What is Index.skill CLAUDE.md?

Project instructions for Index.skill, a knowledge-management system that turns text, links, files, or folders into structured Obsidian notes. Obsidian is an app for organizing notes in a local, linked vault.

Use it when working on note creation, knowledge retrieval, persona-based chat, setup, or updates in this repository.

It gives an AI assistant the project overview, skill responsibilities, important paths, and memory-system rules.

Index.skill CLAUDE.md — Instructions file for coding agents by AI4CreativityLab: Project instructions for Index.skill, a knowledge-managemen

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/ai4creativitylab/index.skill/claude-md

Clone the repo

git clone --depth 1 https://github.com/AI4CreativityLab/Index.skill

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/ai4creativitylab/index.skill/claude-md.svg)](https://agentmods.dev/instructions/ai4creativitylab/index.skill/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/ai4creativitylab/index.skill/claude-md"><img src="https://agentmods.dev/badge/instructions/ai4creativitylab/index.skill/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 2,933 This file is loaded in full into every session.

When invoked 2,933 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.

Model	Per session	Once invoked
Fable 5	$0.02933	$0.02933
Opus 5	$0.01466	$0.01466
Sonnet 5	$0.00587	$0.00587
Haiku 4.5	$0.00293	$0.00293

Measured 3d ago against content hash 3779b6ae0e9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Index.skill 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 3d 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 · 209 lines

How it starts

The opening of the file, as written. The whole thing — 209 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.

Project Overview

茵蒂克丝.skill（LLM Wiki）is a knowledge management system built as Claude Code skills. It captures arbitrary input (text, URLs, files, folders), auto-classifies it into 6 types, and produces structured Obsidian notes with extracted images. It also provides persona-driven chat with memory-augmented retrieval.

Skills

Four complementary skills in skills/:

index-init (/index-init): First-run setup. Creates the Obsidian vault directory structure, copies templates from skills/index-init/resources/ to the vault, and generates persona.md via interactive MBTI questionnaire.
index-note (/index-note INPUT): Core skill. Classifies input → downloads content if needed → extracts images → fills type-specific template → writes note to _new/.
index-chat (/index-chat INPUT): Chat skill. Loads persona from persona.md → extracts keywords from user input → retrieves relevant knowledge from memory/ via layered navigation → responds in persona style with references → saves conversation to _chat/.
index-update (/index-update): Knowledge organizer. Scans _new/ for notes marked "已读" → extracts knowledge items → classifies into 4-type hierarchical memory system (memory/) → archives note to deep/. Also processes _chat/ logs: applies persona updates to persona.md, extracts user-provided knowledge, and archives chat files to deep/. The read marker is a literal checkbox at the bottom of every note: - [x] <big><big>已读</big></big> triggers archiving; - [ ] <big><big>已读</big></big> is skipped.

Each skill is defined by a SKILL.md file with frontmatter:

---
name: index-note
description: ...
allowed-tools: Read, Write, Bash, WebFetch, Glob, Grep, WebSearch
---

Key Paths

All paths are relative to the project root:

IndexVault/              Obsidian vault root
IndexVault/_new/         Generated notes output (YYYY-MM-DD_TYPE_NNN.md)
IndexVault/deep/         Archive for read notes (moved from _new/ after reading)
IndexVault/memory/       Hierarchical knowledge base (see Memory System below)
IndexVault/_template/    6 note templates (idea/project/book/paper/webinfo/webnews)
IndexVault/_images/      Extracted images, organized per-note ({note_id}/{note_id}_{nn}.ext)
IndexVault/_downloads/   Downloaded source material
IndexVault/_chat/        Chat logs (YYYY-MM-DD_Chat.md, archived to deep/ by index-update)
IndexVault/persona.md    Agent personality config (created by index-init, updated by index-update from chat logs)

Read the full file on GitHub · 209 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.

3d ago First seen · 209 lines · 2,933 tokens per session scan A 3779b6ae0e9f

Subscribe to this mod's changes

Index.skill CLAUDE.md is an instructions file published in the GitHub repository AI4CreativityLab/Index.skill (77 stars, last pushed 2mo ago), licensed MIT. It adds 2,933 tokens to every session, about $0.0147 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 2026-08-30.

Documents Memory and context

Index.skill CLAUDE.md

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

CLAUDE.md

Project Overview

Skills

Key Paths

What this file has done since we first saw it

Other instructions, from other repositories

mcp-pandoc AGENTS.md

gpt-rag-mcp documentation.instructions.md

agentic-resume-builder CLAUDE.md

fcp-sheets CLAUDE.md

rodya-caijing-studio AGENTS.md

paperless-ngx-mcp-server CLAUDE.md