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 kedro-org/kedro-skills --skill kedro-build-demogit clone --depth 1 https://github.com/kedro-org/kedro-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/kedro-org/kedro-skills/kedro-build-demo)<a href="https://agentmods.dev/skills/kedro-org/kedro-skills/kedro-build-demo"><img src="https://agentmods.dev/badge/skills/kedro-org/kedro-skills/kedro-build-demo/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/kedro-org/kedro-skills/kedro-build-demo"><img src="https://agentmods.dev/badge/skills/kedro-org/kedro-skills/kedro-build-demo.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 | $0.00078 | $0.04837 |
| Opus 5.5 | $0.00031 | $0.01935 |
| Sonnet 5.5 | $0.00016 | $0.00967 |
| Haiku 4.5 | $0.00008 | $0.00484 |
Grade A, and why
kedro-build-demo 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 9d 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 — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build a Kedro demo
Scope
Every demo you build or prepare includes a self-contained DEMO.html walkthrough in the project root. The working project saves a result that answers the user's question and can be explored in Kedro-Viz. Slides, separate architecture diagrams, Markdown walkthroughs and technical overviews are extras, made only when asked.
- Build in a new folder, or in a fresh blank project the user created for the demo (template files only, no pipelines yet). If the current folder is a project with real pipelines, leave it untouched and ask where the demo should go.
- For a question only about whether Kedro fits, answer it (step 1) and offer to build. Create nothing yet.
- Out of scope: changing or explaining an existing project (
explain-projectcovers explaining), deployment, production hardening and serving live requests.
CRITICAL:
- Say plainly where Kedro helps and where it does not.
- A demo "works" only for the exact command you ran and whose result you inspected. If something blocked the run, hand it over as prepared but unverified.
- Keep real secret values out of code, docs, outputs and shareable configuration. Reference them by name; ignored local credential files are fine. Never open, print or grep a credential file such as
conf/local/credentials.ymlor.env(step 4), and exclude them from bulk reads and searches. Never print environment variable values or the whole environment; check only whether a required key is set. - Before writing any file, show a short plan, even if you continue straight away.
- Always create
DEMO.htmlfor a demo you build or prepare, and link it fromREADME.md. - Label every simulated component wherever it appears.
- Get the user's OK before installing packages or making paid or external calls, unless they already gave it.
1. Understand the request and Kedro's role
Take what the request already says, then establish:
- the use case and the result they want to see. That may be a cleaned table, an aggregate, a report, a score or an evaluation;
- the data: theirs, or a generated sample;
- the stack or framework they use or prefer;
- who will watch the demo, when that changes what you deliver;
- constraints such as no API key, no network or limited time;
- how they will judge that it works.
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.
- 9d ago First seen · 271 lines · 78 tokens per session scan A 3fe9cdd3c978
kedro-build-demo is a skill published in the GitHub repository kedro-org/kedro-skills (7 stars, last pushed yesterday), licensed Apache-2.0. It adds 78 tokens to every session and 4,837 once invoked, about $0.0003 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 2026-10-29.
kedro-build-demo compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| kedro-build-demokedro-org/kedro-skills | Skill | 7 | yesterday | Apache-2.0 | A | 78 | Claude Code, Codex |
| fs-notebook-tabsnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 47 | Claude Code, Codex |
| model-architecture-litgptdavila7/claude-code-templates | Skill | 33k | yesterday | MIT | A | 75 | Claude Code, Codex |
| model-architecture-nanogptdavila7/claude-code-templates | Skill | 33k | yesterday | MIT | A | 69 | Claude Code, Codex |
| model-architecture-rwkvdavila7/claude-code-templates | Skill | 33k | yesterday | MIT | A | 74 | Claude Code, Codex |
| kaggle-learnerGalaxy-Dawn/claude-scholar | Skill | 6.0k | 18d ago | MIT | A | 69 | Claude Code |
| data-science-engineering-foundationmicrosoft/hve-core | Skill | 1.6k | yesterday | MIT | A | 43 | Claude Code |