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 cruxible-ai/cruxible --skill prepare-datagit clone --depth 1 https://github.com/cruxible-ai/cruxibleWrote 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/cruxible-ai/cruxible/prepare-data)<a href="https://agentmods.dev/skills/cruxible-ai/cruxible/prepare-data"><img src="https://agentmods.dev/badge/skills/cruxible-ai/cruxible/prepare-data/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/cruxible-ai/cruxible/prepare-data"><img src="https://agentmods.dev/badge/skills/cruxible-ai/cruxible/prepare-data.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00037 | $0.00969 |
| Opus 5 | $0.00018 | $0.00485 |
| Sonnet 5 | $0.00007 | $0.00194 |
| Haiku 4.5 | $0.00004 | $0.00097 |
Grade A, and why
prepare-data 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prepare Data
Use this skill before create-state, and before overlay-and-fit whenever local source files need to be loaded into an overlay.
Cruxible validates, loads, and evaluates. File cleaning and transforms are external.
This skill is about source-data preparation only:
- profiling files
- validating keys and joins
- checking grain and cardinality
- identifying cleaning and transform work
- producing cleaned files or a preparation plan
It is not for cross-dataset matching or governed relationship design. Those happen later in the state-building flow.
Use your own tools freely here: Python, Polars, SQL, spreadsheets, or shell tooling. The goal is to hand the later skills source files that are understood, defensible, and ready.
Workflow
Phase 1: Inventory the files
For each file, identify:
- what the file appears to represent
- whether it looks like an entity source, deterministic relationship source, reference file, or unknown source
- what its likely row grain is
- what other files it seems to join to
Do not assume the target state shape is already known. This skill is part of discovering it.
Phase 2: Profile each file
For every source file, inspect:
- row count
- columns
- dtypes
- null counts
- sample rows
- obvious schema inconsistencies across files of the same kind
Do not stop at one-line summaries. The point is to understand what later modeling and loading work would actually consume.
Phase 3: Validate entity keys and relationship joins
For likely entity files, check:
- duplicate primary keys
- null or empty IDs
- whitespace, prefix garbage, or sentinel values in IDs
- whether the file grain is really one row per entity
For likely deterministic relationship files, check:
- source and target key columns exist
- foreign keys actually resolve against the referenced entity files
- duplicate
(from, to, relationship_type)rows - whether the file grain is really one row per relationship
Across files, check:
- shared join columns exist where expected
- values actually overlap
- types are compatible
- normalization work is needed before joins can succeed
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 · 150 lines · 37 tokens per session scan A 1a8146785495
prepare-data is a skill published in the GitHub repository cruxible-ai/cruxible (17 stars, last pushed 2d ago), licensed Apache-2.0. It adds 37 tokens to every session and 969 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 2026-08-30.
Other skills, from other repositories
n8n-agents
Design n8n AI agents the right way. Use when building or editing any @n8n/n8n-nodes-langchain. AI node — an AI Agent, LLM chain, Text Classifier, or Information Extractor — and whenever the user mentions AI agents, LLM with tools, tool calling, $fromAI, system prompts, agent memory, sessionId, structured/JSON output…
open-ontologies
AI-native ontology engineering using 50+ MCP tools backed by an in-memory Oxigraph triple store. Build, validate, query, and govern RDF/OWL ontologies with a generate-validate-iterate loop. Use when building ontologies, knowledge graphs, RDF data, SPARQL queries, BORO/4D modeling, SHACL validation, clinical…
blockrun
Pay-per-call access to AI models, real-time data, media generation and multi-chain RPC over x402 micropayments (USDC on Base or Solana). No API keys, no accounts, no subscriptions. Start here when you have the BlockRun MCP installed and need to know WHICH tool answers a question, how the wallet works, or how to make a…
solr-semantic-search
To build Solr phrase-tagging semantic search: concept tagging, taxonomy, graph paths.
opik-instrument
Add Opik tracing to an existing app and verify a real trace lands. Installs the Opik package, detects the language and LLM framework, adds the minimum tracing, runs a safe representative path, confirms a trace in Opik, and returns the trace link. Use for "instrument my code", "add opik tracing", "add observability"…
haiku-rag
Search, read and compute over the user's haiku.rag knowledge base through the haiku-rag MCP tools. Use whenever a request could be answered from the user's ingested documents, when asked to find, look up, check or cite something in their documents or knowledge base, or when the question is about the user's own…