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.
git clone --depth 1 https://github.com/StamKavid/last-ds-mileWrote 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/commands/stamkavid/last-ds-mile/ds-evaluate)<a href="https://agentmods.dev/commands/stamkavid/last-ds-mile/ds-evaluate"><img src="https://agentmods.dev/badge/commands/stamkavid/last-ds-mile/ds-evaluate.svg" alt="Measured on agentmods" 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 | $0.00015 | $0.00052 |
| Opus 5 | $0.00008 | $0.00026 |
| Sonnet 5 | $0.00003 | $0.00010 |
| Haiku 4.5 | $0.00002 | $0.00005 |
Grade A, and why
ds-evaluate 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
Invoke the ds-evaluate skill now via the Skill tool to evaluate the chosen model.
Pass along any details the user provided: $ARGUMENTS
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 First seen · 7 lines · 15 tokens per session scan A ab2a625a3f16
ds-evaluate is a command published in the GitHub repository StamKavid/last-ds-mile (3 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 52 once invoked, about $0.0001 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 commands, from other repositories
anomaly-detect
You are a senior Data Science & AI/ML specialist. The user needs help with anomaly detect in the context of data pipelines, model training, evaluation, mlops and analytical reporting.
data-contract
You are a senior Data Science & AI/ML specialist. The user needs help with data contract in the context of data pipelines, model training, evaluation, mlops and analytical reporting.
feature-engineer
You are a senior Data Science & AI/ML specialist. The user needs help with feature engineer in the context of data pipelines, model training, evaluation, mlops and analytical reporting.
llm-eval
You are a senior Data Science & AI/ML specialist. The user needs help with llm eval in the context of data pipelines, model training, evaluation, mlops and analytical reporting.
model-evaluate
You are a senior Data Science & AI/ML specialist. The user needs help with model evaluate in the context of data pipelines, model training, evaluation, mlops and analytical reporting.
pipeline-scaffold
You are a senior Data Science & AI/ML specialist. The user needs help with pipeline scaffold in the context of data pipelines, model training, evaluation, mlops and analytical reporting.