datasource

datasource is a skill for Claude Code, Codex from CloudChef/atlasclaw-providers. It costs 68 tokens per session (2,886 once invoked), scanned A, original, Apache-2.0.

A read-only browser for SmartCMP reference information, such as service catalogs, projects, applications, operating-system templates, and machine images. SmartCMP is a system for managing cloud or data-centre resources.

In plain words
What is it for?
Use it to list business groups, applications, operating-system templates, images, service options, and other available resource details.
Why use it?
It lets an agent look up available choices and organizational scopes without submitting a provisioning request or changing resources.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/cloudchef/atlasclaw-providers/datasource
Any agent
npx skills add CloudChef/atlasclaw-providers --skill datasource
Clone the repo
git clone --depth 1 https://github.com/CloudChef/atlasclaw-providers

Made for: Claude Code, Codex.

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.

agentmods badge for datasource

README.md
[![agentmods](https://agentmods.dev/badge/skills/cloudchef/atlasclaw-providers/datasource.svg)](https://agentmods.dev/skills/cloudchef/atlasclaw-providers/datasource)
Your own site
<a href="https://agentmods.dev/skills/cloudchef/atlasclaw-providers/datasource"><img src="https://agentmods.dev/badge/skills/cloudchef/atlasclaw-providers/datasource.svg" alt="Measured on agentmods" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,886 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00068 $0.02886
Opus 5 $0.00034 $0.01443
Sonnet 5 $0.00014 $0.00577
Haiku 4.5 $0.00007 $0.00289

Measured 4d ago against content hash 6e8ed9b75a6a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

datasource 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 4d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/adapter.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

providers/SmartCMP-Provider/skills/datasource/SKILL.md · 337 lines

How it starts

The opening of the file, as written. The whole thing — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.

datasource

Reference data discovery skill (read-only).

Purpose

Query and browse reference data as standalone read-only operations. Use when user wants to explore available options without submitting a request. This skill owns standalone business-group scope discovery. Dedicated resource-pool and resource skills still handle standalone resource-pool and resource browsing.

Terminology Mapping

Treat SmartCMP business group as a generic organizational scope. Users may describe the same concept as:

  • tenant
  • 租户
  • 部门
  • BU
  • Department
  • 项目
  • Project

Resolve these terms against SmartCMP business-group data unless the user is clearly referring to some other system-level tenant concept. Mirror the user's wording in replies when it helps readability, but keep the SmartCMP field names businessGroupName and bgId when calling scripts or building request data.

Trigger Conditions

Activate this skill when user intent matches:

Intent Keywords
View business-group scopes "show business groups", "show tenants", "查看租户", "查看部门", "查看项目"
List applications "list applications", "show apps"
List OS templates "list OS templates", "available OS"
List images "list images", "available images"

NOT for: Resource provisioning -> use request skill instead. NOT for: Catalog discovery -> use request. NOT for: Direct "查询资源池", "查看所有资源", "查看所有云主机", or "查看某个云主机详情" requests -> use resource-pool or resource.

Handlers

All five datasource Tool commands are co-located in scripts/adapter.py:

Handler Tool Purpose
list_all_business_groups smartcmp_list_all_business_groups List standalone business-group scopes
list_applications smartcmp_list_applications List applications in a business group
list_components smartcmp_list_components List component metadata for a catalog source key
list_logical_templates smartcmp_query_logical_templates Query logical templates
list_images smartcmp_query_images Query cloud images

Read the full file on GitHub · 337 lines

Files

What ships with it

2 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.

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.

  1. 4d ago First seen · 337 lines · 68 tokens per session scan A 6e8ed9b75a6a

Subscribe to this mod's changes

datasource is a skill published in the GitHub repository CloudChef/atlasclaw-providers (15 stars, last pushed today), licensed Apache-2.0. It adds 68 tokens to every session and 2,886 once invoked, about $0.0003 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.