pkmn_yellow_legacy_dbt: Instructions file for Claude Code

CLAUDE.md

pkmn_yellow_legacy_dbt CLAUDE.md is an instructions file for Claude Code from wjsutton/pkmn_yellow_legacy_dbt. It costs 1,241 tokens per session, scanned A, original, MIT.

Project instructions for using dbt, a tool that builds and tests data models, to find the best six-Pokémon teams for each stage of Pokémon Yellow Legacy. They define the required results, model structure, and testing rules.

In plain words
What is it for?
Running the analysis for different Pikachu, legendary-Pokémon, and rival choices; validating teams, matchups, TMs, rows, tests, and the dbt model folders.
Why use it?
They give agents clear checks for whether the game-analysis data is correct and explain what to change when those checks fail.

Instructions file for Claude Code

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

This is wjsutton/pkmn_yellow_legacy_dbt's own configuration. It tells Claude Code how to work on pkmn_yellow_legacy_dbt 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 pkmn_yellow_legacy_dbt configures →

Reuse

Borrowing it

Nothing to install: this file belongs to wjsutton/pkmn_yellow_legacy_dbt. 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/wjsutton/pkmn_yellow_legacy_dbt/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/wjsutton/pkmn_yellow_legacy_dbt

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 pkmn_yellow_legacy_dbt CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/wjsutton/pkmn_yellow_legacy_dbt/claude-md"><img src="https://agentmods.dev/badge/instructions/wjsutton/pkmn_yellow_legacy_dbt/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,241 This file is loaded in full into every session.
When invoked 1,241 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 $0.01241 $0.01241
Opus 5 $0.00620 $0.00620
Sonnet 5 $0.00248 $0.00248
Haiku 4.5 $0.00124 $0.00124

Measured 9d ago against content hash 1a978e1e6cd8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

pkmn_yellow_legacy_dbt 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 · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Project Objective

Find the best 6-pokemon team for every gym leader and all preceding trainers in Pokemon Yellow Legacy (ROM hack). Teams reset at each gym leader -- after defeating Brock, the entire team can change for the Misty segment.

Runs support parameters:

  • Keep Pikachu: yes/no
  • Use Legendary Pokemon: yes/no
  • Rival Type: Jolteon, Vaporeon, or Flareon (each is a separate run)

Tasks

  • Use the dbt mcp server to verify the following success criteria
  • For any failures, modify the existing models in the dbt project use the dbt mcp server to support you
  • Iterate untill the success criteria is met

Success Criteria

  1. Nidoking should be a potential teammate at Misty's gym (Badge_2)
  2. Lt Surge (Badge_3) should have the fewest positive matchups for the player
  3. The Rival should always have one of: Eevee, Jolteon, Vaporeon, or Flareon
  4. All dbt models should produce rows
  5. Staging layer tests: only unique and not_null on primary keys
  6. Each team has a maximum of 6 pokemon; single-use TMs can only be assigned once per team (verified by dbt test)
  7. The intermediate layer should have no tests
  8. Only 5 folders in models/ (staging, intermediate, marts, dashboard, semantic) with no files outside of folders
  9. Fewer files in the final layer (marts) than the intermediate layer

Tools & Environment

  • Database: DuckDB
  • Framework: dbt (data build tool) with dbt-duckdb adapter
  • Virtual Environment: .venv/Scripts/ (Python, dbt, duckdb executables)
  • MCP Server: dbt MCP server available for column lineage queries
  • Macros: Gen 1 battle mechanics (calculate_damage_rby, calculate_hp_rby, calculate_stat_rby, calculate_battle_outcome), run variant generation, TM efficiency

Required Skills

When working on this dbt project, use these skills from the dbt plugin:

  • dbt:using-dbt-for-analytics-engineering -- for building/modifying models, debugging errors, exploring data, writing tests
  • dbt:adding-dbt-unit-test -- when adding unit tests for dbt models
  • dbt:fetching-dbt-docs -- when looking up dbt features or syntax

Read the full file on GitHub · 76 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 · 76 lines · 1,241 tokens per session scan A 1a978e1e6cd8

Subscribe to this mod's changes

pkmn_yellow_legacy_dbt CLAUDE.md is an instructions file published in the GitHub repository wjsutton/pkmn_yellow_legacy_dbt (5 stars, last pushed 2mo ago), licensed MIT. It adds 1,241 tokens to every session, about $0.0062 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