resource-pool

resource-pool is a skill for Claude Code, Codex from CloudChef/atlasclaw-providers. It costs 73 tokens per session (756 once invoked), scanned A, original, Apache-2.0.

A read-only directory for browsing SmartCMP resource pools, which group resources available through the platform.

In plain words
What is it for?
Use it to list all pools or filter them by a keyword, then view their names in a numbered list.
Why use it?
It lets you find resource pools without supplying technical identifiers needed for resource requests.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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/resource-pool
Any agent
npx skills add CloudChef/atlasclaw-providers --skill resource-pool
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 resource-pool

README.md
[![agentmods](https://agentmods.dev/badge/skills/cloudchef/atlasclaw-providers/resource-pool.svg)](https://agentmods.dev/skills/cloudchef/atlasclaw-providers/resource-pool)
Your own site
<a href="https://agentmods.dev/skills/cloudchef/atlasclaw-providers/resource-pool"><img src="https://agentmods.dev/badge/skills/cloudchef/atlasclaw-providers/resource-pool.svg" alt="Measured on agentmods" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 756 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 5.1 $0.00073 $0.00756
Opus 5 $0.00036 $0.00378
Sonnet 5 $0.00015 $0.00151
Haiku 4.5 $0.00007 $0.00076

Measured 6d ago against content hash dc0531fa3577, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

resource-pool 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 6d 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/resource-pool/SKILL.md · 90 lines

What it actually says

resource-pool

List SmartCMP resource pools through the same standalone directory endpoint used by the CMP UI.

Purpose

Provide a precise, read-only skill for direct resource-pool browsing.

  • Query /resource-bundles
  • Default to the first 50 resource pools and use page for further results
  • Support optional keyword filtering with query_value
  • Return a numbered list for the user and a machine-readable metadata block for follow-up actions

Critical Rules

  • Do not ask for businessGroupId, sourceKey, or nodeType when the user only wants to browse resource pools.
  • Do not switch to the request workflow unless the user is actually preparing a request.
  • Keep the user-visible output to the numbered list of resource-pool names.
  • Treat IDs and other metadata as hidden backend state unless the user explicitly asks for them.

Handler

scripts/adapter.py:list_resource_pools converts the optional Tool query and calls the SmartCMP Provider directory operation. This Skill has one Tool, so one direct handler file is appropriate; no extra forwarding Python is kept.

Files

What ships with it

1 file 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. 6d ago First seen · 90 lines · 73 tokens per session scan A dc0531fa3577

Subscribe to this mod's changes

resource-pool is a skill published in the GitHub repository CloudChef/atlasclaw-providers (15 stars, last pushed 2d ago), licensed Apache-2.0. It adds 73 tokens to every session and 756 once invoked, about $0.0004 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.