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 skills add kreuzberg-dev/kreuzberg-lts --skill wasm-constraintsgit clone --depth 1 https://github.com/kreuzberg-dev/kreuzberg-ltsWrote 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/skills/kreuzberg-dev/kreuzberg-lts/wasm-constraints)<a href="https://agentmods.dev/skills/kreuzberg-dev/kreuzberg-lts/wasm-constraints"><img src="https://agentmods.dev/badge/skills/kreuzberg-dev/kreuzberg-lts/wasm-constraints/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.
<a href="https://agentmods.dev/skills/kreuzberg-dev/kreuzberg-lts/wasm-constraints"><img src="https://agentmods.dev/badge/skills/kreuzberg-dev/kreuzberg-lts/wasm-constraints.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00003 | $0.00619 |
| Opus 5 | $0.00002 | $0.00309 |
| Sonnet 5 | $0.00001 | $0.00124 |
| Haiku 4.5 | $0.00000 | $0.00062 |
Grade A, and why
wasm-constraints 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 11d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
priority: high
WASM Build Constraints
Overview
WASM target in crates/kreuzberg-wasm/. Uses wasm-bindgen with sync-only internal APIs.
Feature Flags
[features]
wasm-target = ["pdf", "html", "xml", "email", "language-detection", "chunking", "quality", "office"]
wasm-threads = ["dep:wasm-bindgen-rayon"] # Optional
Critical Constraints
1. No Tokio Runtime
All operations must be synchronous internally. Use #[cfg(not(feature = "tokio-runtime"))] paths.
2. SyncExtractor Required
Every WASM-compatible extractor MUST implement SyncExtractor:
impl SyncExtractor for MyExtractor {
fn extract_sync(&self, content: &[u8], mime_type: &str, config: &ExtractionConfig)
-> Result<ExtractionResult> { /* sync implementation */ }
}
impl DocumentExtractor for MyExtractor {
fn as_sync_extractor(&self) -> Option<&dyn SyncExtractor> {
Some(self) // MUST return Some for WASM
}
}
3. HTML Size Limit
const MAX_HTML_SIZE: usize = 2 * 1024 * 1024; // 2MB - stack constraint
4. PDFium Initialization (from JS)
import init, { initialize_pdfium_render } from './kreuzberg_wasm.js';
const wasm = await init();
const pdfium = await pdfiumModule();
initialize_pdfium_render(pdfium, wasm, false); // REQUIRED for PDF
Build Config
[lib]
crate-type = ["cdylib", "rlib"]
[profile.release.package.kreuzberg-wasm]
opt-level = "z" # Size optimization
codegen-units = 1
API Pattern
#[wasm_bindgen]
pub async fn extract_from_bytes(content: Vec<u8>, config: JsValue) -> Result<JsValue, JsValue> {
let config: ExtractionConfig = serde_wasm_bindgen::from_value(config)?;
let result = extract_bytes_sync(&content, mime_type, &config)?;
Ok(serde_wasm_bindgen::to_value(&result)?)
}
Functions can be async for JS compatibility, but internal extraction is sync.
Critical Rules
- No tokio — all operations synchronous
- Implement SyncExtractor for all WASM-compatible extractors
- HTML limited to 2MB due to stack constraints
- PDFium requires manual JS initialization
- Size optimization via
opt-level = "z" - Feature gate with
#[cfg(target_arch = "wasm32")]
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.
- 11d ago First seen · 92 lines · 3 tokens per session scan A e58f4bf58e5e
wasm-constraints is a skill published in the GitHub repository kreuzberg-dev/kreuzberg-lts (15 stars, last pushed yesterday), licensed MIT. It adds 3 tokens to every session and 619 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 2026-08-30.
Other skills, from other repositories
doc-reader
PDF/DOCX/XLSX/image document intelligence — text extraction, table parsing, OCR, financial statement analysis, contract clause detection, document classification, and format conversion. Use when reading, analyzing, extracting data from, or converting documents.
rust-patterns
Idiomatic Rust patterns, ownership, error handling, traits, concurrency, and best practices for building safe, performant applications.
paddleocr-doc-parsing
A document-parsing tool configuration for extracting structured Markdown or JSON from complex PDFs and document images, including tables, formulas, charts, and multi-column pages.
dd-code-generation
Use pup CLI for immediate Datadog operations or generate code for integration into applications.
omh-rust
This is a Hermes-native rust workflow skill.
rust-project
Modern Rust project architecture guide for 2025. Use when creating Rust projects (CLI, web services, libraries). Covers workspace structure, error handling, async patterns, and idiomatic Rust best practices.