td-skills: Instructions file for Claude Code

CLAUDE.md

td-skills CLAUDE.md is an instructions file for Claude Code from treasure-data/td-skills. It costs 1,901 tokens per session, scanned A, original, Apache-2.0.

Project instructions for Treasure Data’s `td-skills` repository, including its purpose, architecture, and structure for skills.

In plain words
What is it for?
Creating, editing, and organizing skills in the `td-skills` repository.
Why use it?
They help an agent understand how the repository organizes and defines its skills.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: mentions .claude-plugin; mentions CLAUDE.md; mentions Claude Code.

This is treasure-data/td-skills's own configuration. It tells Claude Code how to work on td-skills 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 td-skills configures →

Reuse

Borrowing it

Nothing to install: this file belongs to treasure-data/td-skills. 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/treasure-data/td-skills/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/treasure-data/td-skills

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 td-skills CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/treasure-data/td-skills/claude-md/github.svg)](https://agentmods.dev/instructions/treasure-data/td-skills/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/treasure-data/td-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/treasure-data/td-skills/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 td-skills CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/treasure-data/td-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/treasure-data/td-skills/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,901 This file is loaded in full into every session.
When invoked 1,901 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 $0.01901 $0.01901
Opus 5.5 $0.00760 $0.00760
Sonnet 5.5 $0.00380 $0.00380
Haiku 4.5 $0.00190 $0.00190

Measured 2mo ago against content hash 5ada0011df65, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

td-skills 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 2mo 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 · 239 lines

How it starts

The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Repository Purpose

This is a Claude Code skills marketplace for Treasure Data internal tools. It contains skill definitions that teach Claude how to work with TD-specific technologies: Trino SQL, Hive SQL, and digdag workflows.

Architecture

Skill Structure

Each skill is a directory containing a SKILL.md file with:

  • YAML frontmatter: name and description fields that define when Claude should use the skill
  • Markdown content: Detailed instructions, examples, and best practices that Claude follows

Organization

.claude-plugin/marketplace.json  # Plugin registry defining skill collections
sql-skills/
  ├── trino/SKILL.md            # Trino query expertise
  └── hive/SKILL.md             # Hive query expertise
workflow-skills/
  ├── digdag/SKILL.md           # Workflow authoring (.dig files)
  │   └── references/           # Operator, pattern, runtime, scheduling references
  └── dbt/SKILL.md              # dbt with TD Trino
template-skill/SKILL.md         # Template for new skills

Plugin Collections

The marketplace.json defines three plugin collections:

  1. sql-skills: Trino and Hive query assistance
  2. workflow-skills: Digdag workflow creation and management
  3. template-skill: Template for creating new TD skills

Creating New Skills

When adding a new skill:

  1. Choose the correct category: Place SQL-related skills under sql-skills/, workflow-related skills under workflow-skills/, or create a new category if needed

  2. Create directory and SKILL.md:

    mkdir sql-skills/your-skill-name
    # Copy structure from template-skill/SKILL.md
    
  3. Write YAML frontmatter:

    • name: lowercase-with-hyphens, unique identifier
    • description: Clear explanation of what the skill does and when Claude should use it
  4. Include TD-specific patterns:

    • Use TD table naming: database_name.table_name
    • Include TD functions: TD_INTERVAL, TD_TIME_RANGE, TD_SCHEDULED_TIME
    • Use JST timezone for Japan data, UTC for others
    • Provide complete, working examples with realistic TD data patterns

Read the full file on GitHub · 239 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. 2mo ago First seen · 239 lines · 1,901 tokens per session scan A 5ada0011df65

Subscribe to this mod's changes

td-skills CLAUDE.md is an instructions file published in the GitHub repository treasure-data/td-skills (22 stars, last pushed 5d ago), licensed Apache-2.0. It adds 1,901 tokens to every session, about $0.0076 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.

Related

td-skills CLAUDE.md compared with instructions from other repositories

td-skills CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
td-skills CLAUDE.mdtreasure-data/td-skillsInstructions file225d agoApache-2.0A1,901Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,649GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot