ask-ai-confidence-rating

ask-ai-confidence-rating is a skill for Claude Code from alivirgo/Major-AI-Skills. It costs 20 tokens per session (1,342 once invoked), scanned A, original, MIT.

A prompting guide for getting confidence ratings and uncertainty notes from an AI assistant. It distinguishes well-established facts from judgments, changing information, and speculation.

In plain words
What is it for?
Use it to request confidence levels, identify uncertain claims, examine assumptions, and flag parts of an answer that need verification.
Why use it?
It helps reveal weak assumptions and makes answers easier to assess before using them for important decisions.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Codex.

Part of the mas-common-sense-pack plugin — 5 skills shipped together

Good fit Use it to request confidence levels, identify uncertain claims, examine assumptions, and flag parts of an answer that need verification.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/alivirgo/major-ai-skills/ask-ai-confidence-rating
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 alivirgo/Major-AI-Skills --skill ask-ai-confidence-rating
Clone the repo
git clone --depth 1 https://github.com/alivirgo/Major-AI-Skills

Made for: Claude Code.

Or install mas-common-sense-pack, the plugin that ships this one along with the rest of its 5 skills.

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 ask-ai-confidence-rating

README.md
[![agentmods](https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/ask-ai-confidence-rating/github.svg)](https://agentmods.dev/skills/alivirgo/major-ai-skills/ask-ai-confidence-rating)
Your own site
<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/ask-ai-confidence-rating"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/ask-ai-confidence-rating/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 ask-ai-confidence-rating

Your own site · 80×15
<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/ask-ai-confidence-rating"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/ask-ai-confidence-rating.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,342 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.
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 $0.00020 $0.01342
Opus 5 $0.00010 $0.00671
Sonnet 5 $0.00004 $0.00268
Haiku 4.5 $0.00002 $0.00134

Measured today against content hash b50dd883e544, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ask-ai-confidence-rating 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 today.

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/mas-common-sense-pack/skills/ask-ai-confidence-rating/SKILL.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ask AI for Confidence & Uncertainty Ratings (AI Skill)

Overview

Standard LLMs produce responses with an unwavering, authoritative tone regardless of whether they are stating a verified mathematical axiom or guessing an obscure regulatory nuance.

This skill provides an Epistemic Calibration Framework that instructs AI models to evaluate their own certainty, explicitly flag assumptions, and provide numeric confidence ratings for each component of an analysis.


The Confidence Calibration Matrix

┌─────────────────────────────────────────────────────────────┐
│                 Certainty Breakdown Scale                   │
│                                                             │
│  [90-100%] HIGH CERTAINTY ──► Established facts, syntax,   │
│                               mathematical derivations      │
│  [60-89%]  MODERATE       ──► Best practices, industry      │
│                               heuristics, common patterns   │
│  [0-59%]   LOW / SPECULATIVE► Rapidly changing data, niche  │
│                               laws, subjective predictions  │
└─────────────────────────────────────────────────────────────┘

The Calibrated System Prompt Template

Use this prompt modifier for research, technical architecture, legal/tax guidelines, and high-stakes problem solving:

Answer the following query: [INSERT QUESTION]

Formatting Requirements:
1. Provide the direct, actionable answer first.
2. Underneath your answer, include a "Certainty & Risk Breakdown" with:
  - **Confidence Score (1-100%)**: State your overall confidence in the factual accuracy of this response.
  - **High-Certainty Elements**: List the specific points you are 100% sure about.
  - **Uncertainty & Assumptions**: Explicitly list any assumptions, ambiguities in my prompt, or edge cases where this answer might fail.
  - **Verification Step**: Provide the single most effective action I can take to verify this independently (e.g., official docs page, CLI test, calculation).

Read the full file on GitHub · 111 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. today Changed · -8 tokens per session b50dd883e544
  2. 12d ago First seen · 111 lines · 28 tokens per session scan A 7bc104ca963e

Subscribe to this mod's changes

ask-ai-confidence-rating is a skill published in the GitHub repository alivirgo/Major-AI-Skills (1 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 1,342 once invoked, about $0.0001 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 2026-08-31.

Related

Other skills, from other repositories

ai-engineering-toolkit

AI Engineering Toolkit workflow skill. Use this skill when the user needs 6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching and the operator…

diegosouzapw/awesome-omni-skills · 81 tokens

few-shot-architect

Professional Few Shot Architect skill. Integrate LLM API workflows, safe system prompt guidelines, and agentic workflows.

AtulPurohit/Antigravity-Awesome-Skills · 28 tokens

llm-prompt-master

Professional LLM Prompt Master skill. Integrate LLM API workflows, safe system prompt guidelines, and agentic workflows.

AtulPurohit/Antigravity-Awesome-Skills · 30 tokens

responsible-ai

Professional Responsible Ai Expert skill. Integrate LLM API workflows, safe system prompt guidelines, and agentic workflows.

AtulPurohit/Antigravity-Awesome-Skills · 27 tokens

ai-engineering-toolkit

6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.

sickn33/agentic-awesome-skills · 47 tokens

ai-wrapper-product-v2

AI Wrapper Product workflow skill. Use this skill when the user needs Expert in building products that wrap AI APIs (OpenAI, Anthropic, and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

diegosouzapw/awesome-omni-skills · 55 tokens