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 GoalfyAI/goalfydata --skill skillgit clone --depth 1 https://github.com/GoalfyAI/goalfydataWrote 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/goalfyai/goalfydata/skill)<a href="https://agentmods.dev/skills/goalfyai/goalfydata/skill"><img src="https://agentmods.dev/badge/skills/goalfyai/goalfydata/skill/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/goalfyai/goalfydata/skill"><img src="https://agentmods.dev/badge/skills/goalfyai/goalfydata/skill.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 | $0.00151 | $0.18112 |
| Opus 5 | $0.00076 | $0.09056 |
| Sonnet 5 | $0.00030 | $0.03622 |
| Haiku 4.5 | $0.00015 | $0.01811 |
Grade C, and why
goalfydata scanned grade C with 2 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 9d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://cdn.goalfydata.ai/dataset-uds/install.sh | sh Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**Agent-run installation and sandbox elevation (Claude Code / Codex)**: the current conversation already runs inside the platform's sandbox and permission flow. Run every uds-cli install, update, login, and configuration This is a copy
100% identical to goalfydata — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 946 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GoalfyData
Persist the user's business data as a structured dataset asset that is independent of projects and conversations and reusable and shareable across Agents / services / machines, and support developing datasets into publicly accessible data apps.
This document is the main guide with the complete execution flows. The sub-guides below provide supplementary reference:
references/dataset-building-guide.md— business interview matrix, table naming rules, PG syntax pitfalls, pre-create checklistreferences/data-quality-guide.md— dirty-data classification and detection methodsreferences/scheduled-sync-guide.md— script spec and fetch standard template, sandbox rules, external data-source templates (MySQL chunked, API paged), multi-table coordination, troubleshootingreferences/app-deploy-guide.md— app template structure, development conventions, version management detailsThe paths above are relative to the directory containing this SKILL.md, not to your working directory —
references/always sits next to this file. When reading a sub-guide or reopening this file, use the path the platform provided when loading the skill; if you cannot find it, search by filename (e.g.SKILL.md,dataset-building-guide*) instead of reconstructing path segments from memory. When installed as a plugin (Claude Code / Codex), note that the install path repeats "goalfydata" at several consecutive levels with a version directory in between (e.g..../plugins/cache/goalfydata/goalfydata/<version>/skills/goalfydata/).
Prerequisites
Required MCP Server: goalfydata-mcp
The GoalfyData MCP Server provides 20 tools (15 dataset management-plane tools + 5 app development/deployment tools); all operations go through the GoalfyData backend API.
MCP configuration (streamable-http transport, API Key auth, Bearer scheme):
{
"goalfydata-mcp": {
"type": "streamable-http",
"url": "https://mcp.goalfydata.ai/mcp",
"headers": {
"Authorization": "Bearer ${GOALFY_UDS_API_KEY}"
}
}
}
What ships with it
4 files 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.
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.
- 9d ago First seen · 946 lines · 151 tokens per session scan C 9c7dd6c191d6
goalfydata is a skill published in the GitHub repository GoalfyAI/goalfydata (9 stars, last pushed 16d ago), licensed Apache-2.0. It adds 151 tokens to every session and 18,112 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). It is 100% identical to goalfydata, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
metabase-data-app-semantic-layer
Use when building, creating, or editing data apps that should query Metabase tables and metrics through generated schema files like metabase.data.ts or .metabase.data.ts.
doris-debug-import
Use for Doris Stream/Broker/Routine Load issues and Group Commit asyncmode WAL pile-up. Tunables: table groupcommitintervalms / groupcommitdatabytes; BE groupcommitinsertthreads, groupcommitwalpath, groupcommitwalmaxdisklimit.
exasol-import-export
Exasol IMPORT and EXPORT SQL statements: syntax, file formats (CSV, FBV, Parquet), cloud storage (S3, Azure, GCS), connection objects, error handling, and ETL staging patterns.
gen-table
Create database tables from SQL (CTAS) or natural language descriptions.
import
Use when import jobs are slow, timing out, or failing — Stream Load, Broker Load, Routine Load, INSERT INTO, Flink connector. Covers write-slow triage (asyncdeltawriter / memtableflush / segmentreplicatesync thread pools), publish timeout on PK tables, RPC Failed errors, Reached timeout auto-diagnostics (v3.4+), and…
nextjs-dashboard
Next.js 15+ App Router dashboard skill — server/client components, mobile nav, polling, data tables, skeleton states, and production-grade dashboard UX patterns.