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 config-loading-precedencegit 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/config-loading-precedence)<a href="https://agentmods.dev/skills/kreuzberg-dev/kreuzberg-lts/config-loading-precedence"><img src="https://agentmods.dev/badge/skills/kreuzberg-dev/kreuzberg-lts/config-loading-precedence/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/config-loading-precedence"><img src="https://agentmods.dev/badge/skills/kreuzberg-dev/kreuzberg-lts/config-loading-precedence.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 | $0.00464 |
| Opus 5 | $0.00002 | $0.00232 |
| Sonnet 5 | $0.00001 | $0.00093 |
| Haiku 4.5 | $0.00000 | $0.00046 |
Grade A, and why
config-loading-precedence 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 12d 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.
What it actually says
priority: high
Configuration Loading & Precedence
CLI Mode Precedence (highest → lowest)
- Individual CLI flags (
--ocr,--output-format,--chunk) - Inline JSON config (
--config-jsonor--config-json-base64) - Config file (
--config path.toml) - Auto-discovered config (
kreuzberg.{toml,yaml,json}in cwd/parents) - Default values
Server/MCP Mode Precedence
- CLI arguments (
--host,--port) - Environment variables (
KREUZBERG_HOST,KREUZBERG_PORT) - Config file
[server]section - Defaults (
127.0.0.1:8000)
Config File Discovery
Searches current directory and parents for kreuzberg.toml, kreuzberg.yaml, or kreuzberg.json. Stops at first match.
Inline JSON Config
Field-level merge (not whole-object replacement):
fn merge_json_into_config(base: &ExtractionConfig, json: Value) -> Result<ExtractionConfig> {
let mut config_json = serde_json::to_value(base)?;
// Merge fields from json into config_json
serde_json::from_value(merged)?
}
Use --config-json-base64 for shell escaping.
Config File Formats
TOML (kreuzberg.toml):
use_cache = true
[ocr]
backend = "tesseract"
languages = ["eng", "deu"]
[security_limits]
max_archive_size = 524288000
YAML and JSON follow equivalent structure.
CLI Flag Overrides
In commands.rs: apply_extraction_overrides() applies individual flags on top of merged config.
Critical Rules
- CLI flags always win over config file
- JSON merge is field-level, not whole-object
- Auto-discovery stops at first config file found
--config-json-base64for shell-safe JSON passing- Server config uses
[server]section + extraction config
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.
- 12d ago First seen · 69 lines · 3 tokens per session scan A e68a601a6b02
config-loading-precedence 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 464 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.
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.
paddleocr-text-recognition
An optical character recognition tool configuration for extracting text from images, photos, scans, screenshots, and scanned PDFs. OCR means converting text visible in an image into machine-readable text.
ade
Parse documents and extract schema-shaped data with the ADE (Agentic Document Extraction) v2 APIs through the ade CLI. A local job-item store makes every run idempotent, resumable, and citable — repeat runs are free, interrupted runs resume, and every answer can cite element ids with visual evidence.
document-processing
Use when the deliverable is a document's bytes or its literal content — text/tables out of PDFs, AcroForm fill and flatten, page merge/split, PDF/DOCX from templates, OCR of image-only scans. NOT schema-typed fields pulled from text (that is structured-extraction), NOT signature routing (e-signature) or spreadsheet…
document-processing-expert
Read, generate and modify office documents and PDFs from code: PDF extraction and forms, Word documents, Excel workbooks and PowerPoint decks. Use when the user mentions PDF, DOCX, XLSX, PPTX, Word, Excel, PowerPoint or spreadsheets, wants data extracted from documents, needs a report or invoice generated as a file…