markdown-scanner

markdown-scanner is an agent for Claude Code from Community-Access/accessibility-agents. It costs 59 tokens per session (4,020 once invoked), scanned A, original, MIT.

A scanner that checks one Markdown file for accessibility problems across nine areas. It reports each finding with its severity, location, suggested fix, and whether it can be fixed automatically.

In plain words
What is it for?
Use it to audit Markdown files, identify problems by line number, and prepare a structured list for a separate fixing step.
Why use it?
It gives developers a consistent way to find accessibility issues before someone has to inspect the file manually.

Agent for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Good fit Use it to audit Markdown files, identify problems by line number, and…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/community-access/accessibility-agents/markdown-scanner
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.

Clone the repo
git clone --depth 1 https://github.com/Community-Access/accessibility-agents

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 markdown-scanner

README.md
[![agentmods](https://agentmods.dev/badge/agents/community-access/accessibility-agents/markdown-scanner.svg)](https://agentmods.dev/agents/community-access/accessibility-agents/markdown-scanner)
Your own site
<a href="https://agentmods.dev/agents/community-access/accessibility-agents/markdown-scanner"><img src="https://agentmods.dev/badge/agents/community-access/accessibility-agents/markdown-scanner.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,020 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 $0.00059 $0.04020
Opus 5 $0.00030 $0.02010
Sonnet 5 $0.00012 $0.00804
Haiku 4.5 $0.00006 $0.00402

Measured 3d ago against content hash abd43ff7d0a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

markdown-scanner 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 3d 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.

.github/agents/markdown-scanner.agent.md · 386 lines

How it starts

The opening of the file, as written. The whole thing — 386 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Authoritative Sources

Markdown Scanner

You are a markdown accessibility scanner. You receive a single file path and scan configuration, then return structured findings across all 9 accessibility domains.

You do NOT apply fixes. You scan, classify, and report. All fixing is handled by markdown-fixer.

Input

You will receive a Markdown Scan Context block:

## Markdown Scan Context
- **File:** [full path]
- **Scan Profile:** [strict | moderate | minimal]
- **Emoji Preference:** [remove-all | remove-decorative | translate | leave-unchanged]
- **Mermaid Preference:** [replace-with-text | flag-only | leave-unchanged]
- **ASCII Preference:** [replace-with-text | flag-only | leave-unchanged]
- **Dash Preference:** [normalize-to-hyphen | normalize-to-double-hyphen | leave-unchanged]
- **Anchor Validation:** [yes | no]
- **Fix Mode:** [auto-fix-safe | flag-all | fix-all]
- **User Notes:** [any specifics from Phase 0]

MCP Tools

When the MCP server is available, use this tool to supplement your manual scan:

  • scan_markdown_document -- Automated Markdown accessibility scanner covering all 9 domains. Run this first to get baseline findings, then perform your manual scan to catch context-dependent issues the automated tool may miss.

Scan Process

Step 1: Read the File

Read the full file content. Note the total line count.

Step 2: Run markdownlint

npx --yes markdownlint-cli2 "<filepath>"

Collect all linter output. Map each rule violation to its accessibility domain:

Rule Domain
MD001 Heading hierarchy
MD022 Heading hierarchy
MD023 Heading hierarchy
MD025 Heading hierarchy
MD034 Descriptive links
MD041 Heading hierarchy
MD045 Alt text
MD055 Table accessibility
MD056 Table accessibility

Read the full file on GitHub · 386 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. 3d ago First seen · 386 lines · 59 tokens per session scan A abd43ff7d0a8

Subscribe to this mod's changes

markdown-scanner is an agent published in the GitHub repository Community-Access/accessibility-agents (405 stars, last pushed 26d ago), licensed MIT. It adds 59 tokens to every session and 4,020 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 2026-09-03.

Related

Other agents, from other repositories

bench-runner

Executes a11y skill benchmarks across hosted and local model families. Runs cloud/Codex/Ollama benchmark scripts, monitors progress, handles errors and retries. Reports raw results to the team.

zivtech/accessibility-skills · 44 tokens

fixture-builder

Creates and enriches eval suite fixtures — .md component files, .metadata.yaml grading criteria, and .rubric.yaml scoring definitions. Handles all three suites (critic, planner, perspective).

zivtech/accessibility-skills · 41 tokens

bench-reviewer

Reviews eval suite quality — fixture/rubric consistency, scoring accuracy, false positive traps, difficulty calibration. Read-only reviewer that identifies issues without fixing them.

zivtech/accessibility-skills · 35 tokens

prism

Implements design system specs into production-quality UI components, pages, and internal tools using design tokens, TDD, and full a11y — never reinterprets Form's visual decisions. Use when building React/Vue/Svelte components, wiring state management, or hardening production UI against empty/error/loading states.…

jeremylongshore/tons-of-skills-marketplace · 78 tokens

a11y-planner

Accessibility Design Planner — 9-phase protocol for designing accessible implementations before coding. Maps interactive patterns to WAI-ARIA APG patterns, plans focus management, state communication, visual accessibility, content strategy, and testing approach.

zivtech/accessibility-skills · 50 tokens

a11y-scout

Lightweight reconnaissance agent for accessibility reviews. Discovers files, inventories existing ARIA attributes, identifies component type and complexity. Returns structured summary for handoff to planner or critic.

zivtech/accessibility-skills · 41 tokens