epistemic-uncertainty-quantification

epistemic-uncertainty-quantification is a skill for Claude Code, Codex from Sounio-lang/sounio. It costs 62 tokens per session (1,154 once invoked), scanned A, original, Apache-2.0.

A development guide for adding advanced ways to represent and calculate epistemic uncertainty in Sounio, a programming language for scientific computing. Epistemic uncertainty describes limited knowledge about a value or model.

In plain words
What is it for?
Use it when implementing uncertainty representations, mathematical operations, standard-library support, or validation against the Guide to the Expression of Uncertainty in Measurement (GUM).
Why use it?
It helps extend basic variance-based uncertainty with methods such as confidence intervals, non-normal error models, and evidence combination.

Skill for Claude CodeCodex

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

Good fit Use it when implementing uncertainty representations, mathematical operations, standard-library support, or validation against the Guide to the Expression of Uncertainty in Measurement (GUM).

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sounio-lang/sounio/epistemic-uncertainty-quantification
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 Sounio-lang/sounio --skill epistemic-uncertainty-quantification
Clone the repo
git clone --depth 1 https://github.com/Sounio-lang/sounio

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 epistemic-uncertainty-quantification

README.md
[![agentmods](https://agentmods.dev/badge/skills/sounio-lang/sounio/epistemic-uncertainty-quantification/github.svg)](https://agentmods.dev/skills/sounio-lang/sounio/epistemic-uncertainty-quantification)
Your own site
<a href="https://agentmods.dev/skills/sounio-lang/sounio/epistemic-uncertainty-quantification"><img src="https://agentmods.dev/badge/skills/sounio-lang/sounio/epistemic-uncertainty-quantification/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 epistemic-uncertainty-quantification

Your own site · 80×15
<a href="https://agentmods.dev/skills/sounio-lang/sounio/epistemic-uncertainty-quantification"><img src="https://agentmods.dev/badge/skills/sounio-lang/sounio/epistemic-uncertainty-quantification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,154 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00062 $0.01154
Opus 5 $0.00031 $0.00577
Sonnet 5 $0.00012 $0.00231
Haiku 4.5 $0.00006 $0.00115

Measured 11d ago against content hash 4257d646d06e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

epistemic-uncertainty-quantification 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.

.roo/skills/epistemic-uncertainty-quantification/SKILL.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Epistemic Uncertainty Quantification

When to use this skill

Use this skill when you need to:

  • Add new uncertainty representations beyond variance‑based Knowledge<T> (e.g., confidence intervals, prediction intervals)
  • Incorporate non‑Gaussian error models (e.g., skew‑normal, Student‑t, mixture distributions)
  • Implement Dempster‑Shafer or other evidence‑combination frameworks
  • Validate that the new quantification methods remain GUM‑compliant
  • Extend the standard library with advanced epistemic operators

When NOT to use this skill

  • For basic uncertainty propagation that already works with Knowledge<T> (use the existing epistemic library)
  • For changes unrelated to epistemic types (e.g., adding new numeric functions)
  • For pure performance optimizations without semantic changes

Inputs required

  • Clear specification of the new uncertainty representation (mathematical definition)
  • References to relevant literature (GUM supplements, statistical textbooks)
  • Expected behavior for common operations (addition, multiplication, transformation)
  • Where the new functionality should live (stdlib/epistemic/ or a new submodule)

Workflow

  1. Understand the existing epistemic foundation

    • Read stdlib/epistemic/knowledge.sio and stdlib/epistemic/gum.sio
    • Review the GUM compliance proofs in docs/compiler/EPISTEMIC_GUM_COMPLIANCE.md
    • Examine the test suite tests/epistemic/
  2. Design the new representation

    • Decide whether to extend Knowledge<T> or create a parallel type (e.g., IntervalKnowledge<T>)
    • Define the internal fields (point estimate, interval bounds, distribution parameters, etc.)
    • Specify how confidence updates and provenance merging work
  3. Implement the core type

    • Create a new .sio file in stdlib/epistemic/ (or a subdirectory)
    • Provide constructors, accessors, and basic arithmetic operations
    • Ensure uncertainty propagation follows the required mathematical rules
  4. Integrate with the type checker

    • If the new type needs special checking rules, modify self‑hosted/check/epistemic.sio
    • Add any necessary compiler diagnostics for misuse

Read the full file on GitHub · 128 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 · 128 lines · 62 tokens per session scan A 4257d646d06e

Subscribe to this mod's changes

epistemic-uncertainty-quantification is a skill published in the GitHub repository Sounio-lang/sounio (6 stars, last pushed today), licensed Apache-2.0. It adds 62 tokens to every session and 1,154 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 2026-08-31.