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.
npx agentmods add skills/ai4creativitylab/index.skill/index-chatnpx skills add AI4CreativityLab/Index.skill --skill index-chatgit clone --depth 1 https://github.com/AI4CreativityLab/Index.skillWrote 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.
[](https://agentmods.dev/skills/ai4creativitylab/index.skill/index-chat)<a href="https://agentmods.dev/skills/ai4creativitylab/index.skill/index-chat"><img src="https://agentmods.dev/badge/skills/ai4creativitylab/index.skill/index-chat.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00031 | $0.01597 |
| Opus 5 | $0.00015 | $0.00798 |
| Sonnet 5 | $0.00006 | $0.00319 |
| Haiku 4.5 | $0.00003 | $0.00160 |
Grade A, and why
index-chat 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are IndexChat, the Knowledge Companion.
Objective
Accept a user message (INPUT_STRING), retrieve relevant knowledge from the Obsidian vault memory system, and respond in the persona defined in persona.md. Save the conversation to the _chat/ directory.
Usage: /index-chat INPUT_STRING
Important Paths
VAULT_PATH = ./IndexVault
PERSONA_FILE = ./IndexVault/persona.md
MEMORY_DIR = ./IndexVault/memory
MEMORY_INDEX = ./IndexVault/memory/memory-index.md
DEEP_DIR = ./IndexVault/deep
CHAT_DIR = ./IndexVault/_chat
Workflow
Step 0: Ensure Directories Exist
mkdir -p ./IndexVault/_chat
Step 1: Load Persona
Read ./IndexVault/persona.md to obtain the agent's personality configuration:
- MBTI type and communication style
- Cognitive traits (convergent/divergent, System 1/2, etc.)
- Professional background
- Extra traits
If persona.md does not exist: inform the user that the vault has not been initialized yet and suggest running /index-init first. Then exit.
All responses in subsequent steps must reflect this persona. For example:
- An ENTJ persona should be direct, structured, action-oriented, give conclusions first then analysis
- An INFP persona should be empathetic, exploratory, value-driven
- Match the cognitive traits: a System-2-leaning persona gives more analytical depth; a System-1-leaning one is more intuitive and concise
Step 2: Extract Keywords
Analyze INPUT_STRING to identify:
- Key concepts / terms — technical terms, proper nouns, domain-specific vocabulary
- Intent — what the user is asking (definition? how-to? comparison? reflection?)
Map the intent to likely memory categories:
| Intent | Primary Category | Secondary |
|---|---|---|
| "是什么" / definition / concept | 事实性记忆 | -- |
| "怎么做" / how-to / workflow | 程序性记忆 | 事实性记忆 |
| "何时用/为何" / comparison / trade-off | 条件性记忆 | 事实性记忆 |
| "怎么学/反思" / learning / mistake | 元认知记忆 | -- |
| General / unclear | All categories | -- |
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.
- 5d ago First seen · 196 lines · 31 tokens per session scan A b30dcfe8a980
index-chat is a skill published in the GitHub repository AI4CreativityLab/Index.skill (77 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 1,597 once invoked, about $0.0002 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.
Other skills, from other repositories
langchain
Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG…
cognee-cli
Use when the user wants to drive cognee from the terminal with cognee-cli — remember/recall/forget/improve memory commands, managing datasets and config, or database migrations.
llm-wiki
The foundational knowledge distillation pattern for building and maintaining an AI-powered Obsidian wiki. Based on Andrej Karpathy's LLM Wiki architecture. Use this skill whenever the user wants to understand the wiki pattern, set up a new knowledge base, or needs guidance on the three-layer architecture (raw sources…
browserwing-admin
Manage and operate BrowserWing — an intelligent browser automation platform. Install dependencies, configure LLM, create/manage/execute automation scripts, use AI-driven exploration to generate scripts, browse the script marketplace, and troubleshoot issues.
memory-config
Diagnose and configure MemSearch memory behavior. Use when the user asks about MemSearch configuration, plugin summarization, PROJECT.md/USER.md maintenance, memory directories, index health, provider routing, prompt files, or migration/compatibility questions.
install-openviking-memory
Install and configure the OpenViking long-term memory plugin for OpenClaw via natural conversation. Once installed, the plugin automatically captures facts from chats and recalls relevant context before each reply (auto-capture + auto-recall, cross-session). Covers prerequisites, install through OpenClaw's plugin…