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 cognitedata/builder-skills --skill integrate-atlas-chatgit clone --depth 1 https://github.com/cognitedata/builder-skillsWrote 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/cognitedata/builder-skills/integrate-atlas-chat)<a href="https://agentmods.dev/skills/cognitedata/builder-skills/integrate-atlas-chat"><img src="https://agentmods.dev/badge/skills/cognitedata/builder-skills/integrate-atlas-chat/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/cognitedata/builder-skills/integrate-atlas-chat"><img src="https://agentmods.dev/badge/skills/cognitedata/builder-skills/integrate-atlas-chat.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
- Snyk pass
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 | $0.00077 | $0.00393 |
| Opus 5 | $0.00039 | $0.00197 |
| Sonnet 5 | $0.00015 | $0.00079 |
| Haiku 4.5 | $0.00008 | $0.00039 |
Grade A, and why
integrate-atlas-chat 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 7d 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.
What it actually says
Integrate Atlas Agent Chat (exception path)
Stop. Use integrate-fusion-agent (Atlas / EOS sidebar) unless all of:
- The user asked for an in-app / embedded chat — not "add Atlas" / "add a chat"
- The host Atlas sidebar cannot work. There is no manifest field for this. Probe the app:
@cognite/app-sdk+connectToHostApp/useHostAppresolving inside Fusion/EOS → sidebar works; do not continue- Standalone-only (host connect always rejects; app is never loaded in Fusion) → in-app chat is allowed
- If unsure, ask. Default to the sidebar.
- The user accepted this as the non-standard path
Then follow https://docs.cognite.com/cdf/flows/guides/ai_agent_integration and wire useAtlasChat for $ARGUMENTS. Keep the product UI; do not replace the app with a chat view.
Do not map send() / chat completions over DMS rows. If per-item completions are required: 5 per user action, ceiling 50, cache by space:externalId:lastUpdatedTime. See integrate-fusion-agent.
What ships with it
12 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.
- code/client.ts 4.3 KB runs code
- code/index.ts 760 B runs code
- code/pyodide-react.ts 4.3 KB runs code
- code/pyodide-runtime.ts 10.0 KB runs code
- code/pyodide.ts 567 B runs code
- code/python.ts 1.5 KB runs code
- code/react.ts 8.8 KB runs code
- code/session.test.ts 4.4 KB runs code
- code/session.ts 11 KB runs code
- code/types.ts 8.9 KB runs code
- code/validation.test.ts 1.3 KB runs code
- code/validation.ts 752 B runs code
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.
- 7d ago Changed · +14 lines · -35 tokens per session 3da7920874cc
- 11d ago First seen · 14 lines · 112 tokens per session scan A ea679ab37403
integrate-atlas-chat is a skill published in the GitHub repository cognitedata/builder-skills (6 stars, last pushed 3d ago), licensed Apache-2.0. It adds 77 tokens to every session and 393 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…
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…