What is ai-content-kb CLAUDE.md?

Operating rules for an AI-assisted personal knowledge base. They define folders for original notes, outside sources, finished work, human-readable reference pages, and rebuildable indexes, while requiring important claims to retain their source paths.

Use them when adding research or notes, creating wiki pages, recording translations, preserving history, or preparing content for publication.

They make it possible to distinguish personal ideas from external information and trace knowledge-base claims back to their origins.

How mrbear1024/ai-content-kb configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to mrbear1024/ai-content-kb. 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/mrbear1024/ai-content-kb/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/mrbear1024/ai-content-kb

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/mrbear1024/ai-content-kb/claude-md/github.svg)](https://agentmods.dev/instructions/mrbear1024/ai-content-kb/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/mrbear1024/ai-content-kb/claude-md"><img src="https://agentmods.dev/badge/instructions/mrbear1024/ai-content-kb/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/mrbear1024/ai-content-kb/claude-md"><img src="https://agentmods.dev/badge/instructions/mrbear1024/ai-content-kb/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 920 This file is loaded in full into every session.

When invoked 920 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.

Model	Per session	Once invoked
Fable 5.1	$0.00920	$0.00920
Opus 5.5	$0.00368	$0.00368
Sonnet 5.5	$0.00184	$0.00184
Haiku 4.5	$0.00092	$0.00092

Measured 2mo ago against content hash a3bba4f8f6a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ai-content-kb 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 · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Knowledge Base Operating Rules

This file contains detailed instructions for AI agents working in the vault. AGENTS.md contains the shorter portable rule set. Follow both files together with KNOWLEDGE_BASE_GUIDE.md.

If this is a new session, read START_HERE.md first.

Repository Roles

raw/ stores original writing, spoken notes, judgments, research conclusions, and owned drafts.
sources/ stores external web clips, papers, books, reports, and media transcripts.
products/ stores reviewed articles, courses, scripts, and other published or delivered work.
wiki/ stores human-readable concepts, entities, maps, and source summaries.
.kb/ stores rebuildable machine indexes, relationship data, staging output, reports, and logs.

Provenance

Treat raw/, sources/, and products/ as authoritative for their respective roles.
Treat wiki/ as a navigation and synthesis layer.
Every important wiki claim must identify a repository-relative source path.
Keep personal judgment distinguishable from external claims.
Record translations and adaptations with derived_from edges.

Safe Editing

Preserve historical raw notes. Prefer a dated correction or follow-up note over silently rewriting history.
Preserve external source captures unless the user explicitly requests cleanup.
Preserve published product bodies and their existing build workflow.
Never add vault-specific syntax to many product files without explicit approval.
Never treat generated summaries, drafts, or graph candidates as reviewed knowledge.
Never store secrets, API keys, cookies, private URLs, personal absolute paths, or binary media.

AI Output Lifecycle

generate -> .kb/staging -> human review -> promote or discard

Use these destinations:

.kb/staging/drafts/ for unreviewed prose;
.kb/staging/course-drafts/ for course control-file drafts;
.kb/staging/wiki/ for candidate concept, entity, map, and source-note pages;
.kb/staging/links/ for candidate graph sidecars;
raw/drafts/ for drafts the owner has chosen to develop;
wiki/ for reviewed knowledge pages;
.kb/links/ for reviewed relationship data;
products/ for reviewed output ready for publication or maintenance.

Read the full file on GitHub · 101 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.

2mo ago First seen · 101 lines · 920 tokens per session scan A a3bba4f8f6a4

Subscribe to this mod's changes

ai-content-kb CLAUDE.md is an instructions file published in the GitHub repository mrbear1024/ai-content-kb (120 stars, last pushed 3mo ago), licensed MIT. It adds 920 tokens to every session, about $0.0037 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.

Documents Writing and docs

ai-content-kb CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ai-content-kb CLAUDE.mdmrbear1024/ai-content-kb	Instructions file	120	3mo ago	MIT	A	920	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	3d ago	MIT	A	4,313	Codex, OpenCode

ai-content-kb: Instructions file for Claude Code