What is core-conversion-architecture?

A technical guide to the Rust code that converts HTML into Markdown. It explains the two conversion paths, element-specific converters, output options, input checks, and visitor hooks.

Use it when modifying HTML-to-Markdown output, parser behavior, traversal hooks, conversion settings, input validation, or depth limits in the core crate.

It helps developers change conversion, parsing, or input-safety behavior without using the wrong part of the codebase or assuming that converted Markdown is safe to render. It also records important implementation boundaries and file locations.

core-conversion-architecture — Skill for Claude Code by xberg-io

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 xberg-io/html-to-markdown --skill core-conversion-architecture

Clone the repo

git clone --depth 1 https://github.com/xberg-io/html-to-markdown

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/xberg-io/html-to-markdown/core-conversion-architecture/github.svg)](https://agentmods.dev/skills/xberg-io/html-to-markdown/core-conversion-architecture)

Your own site

<a href="https://agentmods.dev/skills/xberg-io/html-to-markdown/core-conversion-architecture"><img src="https://agentmods.dev/badge/skills/xberg-io/html-to-markdown/core-conversion-architecture/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/xberg-io/html-to-markdown/core-conversion-architecture"><img src="https://agentmods.dev/badge/skills/xberg-io/html-to-markdown/core-conversion-architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 575 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.

Model	Per session	Once invoked
Fable 5.1	$0.00049	$0.00575
Opus 5.5	$0.00020	$0.00230
Sonnet 5.5	$0.00010	$0.00115
Haiku 4.5	$0.00005	$0.00057

Measured 2d ago against content hash 98339aeac74c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

core-conversion-architecture 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.

.ai-rulez/skills/core-conversion-architecture/SKILL.md · 37 lines

What it actually says

Core Conversion Architecture

All paths are under crates/html-to-markdown/src/.

Pipeline

convert() in convert_api.rs checks max_input_size, normalizes the input, tries Tier-1, then falls back to Tier-2.
Tier-1: byte scanner in converter/tier1/.
Tier-2: astral-tl DOM walk, walk_node in converter/main.rs; html5ever is used for tree repair.
ConversionOptions::tier_strategy (Auto default, Tier2, Tier1 testkit only) picks the path.
Per-element converters live under converter/ (block/, inline/, list/, form/, media/, semantic/, text/).
Output is shaped by ConversionOptions in options/conversion.rs (heading style, list indent, code block style, newline style, whitespace mode).
Caller traversal hooks: HtmlVisitor trait in visitor/traits.rs (feature visitor). There is no DomWalker trait.

Input safety (not output sanitization)

Converted Markdown is not safe to render as trusted content; callers sanitize downstream. See SECURITY.md.
validate_input() in validation.rs rejects binary input: gzip/zstd/zip/PDF magic bytes, excess NUL bytes, high control-character ratio, undeclared UTF-16. It does not inspect HTML elements, attributes or URLs.
max_input_size (Option<u64>) returns ConversionError::InputTooLarge; default is None natively and 2 MiB on wasm32.
max_depth bounds the Tier-2 walk to avoid stack overflow; effective_max_depth in converter/main_helpers.rs defaults it and clamps caller values to a ceiling.
ConversionError::SanitizationError exists in error.rs and in binding error mappings, but the core never constructs it.
Script and style are stripped (markup fidelity, not security); javascript:/data: URLs and event-handler attributes pass through.
There is no SafetyConfig, URL scheme allow-list or attribute allow-list.

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.

index.md 289 B

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.

2d ago First seen · 37 lines · 49 tokens per session scan A 98339aeac74c

Subscribe to this mod's changes

core-conversion-architecture is a skill published in the GitHub repository xberg-io/html-to-markdown (885 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 575 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 2026-10-27.

Debugging RAG and vectors hocr html-converter markdown-converter text-extraction text-processing

mcp-apps-builder

MANDATORY for ALL MCP server work - mcp-use framework best practices and patterns. READ THIS FIRST before any MCP server work, including: Creating new MCP servers Modifying existing MCP servers (adding/updating tools, resources, prompts, widgets) Debugging MCP server issues or errors Reviewing MCP server code for…

Shubhamsaboo/awesome-llm-apps · 139 tokens

mem0-status

Diagnoses mem0 connectivity, API key validity, and memory read/write functionality. Use when memory operations fail, searches return empty, addmemory errors occur, or to verify the plugin is working correctly.

mem0ai/mem0 · 44 tokens

plugin-architecture-patterns

Xberg plugin traits, typed registries, priority collisions, lifecycle and Alef Python plugin bridges. Use for plugin-system work, not parsing.

xberg-io/xberg · 29 tokens

xberg-chunking

Use when splitting extracted text into chunks for LLM context windows or RAG ingestion. Covers chunk size, overlap, markdown/yaml/semantic chunkers, tokenizer-based sizing, and the standalone chunk command.

xberg-io/xberg · 43 tokens

xberg-extracting-keywords

Use when extracting keywords (YAKE/RAKE) from documents — and, secondarily, when detecting document language or generating embeddings for RAG and search. Covers the keyword config (and its feature gating), --detect-language, and the standalone embed command with real flags.

xberg-io/xberg · 58 tokens

test-corpus

The testdocuments corpus (submodule, bucket-fetched): readtestfixture, missing fixtures, A/B controls. Use on a fresh clone or a missing fixture.

xberg-io/xberg · 33 tokens