last-ds-mile: Instructions file for Claude Code

CLAUDE.md

last-ds-mile CLAUDE.md is an instructions file for Claude Code from StamKavid/last-ds-mile. It costs 798 tokens per session, scanned A, original, MIT.

Project-specific instructions for the last-ds-mile plugin, which packages data-science methods as agent skills and commands. Data science uses data to build models and support conclusions.

In plain words
What is it for?
Use them when adding or changing data-science skills, commands, hooks, or tests in this plugin.
Why use it?
They set safeguards for reliable analysis, including consistent command wiring, limited hook behavior, and avoiding unsupported claims.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is StamKavid/last-ds-mile's own configuration. It tells Claude Code how to work on last-ds-mile itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything last-ds-mile configures →

Reuse

Borrowing it

Nothing to install: this file belongs to StamKavid/last-ds-mile. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/StamKavid/last-ds-mile/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/StamKavid/last-ds-mile

Made for: Claude Code.

Wrote 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.

agentmods badge for last-ds-mile CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/stamkavid/last-ds-mile/claude-md/github.svg)](https://agentmods.dev/instructions/stamkavid/last-ds-mile/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/stamkavid/last-ds-mile/claude-md"><img src="https://agentmods.dev/badge/instructions/stamkavid/last-ds-mile/claude-md/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.

agentmods 80×15 button for last-ds-mile CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/stamkavid/last-ds-mile/claude-md"><img src="https://agentmods.dev/badge/instructions/stamkavid/last-ds-mile/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 798 This file is loaded in full into every session.
When invoked 798 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00798 $0.00798
Opus 5 $0.00399 $0.00399
Sonnet 5 $0.00160 $0.00160
Haiku 4.5 $0.00080 $0.00080

Measured 9d ago against content hash 8d97dcd56346, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

last-ds-mile CLAUDE.md 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.

CLAUDE.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Instructions for Claude Code when working in this repository.

What this repo is

A Claude Code plugin that packages data-science lifecycle discipline as skills and slash commands (commands/ route to skills/, one SKILL.md per skill). The product is the Markdown itself — the guidance an agent follows when it runs /ds-frame, /ds-model, etc. in someone else's project. Precision and honesty in that guidance matters more than usual: a skill that's vague or wrong doesn't just read badly, it lets an agent ship a leaky model or an overreached causal claim in a real project.

Hard rules

  • Hooks (hooks/*.py) stay stdlib-only, zero network calls, fail-open (warn, never block). This is a load-bearing trust claim documented in AUDIT.md — if you touch a hook, update that file's table in the same change.
  • Don't invent scope. Skills here encode discipline someone already got burned by not having — see the CHANGELOG entries for the story behind most of them. A new skill needs a concrete failure mode it catches, not a hypothetical one.
  • Command ↔ skill wiring must stay consistenttests/test_plugin_structure.py checks frontmatter shape and that commands reference real skills. Run pytest before treating a commands/skills change as done.
  • The five hard-gate stages stay hard gates. ds-method splits them into two kinds and the distinction is load-bearing — don't collapse it. Discipline gates self-heal: /ds-model (baseline + validation strategy), /ds-report (subgroup performance, not just an aggregate) and /ds-handoff (pinned environment) produce the missing artifact inline rather than ending the turn telling the user to go make it. Safety gates stop: /ds-package won't call a model servable until training/serving parity passes, and /ds-deploy won't go to full traffic without monitoring, drift detection, and a rollback pointer. Don't soften either kind without discussing it explicitly — they're the whole point of the plugin.

Read the full file on GitHub · 62 lines

Changes

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.

  1. 9d ago First seen · 62 lines · 798 tokens per session scan A 8d97dcd56346

Subscribe to this mod's changes

last-ds-mile CLAUDE.md is an instructions file published in the GitHub repository StamKavid/last-ds-mile (3 stars, last pushed 1mo ago), licensed MIT. It adds 798 tokens to every session, about $0.0040 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens