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 start-flows-appgit 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/start-flows-app)<a href="https://agentmods.dev/skills/cognitedata/builder-skills/start-flows-app"><img src="https://agentmods.dev/badge/skills/cognitedata/builder-skills/start-flows-app/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/start-flows-app"><img src="https://agentmods.dev/badge/skills/cognitedata/builder-skills/start-flows-app.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 | $0.00147 | $0.01282 |
| Opus 5.5 | $0.00059 | $0.00513 |
| Sonnet 5.5 | $0.00029 | $0.00256 |
| Haiku 4.5 | $0.00015 | $0.00128 |
Grade A, and why
start-flows-app 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Start a Flows custom app
Get a clickable https://localhost prototype running quickly. The user story,
data-model curiosity, and App-Brief.md can proceed in parallel after
localhost is up. Missing appHostingAcl WRITE is a parallel track, not a
gate.
The Fusion prompt already covers the folder check, apps create and auth login with CDF flags filled in, "createdVia", apps skills pull, serving
https://localhost:<port>, and this project's MCP command. Run those
commands as given; do not re-ask org, project, cluster, or base URL. If
browser login stalls, loops, or never persists a session, stop and ask the
builder. This skill picks up from there.
Do not dump an empty App-Brief template as the opening move. Do not invent mkcert / brew / choco steps. Do not paste this skill body back into chat.
If a Fusion Custom apps prompt set "createdVia" on app.json, leave that
field as-is.
1. Clickable prototype on https://localhost
Serve the scaffold and open https://localhost:<port> in the browser. Fusion
loads the app at that URL. Do not wait for a finished persona or App-Brief.
Help them over certificate warnings with:
npx @cognite/cli@latest apps setup-https
Docs: https://docs.cognite.com/cdf/flows/guides/local-https
Do not invent mkcert steps. The scaffold already uses vite-plugin-mkcert
(see setup-flows-auth).
Catalog listing in Fusion Custom apps needs deploy plus appHostingAcl WRITE.
Say that once so they do not think the catalog is broken, then keep going.
2. Connect Industrial MCP
Follow connect-atlas-mcp: run the MCP command from the Fusion prompt as written, then finish OAuth in the browser. Do not rebuild the MCP URL or pick client ids here.
Docs: https://docs.cognite.com/cdf/build/industrial_mcp
3. Check app hosting access — REST, not an MCP query tool
Industrial MCP is graph / time series / documents. It does not inspect IAM. Do not invent an MCP query tool for this check.
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.
- 1mo ago First seen · 126 lines · 147 tokens per session scan A 199da95299bc
start-flows-app is a skill published in the GitHub repository cognitedata/builder-skills (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 147 tokens to every session and 1,282 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-09-29.
start-flows-app compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| start-flows-appcognitedata/builder-skills | Skill | 6 | yesterday | Apache-2.0 | A | 147 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 314k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |