lore-db CLAUDE.md

lore-db CLAUDE.md is an instructions file for coding agents from andreehultgren/lore-db. It costs 1,704 tokens per session, scanned A, original, MIT.

Project instructions for Lore DB, a knowledge base that stores shared information about a software project.

In plain words
What is it for?
Use them when developing, debugging, answering project questions, or designing features that depend on existing project context.
Why use it?
They require the assistant to search the knowledge base first, helping prevent guesses, repeated work, and conflicts with recorded decisions.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/andreehultgren/lore-db/claude-md
Clone the repo
git clone --depth 1 https://github.com/andreehultgren/lore-db

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 lore-db CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/andreehultgren/lore-db/claude-md.svg)](https://agentmods.dev/instructions/andreehultgren/lore-db/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/andreehultgren/lore-db/claude-md"><img src="https://agentmods.dev/badge/instructions/andreehultgren/lore-db/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,704 This file is loaded in full into every session.
When invoked 1,704 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01704 $0.01704
Opus 5 $0.00852 $0.00852
Sonnet 5 $0.00341 $0.00341
Haiku 4.5 $0.00170 $0.00170

Measured 4d ago against content hash 09f45ede8c9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

lore-db 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 4d 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 · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Instructions for Lore DB

General Instructions

Any new feature starts with unit tests. These tests must be verified before work starts. Then we iterate against the tests to ensure that we are building a robust product.

Knowledge Base Protocol (The "Brain")

The knowledge-base MCP is our Living Source of Truth and the primary source for all project knowledge. You are its caretaker.

CRITICAL RULE: Search the knowledge base FIRST, before every task. Do not rely on your training data, memory, or assumptions about this project. The KB contains project-specific decisions, patterns, conventions, and context that override general knowledge. If you skip this step, you risk contradicting established decisions or duplicating solved problems.

When to Search (Always)

You MUST search the knowledge base at the start of every task, including but not limited to:

  • Before writing or modifying code — search for relevant architecture decisions, patterns, or conventions
  • Before answering questions about the project — the KB may already have the answer
  • Before debugging — search for known issues, past fixes, or related context
  • Before designing a feature — search for prior design decisions or constraints
  • Before refactoring — search for documented reasons behind the current structure
  • When encountering unfamiliar code — search for explanations or context

Run multiple searches with different queries if your first search doesn't cover the full scope of the task. Cast a wide net — it's better to search too much than too little.

Available MCP Tools

Tool When to use
search_documents(query, limit) Find relevant documents by meaning
get_document(document_id) Fetch full content of a specific document
create_document(title, content) Add a new Brief
update_document(document_id, title, content) Update an existing Brief
delete_document(document_id) Remove a stale Brief
verify_document(document_id) Confirm a document is still accurate (bumps freshness)
get_stale_documents(days_threshold) Find documents that may be outdated
reindex_documents() Re-embed all documents after embedder changes

Read the full file on GitHub · 125 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. 4d ago First seen · 125 lines · 1,704 tokens per session scan A 09f45ede8c9f

Subscribe to this mod's changes

lore-db CLAUDE.md is an instructions file published in the GitHub repository andreehultgren/lore-db (0 stars, last pushed 5mo ago), licensed MIT. It adds 1,704 tokens to every session, about $0.0085 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.