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 Kaggle/kaggle-skills --skill write-kaggle-benchmarksgit clone --depth 1 https://github.com/Kaggle/kaggle-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/kaggle/kaggle-skills/write-kaggle-benchmarks)<a href="https://agentmods.dev/skills/kaggle/kaggle-skills/write-kaggle-benchmarks"><img src="https://agentmods.dev/badge/skills/kaggle/kaggle-skills/write-kaggle-benchmarks/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/kaggle/kaggle-skills/write-kaggle-benchmarks"><img src="https://agentmods.dev/badge/skills/kaggle/kaggle-skills/write-kaggle-benchmarks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 12 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 35 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 107 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Excessive Agency · line 126 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- high Excessive Agency · line 129 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- high Excessive Agency · line 132 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- high Excessive Agency · line 174 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- high Excessive Agency · line 139 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- high Excessive Agency · line 147 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- high Excessive Agency · line 156 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- high Excessive Agency · line 181 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- high Excessive Agency · line 182 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- medium Agent Snooping · line 201 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00095 | $0.04001 |
| Opus 5 | $0.00048 | $0.02001 |
| Sonnet 5 | $0.00019 | $0.00800 |
| Haiku 4.5 | $0.00010 | $0.00400 |
Grade A, and why
write-kaggle-benchmarks 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 — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write Kaggle Benchmarks
Keywords
Kaggle benchmarks, write a benchmark, benchmark task, kbench, push task, run task.
Official Resources
- SDK source & API — https://github.com/Kaggle/kaggle-benchmarks
- SDK auto-generated docs — https://deepwiki.com/Kaggle/kaggle-benchmarks
- CLI docs — https://github.com/Kaggle/kaggle-cli/blob/main/docs/benchmarks.md
Command Hierarchy
kaggle benchmarks (alias: kaggle b)
├── auth — Fetch Model Proxy credentials
├── init — Fetch credentials + setup local dev environment
└── tasks (alias: t) — Manage benchmark tasks
├── push — Upload a task from a .py file
├── run — Run a task against model(s)
├── list — List your benchmark tasks
├── status — Show task details and per-model run status
├── download — Download completed run outputs (and optionally source notebooks)
├── log (logs) — Show execution logs for run(s) (streams live for RUNNING runs)
├── publish — Make a task public (publishes the backing notebook by default)
├── models — List available benchmark models
└── delete — Delete a task (not yet supported by server)
Setup
# Full setup: credentials + .env + example_task.py + kaggle_benchmarks_reference.md
kaggle b init -y
# Credentials only (refresh MODEL_PROXY_* in .env)
kaggle b auth -y
Custom paths: --env-file <FILE> and --example-file <FILE> for init.
Env vars written by init:
MODEL_PROXY_URLMODEL_PROXY_API_KEYMODEL_PROXY_EXPIRY_TIMELLM_DEFAULTLLM_DEFAULT_EVALLLMS_AVAILABLE
Core workflow: Init → Write → Validate → Push → Run → Status → Download
Pacing — check in at every stage
Do NOT chain the full pipeline. Treat each numbered step below as a checkpoint:
- State what you are about to do for the current step (one sentence, including the exact command you intend to run).
- Wait for the user's go-ahead before executing — including for steps that look "obvious" like
initorlist. - After the step completes, show the relevant output, then stop. Do not auto-advance to the next step.
- Ask the user how they want to proceed: continue to the next documented step, change parameters, or branch off.
What ships with it
1 file 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.
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 · 260 lines · 95 tokens per session scan A 1b760137cf4b
write-kaggle-benchmarks is a skill published in the GitHub repository Kaggle/kaggle-skills (64 stars, last pushed 25d ago), licensed Apache-2.0. It adds 95 tokens to every session and 4,001 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
coverage-tracker
Run a Google Alerts-style keyword coverage tracker. Uses news-search for recent keyword queries, lets the LLM dedupe and classify real features versus junk, stores decisions in SQLite, and alerts only on new real coverage.
prompt-set-qa
Gate a prompt universe for schema and provenance completeness, target or campaign contamination, evidence entailment, naturalness, one-concept clarity, architecture consistency, aided status, answer leakage, and semantic duplicates. Use after realistic prompt generation and before human panel selection.
realistic-prompt-generation
Generate natural, controlled prompt variants from a target-blind design brief and prompt architecture while preserving approved jobs, acts, journeys, constraints, roles, locales, proximity bands, and evidence language. Use after architecture design and before contamination or semantic QA.
ai-visibility-panel-design
Select QA-approved canonical intent cells into a versioned AI-visibility tracking panel with partitions, variants, lanes, surfaces, locales, repetitions, separate exposure and priority weights, randomization, uncertainty, refresh rules, and campaign controls. Use after prompt QA or when revising an existing panel.
smoke-test-ml-pipeline
Owns the smoke test contract for an ML experiment: a small, diagnostic-by-construction pytest that fits the experiment's learner on a portion of the real data/ source and predicts on a disjoint portion that deliberately carries no pre-history buffer. The assertion is structural — the number of predictions must equal…
eval-iterate
Iterates on a failing AI/LLM eval (an L2 suite, a golden-set / judge eval, or any eval gating a PR) until it is green AND confirmed, not just luckily passing once. Classifies the failure as a code bug, an eval-definition bug (stale golden item / criteria drift), judge-drift (silent grader version change), or flaky.…