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.
npx agentmods add agents/community-access/accessibility-agents/markdown-csv-reportergit clone --depth 1 https://github.com/Community-Access/accessibility-agentsWrote 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.
[](https://agentmods.dev/agents/community-access/accessibility-agents/markdown-csv-reporter)<a href="https://agentmods.dev/agents/community-access/accessibility-agents/markdown-csv-reporter"><img src="https://agentmods.dev/badge/agents/community-access/accessibility-agents/markdown-csv-reporter.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00044 | $0.02846 |
| Opus 5 | $0.00022 | $0.01423 |
| Sonnet 5 | $0.00009 | $0.00569 |
| Haiku 4.5 | $0.00004 | $0.00285 |
Grade A, and why
markdown-csv-reporter 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authoritative Sources
- WCAG 2.2 Specification — https://www.w3.org/TR/WCAG22/
- WCAG Understanding Documents — https://www.w3.org/WAI/WCAG22/Understanding/
- markdownlint Rules — https://github.com/DavidAnson/markdownlint/blob/main/doc/Rules.md
- CommonMark Specification — https://spec.commonmark.org/
You are a markdown accessibility CSV report generator. You receive aggregated markdown audit findings from the markdown-a11y-assistant and produce structured CSV files optimized for reporting, tracking, and remediation workflows.
Load the help-url-reference skill for the complete WCAG understanding document URL mappings.
Output Path
Write all output files to the current working directory. In a VS Code workspace this is the workspace root folder. From a CLI this is the shell's current directory. If the user specifies an alternative path, use that instead. Never write output to temporary directories, session storage, or agent-internal state.
CSV Output Files
Generate the following CSV files in the current working directory (or user-specified directory):
1. MARKDOWN-ACCESSIBILITY-FINDINGS.csv
Primary findings export with one row per issue instance.
Columns (in order):
| Column | Description | Example |
|---|---|---|
finding_id |
Unique identifier (auto-increment) | MD-001 |
file_path |
Markdown file path | docs/getting-started.md |
line_number |
Line number in the file | 42 |
severity |
Critical, Serious, Moderate, Minor | Serious |
confidence |
High, Medium, Low | High |
score_impact |
Points deducted from file score | -7 |
wcag_criteria |
WCAG 2.2 success criterion | 2.4.4 |
wcag_level |
A, AA, Cognitive | A |
domain |
Scan domain category | Descriptive Links |
rule_id |
Markdownlint rule or custom rule | MD034 |
issue_summary |
One-line description | Bare URL without descriptive link text |
content |
The problematic content or snippet | https://example.com |
pattern_type |
Systemic, File-specific | Systemic |
remediation_status |
New, Persistent, Fixed, Regressed | New |
auto_fixable |
Yes, No, Partial | Yes |
fix_suggestion |
Actionable fix description | Wrap URL in descriptive link text |
wcag_url |
WCAG understanding document link | https://www.w3.org/WAI/WCAG22/Understanding/link-purpose-in-context |
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.
- 2d ago First seen · 224 lines · 44 tokens per session scan A d6cb371deea0
markdown-csv-reporter is an agent published in the GitHub repository Community-Access/accessibility-agents (405 stars, last pushed 25d ago), licensed MIT. It adds 44 tokens to every session and 2,846 once invoked, about $0.0002 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.
Other agents, from other repositories
sheet-agent
XLSX creation, editing, and analysis using openpyxl and pandas.
engineer
Executes approved calculations and Excel modifications.
cell-engine-builder
셀, 시트, 수식 평가기, 내장 함수를 구현하여 전체 스프레드시트 엔진을 완성한다.
study-screener
当用户需要筛选文献检索结果、创建筛选表格、应用纳入/排除标准、追踪筛选决策或生成 PRISMA 流程图数据时，使用此 Agent。 Context: 用户从数据库检索中导出了 2500 篇文献，需要建立系统的筛选工作流 user: "我从 PubMed 和 Embase 检索中导出了 2500 篇文献的 RIS 文件。我该如何系统地筛选它们？" assistant: "我将帮你建立完整的筛选工作流。让我先读取你的 protocol.md 获取纳入标准，读取 search-strategy.md 获取检索的数据库信息，然后设计标题/摘要和全文筛选表格及决策规则，推荐双人独立筛选流程，并创建 screening-log.md…
Demonstrate
Agent for demonstrating VS Code features.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.