills · 44 tokens

tianqi

A weather-lookup workflow for Chinese locations, covering forecasts, hourly conditions, weather warnings, and daily-life indexes.

aahl/skills · 24 tokens

compliance-check

Compliance pre-flight for a feature, campaign, or initiative — maps the data and activity involved, checks applicable regimes (privacy/GDPR-style, consumer protection, marketing rules, sector-specific), lists required approvals and notices, builds a gap list with remediation owners, and ends in a go/no-go…

alebgl77/claude-inc · 98 tokens

plan-payroll

Plans payroll cash: true loaded cost per hire (gross plus employer taxes, benefits, tools), a payroll calendar with cutoffs and cash-out dates, a scenario table for new hire vs raise vs contractor-vs-employee, and a payroll-to-revenue check against rough industry bands. Use when the user asks "can I afford to hire"…

alebgl77/claude-inc · 0 tokens

ui-ux-pro-max

Builds an end-to-end UI system for a product — design tokens (color scale, type scale, spacing, radii, shadows), a component inventory covering every interaction state, a layout grid, and WCAG contrast checks — emitted as CSS variables plus a component spec doc. Use when the user says "set up a design system", "create…

alebgl77/claude-inc · 102 tokens