kb-web-severity-scoring

kb-web-severity-scoring is a skill for Claude Code, Codex from Community-Access/accessibility-agents. It costs 40 tokens per session (1,977 once invoked), scanned A, original, MIT.

A reference guide for turning web accessibility findings into scores from 0 to 100 and letter grades from A to F. It defines severity, confidence, and scoring profiles for different contexts.

In plain words
What is it for?
It helps calculate page scores, apply weighted findings, record confidence, and follow fixes across accessibility audits.
Why use it?
It gives teams a consistent way to compare audit results and track remediation, meaning the work needed to fix problems. Profiles can make scoring stricter or more advisory.

Skill for Claude CodeCodex

Written for Claude Code and Codex: disable-model-invocation in frontmatter, but also agents/openai.yaml present.

Part of the accessibility-agents plugin — 108 skills, 6 hooks shipped together

Good fit It helps calculate page scores, apply weighted findings, record confidence, and follow fixes across accessibility audits.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/community-access/accessibility-agents/kb-web-severity-scoring
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 Community-Access/accessibility-agents --skill kb-web-severity-scoring
Clone the repo
git clone --depth 1 https://github.com/Community-Access/accessibility-agents

Made for: Claude Code, Codex.

Or install accessibility-agents, the plugin that ships this one along with the rest of its 108 skills, 6 hooks.

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 kb-web-severity-scoring

README.md
[![agentmods](https://agentmods.dev/badge/skills/community-access/accessibility-agents/kb-web-severity-scoring/github.svg)](https://agentmods.dev/skills/community-access/accessibility-agents/kb-web-severity-scoring)
Your own site
<a href="https://agentmods.dev/skills/community-access/accessibility-agents/kb-web-severity-scoring"><img src="https://agentmods.dev/badge/skills/community-access/accessibility-agents/kb-web-severity-scoring/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 kb-web-severity-scoring

Your own site · 80×15
<a href="https://agentmods.dev/skills/community-access/accessibility-agents/kb-web-severity-scoring"><img src="https://agentmods.dev/badge/skills/community-access/accessibility-agents/kb-web-severity-scoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,977 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 $0.00040 $0.01977
Opus 5.5 $0.00016 $0.00791
Sonnet 5.5 $0.00008 $0.00395
Haiku 4.5 $0.00004 $0.00198

Measured 1mo ago against content hash dda9f606669f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

kb-web-severity-scoring 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 1mo 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/kb-web-severity-scoring/SKILL.md · 260 lines

How it starts

The opening of the file, as written. The whole thing — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Web Severity Scoring

Severity Scoring Formula

Page Score = 100 - (sum of weighted findings)

Weights:
  Critical (confirmed, all three sources):   -18 points
  Critical (high confidence, both sources):  -15 points
  Critical (high confidence, single source): -10 points
  Critical (medium confidence):               -7 points
  Critical (low confidence):                  -3 points
  Serious (high confidence):                  -7 points
  Serious (medium confidence):                -5 points
  Serious (low confidence):                   -2 points
  Moderate (high confidence):                 -3 points
  Moderate (medium confidence):               -2 points
  Moderate (low confidence):                  -1 point
  Minor:                                      -1 point

Floor: 0 (minimum score)

Scoring Profiles

Use a profile to tune strictness by context while keeping comparable grade bands:

Profile Intended Use Multiplier
balanced (default) Standard product delivery 1.0
strict Regulated/public-sector releases 1.15
advisory Early design and prototyping 0.8

Apply the profile multiplier to each final deduction after confidence handling.

Formula

page_score = 100
for each finding:
    base = lookup(severity, confidence_level, source_count)  // from table above
    multiplier = 1.2 if confidence_level == "confirmed" else 1.0
    deduction = base × multiplier
    page_score = max(0, page_score - deduction)

The values in the lookup table above are base deductions (pre-multiplier). "Confirmed" findings (validated by all three sources: axe-core + agent review + Playwright) apply an additional 1.2× multiplier.

Example: One Critical finding at confirmed confidence = 18 (base) × 1.2 = 21.6 points deducted → page score 78.

Calibration Layer (v2)

To reduce false-positive inflation and stabilize trends, apply a calibration coefficient by rule family:

Read the full file on GitHub · 260 lines

Files

What ships with it

1 file 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. 1mo ago First seen · 260 lines · 40 tokens per session scan A dda9f606669f

Subscribe to this mod's changes

kb-web-severity-scoring is a skill published in the GitHub repository Community-Access/accessibility-agents (428 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 1,977 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-23.

Related

Other skills, from other repositories

Accessibility Auditor

Comprehensive WCAG 2.1 AA compliance testing combining automated axe-core scans with manual keyboard navigation, screen reader compatibility, and focus management verification.

PramodDutta/qaskills · 32 tokens

Accessibility A11y Enhanced

Comprehensive WCAG compliance and accessibility testing covering ARIA, keyboard navigation, screen readers, color contrast, and automated a11y validation.

PramodDutta/qaskills · 34 tokens

a11y-audit

Runs automated accessibility scans with axe-core, pa11y, Lighthouse, or eslint-plugin-jsx-a11y. Interprets results, prioritizes violations, and generates fix recommendations. Use when asked to audit, scan, or check accessibility of a page, component, or codebase.

xrnavigation/web-a11y-plugin · 64 tokens

testing-strategy

Guides accessibility testing strategy — what to test automatically vs manually vs with assistive technology. Provides keyboard testing checklists, screen reader testing basics, and acceptance criteria templates. Use when planning testing, writing acceptance criteria, or deciding how to verify accessibility.

xrnavigation/web-a11y-plugin · 54 tokens

a11y-ally

Use when running comprehensive WCAG accessibility audits with axe-core + pa11y + Lighthouse, generating context-aware remediation, or testing video accessibility. Supports 3-tier browser cascade with graceful degradation.

proffesor-for-testing/agentic-qe · 44 tokens

accessibility-testing

WCAG 2.2 compliance testing, screen reader validation, and inclusive design verification. Use when ensuring legal compliance (ADA, Section 508), testing for disabilities, or building accessible applications for 1 billion disabled users globally.

proffesor-for-testing/agentic-qe · 50 tokens