confidence-levels

confidence-levels is a skill for Claude Code from Liberty91LTD/cti-skills. It costs 63 tokens per session (874 once invoked), scanned A, original, MIT.

A scale for rating how well an analytical judgment is supported by evidence, from 0 to 100. It also maps scores to bands such as low, moderate, and very high.

In plain words
What is it for?
Use it when documenting an analytical conclusion, answering how certain a judgment is, or checking confidence before publishing it.
Why use it?
It separates confidence in the evidence from likelihood that an event will happen, reducing a common source of confusion in analysis.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Good fit Use it when documenting an analytical conclusion, answering how certain a judgment is, or checking confidence before publishing it.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/liberty91ltd/cti-skills/confidence-levels
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 Liberty91LTD/cti-skills --skill confidence-levels
Clone the repo
git clone --depth 1 https://github.com/Liberty91LTD/cti-skills

Made for: Claude Code.

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 confidence-levels

README.md
[![agentmods](https://agentmods.dev/badge/skills/liberty91ltd/cti-skills/confidence-levels/github.svg)](https://agentmods.dev/skills/liberty91ltd/cti-skills/confidence-levels)
Your own site
<a href="https://agentmods.dev/skills/liberty91ltd/cti-skills/confidence-levels"><img src="https://agentmods.dev/badge/skills/liberty91ltd/cti-skills/confidence-levels/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 confidence-levels

Your own site · 80×15
<a href="https://agentmods.dev/skills/liberty91ltd/cti-skills/confidence-levels"><img src="https://agentmods.dev/badge/skills/liberty91ltd/cti-skills/confidence-levels.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 874 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 $0.00063 $0.00874
Opus 5 $0.00032 $0.00437
Sonnet 5 $0.00013 $0.00175
Haiku 4.5 $0.00006 $0.00087

Measured 11d ago against content hash ec1eb92f5560, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

confidence-levels 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 11d 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.

skills/confidence-levels/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Confidence Levels

Every analytical judgment produced by this platform MUST carry a confidence level. Confidence reflects the quality and quantity of evidence supporting the judgment, NOT the probability that the event will occur (that's likelihood — see likelihood-language skill).

Primary Scale: Named Bands

Band Score Range Meaning
Very High 90-100 Based on high-quality information from multiple independent sources. Analyst has no significant concerns about the validity of the sources. Well-corroborated assessment.
High 75-89 Based on high-quality information, or from multiple sources with minor inconsistencies. Key assumptions are well-supported.
Moderate 50-74 Based on credible information that is not sufficient to warrant higher confidence. Key assumptions are reasonable but not fully validated. Alternative interpretations exist.
Low 25-49 Based on limited or fragmentary information. Key assumptions have significant uncertainty. Multiple plausible alternative interpretations.
Very Low 0-24 Based on sparse, unreliable, or largely circumstantial information. Assessment is essentially speculative.

What Determines Confidence

Confidence is determined by three factors:

1. Quality of Sources

  • How reliable are the sources? (Cross-reference with Admiralty Scale)
  • Are sources independent or derivative?
  • Is there potential for deception or disinformation?

2. Quantity and Corroboration

  • How many independent sources support the assessment?
  • Do sources confirm each other or contradict?
  • Is the evidence diverse (technical + human + open source)?

3. Analytical Logic

  • How strong is the analytical reasoning?
  • Have key assumptions been tested?
  • Have alternative hypotheses been considered and evaluated?

How to Express Confidence

In text

"We assess with high confidence that APT28 is responsible for this campaign, based on infrastructure overlaps with three previously attributed operations and consistent TTP alignment documented by two independent vendors."

Read the full file on GitHub · 90 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. 11d ago First seen · 90 lines · 63 tokens per session scan A ec1eb92f5560

Subscribe to this mod's changes

confidence-levels is a skill published in the GitHub repository Liberty91LTD/cti-skills (18 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 874 once invoked, about $0.0003 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 2026-08-30.