create-client-tool

create-client-tool is a skill for Claude Code, Codex from cognitedata/builder-skills. It costs 55 tokens per session (964 once invoked), scanned A, original, Apache-2.0.

A setup guide for creating a browser-side tool that an Atlas agent can call. The tool validates its inputs, runs code in the browser, and sends a result back to the agent.

In plain words
What is it for?
Use it when an Atlas agent needs to render charts, read local app state, show a panel, navigate, or trigger another browser action.
Why use it?
It provides the required structure for defining and connecting these tools instead of wiring them manually. This reduces errors in the tool schema and chat integration.

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/cognitedata/builder-skills/create-client-tool
Any agent
npx skills add cognitedata/builder-skills --skill create-client-tool
Clone the repo
git clone --depth 1 https://github.com/cognitedata/builder-skills

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 create-client-tool

README.md
[![agentmods](https://agentmods.dev/badge/skills/cognitedata/builder-skills/create-client-tool.svg)](https://agentmods.dev/skills/cognitedata/builder-skills/create-client-tool)
Your own site
<a href="https://agentmods.dev/skills/cognitedata/builder-skills/create-client-tool"><img src="https://agentmods.dev/badge/skills/cognitedata/builder-skills/create-client-tool.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 964 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 $0.00055 $0.00964
Opus 5 $0.00028 $0.00482
Sonnet 5 $0.00011 $0.00193
Haiku 4.5 $0.00006 $0.00096

Measured yesterday against content hash 97feba94a9e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

create-client-tool 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 yesterday.

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.

skills/create-client-tool/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create a Client Tool

Scaffold an AtlasTool named $ARGUMENTS. If the app has no approved in-app useAtlasChat, implement a Fusion action via integrate-fusion-agent instead.

Prerequisite: vendored src/atlas-agent/ and @sinclair/typebox from integrate-atlas-chat.

Background

Client tools let the Atlas Agent invoke browser-side logic — charts, local state, UI panels, navigation. The agent decides when to call; the app executes and returns a result.

  1. Agent responds with a clientTool action
  2. TypeBox validates the arguments
  3. execute() runs in the browser and returns { output, details }
  4. output (string) is sent back to the agent
  5. details is available on message.toolCalls for the UI to render

Step 1 — Understand the codebase

Before writing anything, read:

  • The file where useAtlasChat is called (often src/App.tsx or a chat hook) to find where tools is passed — imports are typically from ./atlas-agent/react after integrate-atlas-chat
  • Any existing tool definitions to match the file/naming conventions

Step 2 — Define the tool

Use Type from @sinclair/typebox for the parameters schema (compile-time types + runtime validation).

import { Type } from "@sinclair/typebox";
import type { AtlasTool } from "./atlas-agent/types";

export const myTool: AtlasTool = {
  name: "my_tool",            // snake_case — this is what the agent uses to invoke it
  description:
    "One sentence describing what this tool does and when the agent should call it.",
  parameters: Type.Object({
    exampleParam: Type.String({ description: "What this param is for" }),
    optionalNum: Type.Optional(Type.Number({ description: "..." })),
  }),
  execute: async (args) => {
    return {
      output: "Plain text summary sent back to the agent",
      details: {
        // Any structured data you want available in the UI via message.toolCalls
      },
    };
  },
};

Adjust the ./atlas-agent/... path if the tool file is not directly under src/ next to the atlas-agent folder (for example ../atlas-agent/types from src/tools/).

Read the full file on GitHub · 109 lines

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. yesterday Changed · -14 lines · -71 tokens per session 97feba94a9e0
  2. 5d ago First seen · 123 lines · 126 tokens per session scan A cf49565a62d7

Subscribe to this mod's changes

create-client-tool is a skill published in the GitHub repository cognitedata/builder-skills (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 55 tokens to every session and 964 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens