Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/shepsci/kaggle-skillnpx agentmods add skills/shepsci/kaggle-skill/kaggleWrote 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/shepsci/kaggle-skill/kaggle)<a href="https://agentmods.dev/skills/shepsci/kaggle-skill/kaggle"><img src="https://agentmods.dev/badge/skills/shepsci/kaggle-skill/kaggle/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/shepsci/kaggle-skill/kaggle"><img src="https://agentmods.dev/badge/skills/shepsci/kaggle-skill/kaggle.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
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 | $0.00100 | $0.02668 |
| Opus 5.5 | $0.00040 | $0.01067 |
| Sonnet 5.5 | $0.00020 | $0.00534 |
| Haiku 4.5 | $0.00010 | $0.00267 |
Grade A, and why
kaggle 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 19d 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 — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kaggle
Kaggle for coding agents: competition research, running a competition (status, submissions, scores), datasets, models, notebooks, discussions and solution writeups, benchmarks, and badges.
This is an independent, unofficial project. It is not affiliated with, endorsed by, or sponsored by Kaggle or Google.
Do not use this skill for generic machine learning, GPU, notebook, dataset, model, benchmark, or data-science work unless the user ties the task to Kaggle.
Run a command
Everything is one command with a name:
python3 scripts/kaggle_skill.py <command> [arguments]
python3 scripts/kaggle_skill.py <command> --help
Paths in this file are relative to the skill folder, the one that holds this
SKILL.md. Run every command from the user's working directory as
python3 <skill folder>/scripts/kaggle_skill.py <command>, so that downloads
and records land in the user's project. Do not cd into the skill folder.
Output is short text by default. The read commands take --json for the
same content as JSON; <command> --help lists each command's options. A
long text (a page, a writeup) is cut with a note that says how to get the
rest, so there is no need to pipe a command through head or cut. A
competition is a slug (titanic) or its URL.
Pick the command
| The user wants | Command |
|---|---|
| What a competition is: metric and how it is scored, deadline, prize, limits | brief <competition> [<competition> ...] |
| The rules, the evaluation page, the data description | pages <competition> --page rules (no --page: the list) |
| What worked: solution writeups by rank | solutions <competition> --preview |
| Writeups in full, one or several | writeup <id or URL> [<id or URL> ...] |
| What people are discussing | topics --competition <competition>, then topic <id> |
| Which competitions are running, with each one's prize and metric | competitions; competitions --mine |
| Data files, top of the leaderboard, popular notebooks | details <competition> |
| Where they stand: time left, submissions left, scores, GPU hours | status <competition> |
| The leaderboard, the gap to the medal lines, what moved | leaderboard <competition> |
| The competition's data | download <competition> [dir] --unzip |
| Whether a submission file is well formed | validate <competition> <file> |
| To submit | submit <competition> <file> -m "message" (its dry run checks the file too), then watch <competition> |
| What was submitted and how it scored | ledger |
| A simulation submission's games | episodes <submission id> |
| A hackathon's pages, its writeups | hackathon <competition>, writeups <competition> --winners |
| A dataset or a model | dataset-download owner/name [dir], model-download owner/model/framework/variation [dir] |
| To publish a dataset or a model | dataset-publish owner/name <dir>, model-publish <handle> <dir> |
| To run a notebook on Kaggle | notebook-run <dir>; notebook-wait owner/name |
| Setup problems | doctor; credentials --verify |
| Anything else the Kaggle CLI does | cli -- <kaggle arguments> |
What ships with it
60 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.
- modules/badges/README.md 1.6 KB
- modules/badges/references/badge-catalog.md 6.6 KB
- modules/badges/scripts/badge_registry.py 8.5 KB runs code
- modules/badges/scripts/badge_tracker.py 4.1 KB runs code
- modules/badges/scripts/orchestrator.py 5.3 KB runs code
- modules/badges/scripts/phase_1_instant_api.py 24 KB runs code
- modules/badges/scripts/phase_2_competition.py 14 KB runs code
- modules/badges/scripts/phase_3_pipeline.py 12 KB runs code
- modules/badges/scripts/phase_4_browser.py 2.2 KB runs code
- modules/badges/scripts/phase_5_streaks.py 5.6 KB runs code
- modules/badges/scripts/templates/dataset-metadata.json 871 B
- modules/badges/scripts/templates/kernel-metadata.json 412 B
- modules/badges/scripts/templates/model-instance-metadata.json 253 B
- modules/badges/scripts/templates/model-metadata.json 355 B
- modules/badges/scripts/templates/python_notebook.ipynb 1.3 KB
- modules/badges/scripts/templates/r_notebook.ipynb 1.1 KB
- modules/badges/scripts/templates/README_dataset.md 573 B
- modules/badges/scripts/templates/submission_titanic.csv 2.8 KB
- modules/badges/scripts/templates/utility_script.py 802 B runs code
- modules/badges/scripts/utils.py 3.9 KB runs code
- modules/benchmarks/README.md 1.2 KB
- modules/benchmarks/references/benchmark-endpoints.md 1.6 KB
- modules/benchmarks/references/benchmarks-cli.md 4.4 KB
- modules/competitions/hackathons/README.md 2.9 KB
- modules/competitions/hackathons/references/episode-endpoints.md 2.2 KB
- modules/competitions/hackathons/references/hackathon-endpoints.md 4.6 KB
- modules/competitions/hackathons/scripts/fetch_writeup.py 11 KB runs code
- modules/competitions/hackathons/scripts/hackathon_overview.py 1.5 KB runs code
- modules/competitions/hackathons/scripts/list_writeups.py 9.9 KB runs code
- modules/competitions/README.md 5.8 KB
- modules/competitions/references/competition-categories.md 2.1 KB
- modules/competitions/references/competition-operations.md 5.7 KB
- modules/competitions/references/competition-overview.md 3.9 KB
- modules/competitions/references/competition-research.md 3.0 KB
- modules/competitions/scripts/competition_brief.py 5.4 KB runs code
- modules/competitions/scripts/competition_details.py 8.2 KB runs code
- modules/competitions/scripts/competition_download.py 5.1 KB runs code
- modules/competitions/scripts/competition_episodes.py 9.2 KB runs code
- modules/competitions/scripts/competition_leaderboard.py 12 KB runs code
- modules/competitions/scripts/competition_ledger.py 3.3 KB runs code
- modules/competitions/scripts/competition_pages.py 1.7 KB runs code
- modules/competitions/scripts/competition_status.py 9.0 KB runs code
- modules/competitions/scripts/competition_submit.py 8.9 KB runs code
- modules/competitions/scripts/competition_validate.py 14 KB runs code
- modules/competitions/scripts/competition_watch.py 5.9 KB runs code
- modules/competitions/scripts/list_competitions.py 13 KB runs code
- modules/datasets/README.md 2.1 KB
- modules/datasets/references/kagglehub-datasets.md 2.6 KB
- modules/datasets/scripts/dataset_download.py 4.1 KB runs code
- modules/datasets/scripts/dataset_publish.py 5.5 KB runs code
- modules/discussions/README.md 2.1 KB
- modules/discussions/references/writeups.md 5.8 KB
- modules/discussions/scripts/forums.py 22 KB runs code
- modules/discussions/scripts/leaderboard_writeups.py 25 KB runs code
- modules/models/README.md 2.6 KB
- modules/models/references/kagglehub-models.md 1.7 KB
- modules/models/scripts/model_download.py 4.5 KB runs code
- modules/models/scripts/model_publish.py 8.7 KB runs code
- modules/notebooks/README.md 2.6 KB
- modules/notebooks/scripts/notebook_push.py 5.7 KB 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.
- 19d ago Changed · +2 lines 9cdbf8aa68c0
- 20d ago Changed · -56 lines 36d395d07c3f
- 21d ago Changed · +58 lines scan B → A 2a8ab331dcd8
- 1mo ago First seen · 201 lines · 100 tokens per session scan B d8ed517b0004
kaggle is a skill published in the GitHub repository shepsci/kaggle-skill (105 stars, last pushed 8d ago), licensed MIT. It adds 100 tokens to every session and 2,668 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
agentic-data-science-competition
AI Agent-driven Kaggle competition workflow. Learn from real competition experience: score stabilization patterns, submission troubleshooting, kernel workflows, GPU task delegation, and the spec-driven development approach that achieved top leaderboard positions. Use when: working on any Kaggle competition, analyzing…
mixedbread-search
Build and query managed search indexes (Stores) using the Mixedbread Python and TypeScript SDKs. Use when creating knowledge bases, uploading documents, performing semantic or vector search, asking questions over documents, using agentic multi-step retrieval, combining store search with web results, filtering by…
mxbai-cli
Use the mxbai CLI to manage stores, upload files, search documents, ask questions, and sync directories from the terminal. Use when performing Mixedbread operations via command line, setting up CI/CD pipelines with store sync, or managing API keys.
add-ollama-tool
Add Ollama MCP server so the container agent can call local models and optionally manage the Ollama model library.
graphify
Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community…
sandbase
Access 2,000+ AI models and API tools through one MCP interface for inference, media generation, search, scraping, embeddings, social data, and structured retrieval. Use sandbasediscover before building custom integrations or declaring external data inaccessible; prefer an existing dedicated tool or API key when the…