report

report is a skill for Claude Code, Codex from bromso/metapowers. It costs 9 tokens per session (462 once invoked), scanned A, original, MIT.

A tool for writing a structured report about a website or app's accessibility problems. Accessibility means making software usable by people with disabilities, including people who use screen readers or keyboards.

In plain words
What is it for?
Creating an executive summary, documenting each issue with its relevant WCAG rule and severity, describing its impact, and listing remediation steps.
Why use it?
It turns evaluation results into plain-language findings, priorities, and suggested fixes. It also checks that the required earlier evaluation exists before producing the report.

Skill for Claude CodeCodex

Part of the accessibility plugin — 6 skills shipped together

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.

agentmods
npx agentmods add skills/bromso/metapowers/report
Any agent
npx skills add bromso/metapowers --skill report
Clone the repo
git clone --depth 1 https://github.com/bromso/metapowers

Made for: Claude Code, Codex.

Or install accessibility, the plugin that ships this one along with the rest of its 6 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 report

README.md
[![agentmods](https://agentmods.dev/badge/skills/bromso/metapowers/report.svg)](https://agentmods.dev/skills/bromso/metapowers/report)
Your own site
<a href="https://agentmods.dev/skills/bromso/metapowers/report"><img src="https://agentmods.dev/badge/skills/bromso/metapowers/report.svg" alt="Measured on agentmods" height="20"></a>
Per session 9 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 462 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00009 $0.00462
Opus 5 $0.00005 $0.00231
Sonnet 5 $0.00002 $0.00092
Haiku 4.5 $0.00001 $0.00046

Measured 5d ago against content hash c0446672ce4d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

report 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 5d 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.

plugins/accessibility/skills/report/SKILL.md · 50 lines

What it actually says

Report

Generate a comprehensive accessibility audit report for "$ARGUMENTS" with executive summary, detailed findings, and prioritized remediation steps.

Prerequisites

Read .metapowers/accessibility/$ARGUMENTS/02-evaluate.md. If this file does not exist, tell the user:

Phase 2 (Evaluate) has not been completed for "$ARGUMENTS". Run /accessibility:evaluate $ARGUMENTS first, or use --skip-checks to bypass.

If --skip-checks is present in $ARGUMENTS, skip this check and log to .metapowers/accessibility/$ARGUMENTS/skip-log.md.

Process

  1. Read context files:

    • Read .metapowers/accessibility/$ARGUMENTS/01-scope.md for audit scope
    • Read .metapowers/accessibility/$ARGUMENTS/02-evaluate.md for discovered issues
    • Read plugins/accessibility/shared/audit-report-template.md for output structure
    • Read plugins/accessibility/shared/remediation-patterns.md for fix guidance
  2. Create executive summary:

    • Overall conformance status
    • Total issues by severity
    • Key findings in plain language
    • Business impact assessment
  3. Document detailed findings:

    • For each issue: description, WCAG criterion, severity, location, impact, remediation steps
    • Include code examples (before/after) where applicable
    • Group by WCAG principle for easy navigation
  4. Prioritize remediation:

    • Critical issues first (blocking access)
    • Then major issues (significant barriers)
    • Then minor issues (enhancements)
    • Estimate effort for each fix (quick fix vs. significant rework)
  5. Write the artifact to .metapowers/accessibility/$ARGUMENTS/03-report.md following the audit report template.

Output

The audit report written to .metapowers/accessibility/$ARGUMENTS/03-report.md. Present a summary to the user highlighting:

  • Conformance status
  • Top priority issues to fix
  • Estimated remediation effort
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. 5d ago First seen · 50 lines · 9 tokens per session scan A c0446672ce4d

Subscribe to this mod's changes

report is a skill published in the GitHub repository bromso/metapowers (1 stars, last pushed 4mo ago), licensed MIT. It adds 9 tokens to every session and 462 once invoked, about $0.0000 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.