ddb-mcp: Instructions file for Claude Code

CLAUDE.md

ddb-mcp CLAUDE.md is an instructions file for Claude Code from iamjameslennon/ddb-mcp. It costs 5,791 tokens per session, scanned A, original, from a forked repository, MIT.

A CLAUDE.md instruction file for the ddb-mcp code repository. It documents the project structure, common commands, browser and browserless execution paths, and a character-data parser refactor.

In plain words
What is it for?
Use it when working on ddb-mcp to find development commands, understand its architecture, locate character parser modules, and preserve its snapshot regression checks.
Why use it?
It gives coding agents repository-specific guidance, including how to build, test, lint, type-check, and safely change parsing behaviour.

Instructions file for Claude Code

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

This is iamjameslennon/ddb-mcp's own configuration. It tells Claude Code how to work on ddb-mcp 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 ddb-mcp configures →

Reuse

Borrowing it

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

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 ddb-mcp CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/iamjameslennon/ddb-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/iamjameslennon/ddb-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5,791 This file is loaded in full into every session.
When invoked 5,791 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 fork From a forked repository.
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 $0.05791 $0.05791
Opus 5.5 $0.02316 $0.02316
Sonnet 5.5 $0.01158 $0.01158
Haiku 4.5 $0.00579 $0.00579

Measured 2d ago against content hash a56795a1dcec, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ddb-mcp 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 2d 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 · 176 lines

How it starts

The opening of the file, as written. The whole thing — 176 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.

It holds the commands, invariants and gotchas. The full per-module, per-tool and historical detail lives in docs/claude/. Read the relevant file there before changing that area, and update it when behaviour changes:

File Read it before touching
docs/claude/architecture.md Session lifecycle, execution paths, the full key-modules table (Open5e, edition, game config, library join, …)
docs/claude/caching.md Any cache, in-flight dedupe, failure memo, deadline or epoch guard
docs/claude/tool-notes.md A tool's output, params or edition selection; parseCharacterData behaviour (senses, languages, spells, limited use, …)
docs/claude/release-and-ops.md Releasing, LobeHub, CI workflows, the Dockerfile, package pins
docs/claude/history.md Owner decisions and rulings, every work item and carry-over (a)–(az), security finding F-2026-10-20

parseCharacterData is split into per-domain modules under src/tools/character/. docs/character-refactor.md has the module boundaries and the live-character snapshot regression flow. Keep that flow when changing parse behaviour. The rules-edition spec is docs/superpowers/specs/2026-10-16-rules-edition-design.md. Where it and these notes differ, the spec wins.

Commands

npm ci               # Install dependencies (prefer ci over install — respects the lockfile)
npm run dev          # Run in development mode (no build step, uses tsx)
npm run build        # Compile TypeScript to dist/
npm run build:watch  # Watch mode
npm run lint         # ESLint on the whole repo (src/, tests/, scripts/, root configs)
npm run typecheck    # Type-check src/, tests/ and scripts/release-history.mjs without emitting
npm test             # Run all tests (vitest)
npm run release      # Bump version, generate release notes, publish (patch|minor|major)
                     #   accepts --dry-run (mutate files only, no commit/tag/push)
                     #   and --skip-verify (skip the `npm ci && npm test` gate)
npm run lobehub:manifest  # Regenerate lhm.plugin.json (needs dist/ — run build first)
npx vitest run tests/character-parser.test.ts  # Run a single test file

Read the full file on GitHub · 176 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. 2d ago Changed · +15 lines · +890 tokens per session a56795a1dcec
  2. 4d ago Changed · +2 lines · +205 tokens per session 85758c682700
  3. 5d ago Changed · +2 lines · +291 tokens per session d63330c5eefd
  4. 6d ago Changed · +77 tokens per session 01897fb322e5
  5. 9d ago Changed · -106 lines · -29,705 tokens per session 6efb543723ea
  6. 10d ago Changed · +3,026 tokens per session be2b95091416
  7. 11d ago Changed · +46 lines · +18,475 tokens per session 4da73d029ddf
  8. 27d ago Changed · -13 lines · +1,614 tokens per session a5f68c2de95c
  9. 28d ago Changed · +25 lines · +2,311 tokens per session 1240a6bb27ec
  10. 1mo ago First seen · 205 lines · 8,607 tokens per session scan A 1133ee7b8fb1

Subscribe to this mod's changes

ddb-mcp CLAUDE.md is an instructions file published in the GitHub repository iamjameslennon/ddb-mcp (3 stars, last pushed 2d ago), licensed MIT. It adds 5,791 tokens to every session, about $0.0232 per session on Opus 5.5. A static security scan graded it A with 0 findings. It comes from a forked repository.

Related

ddb-mcp CLAUDE.md compared with instructions from other repositories

ddb-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ddb-mcp CLAUDE.mdiamjameslennon/ddb-mcpInstructions file32d agoMITA5,791Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,086GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file282k3d agoMITA4,335Codex, OpenCode