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 instructions/vibevista/seojae/agents-mdgit clone --depth 1 https://github.com/VibeVista/seojaeWrote 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/instructions/vibevista/seojae/agents-md)<a href="https://agentmods.dev/instructions/vibevista/seojae/agents-md"><img src="https://agentmods.dev/badge/instructions/vibevista/seojae/agents-md.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 | $0.03811 | $0.03811 |
| Opus 5 | $0.01906 | $0.01906 |
| Sonnet 5 | $0.00762 | $0.00762 |
| Haiku 4.5 | $0.00381 | $0.00381 |
Grade A, and why
seojae AGENTS.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.
How it starts
The opening of the file, as written. The whole thing — 338 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Seojae (서재) — Wiki Schema
This file defines the rules and workflows for your LLM-powered knowledge wiki. Your LLM coding tool reads this file and follows these instructions to manage your wiki automatically. It is tool-agnostic — it works with Claude Code, Codex CLI, Gemini CLI, or any LLM coding tool that reads markdown instructions.
schema_version: "1.0"
# Wiki Configuration
wiki_language: en # Default language for meta files (index.md, log.md)
# Options: en, ko, ja, zh, etc.
# Page content follows source language rules below
Project Overview
Seojae is a pattern-based personal knowledge wiki with a 3-tier architecture:
- Raw sources (
raw/) — Immutable originals. Only the user adds files; the LLM reads only. - Wiki (
wiki/) — LLM-generated/maintained markdown pages: summaries, entities, concepts, synthesis. - Schema (
WIKI_SCHEMA.md) — This file. Defines wiki rules and workflows.
Prerequisites
- Python 3.9+ with pip
- Internet access on first run (downloads ~470MB embedding model)
- An LLM coding tool: Claude Code, Codex CLI, Gemini CLI, or similar
If you cannot download the model immediately, you can skip the search index setup and build it later with the Reindex workflow.
Setup
When a user asks to initialize this wiki, perform these steps:
1. Update your tool's rule file
The repo ships starter stubs. After initialization, update the file for your tool with environment-specific settings.
Claude Code (CLAUDE.md):
@WIKI_SCHEMA.md
@extensions/search-chromadb.md
@extensions/obsidian.md
# Environment
- Python: use `venv/bin/python` prefix or `source venv/bin/activate`
- All tools/ scripts require the venv to be active
Codex CLI (AGENTS.md):
(Full WIKI_SCHEMA.md content is already inlined)
(Append active extension contents below)
# Environment
- Python: always use `venv/bin/python` prefix (venv activation
does not persist between commands in Codex)
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 · 338 lines · 3,811 tokens per session scan A 4d92e57d39a6
seojae AGENTS.md is an instructions file published in the GitHub repository VibeVista/seojae (1 stars, last pushed 1mo ago), licensed MIT. It adds 3,811 tokens to every session, about $0.0191 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.
Other instructions, from other repositories
markdown-agent-vault-ru AGENTS.md
Instructions for dzhokhov/markdown-agent-vault-ru, covering agents.md — правила агента для файлового хранилища, главный принцип, карта папок, загрузка контекста and недосказанные запросы.
obsidian-mind CLAUDE.md
Claude Code instructions for breferrari/obsidian-mind, covering obsidian mind, skills & capabilities, custom slash commands, vault structure and obsidian cli.
llm-wiki-agent AGENTS.md
AGENTS.md instructions for SamurAIGPT/llm-wiki-agent, covering llm wiki agent — schema & workflow instructions, how to use, directory layout, page format and ingest workflow.
llm-wiki-agent GEMINI.md
Gemini CLI instructions for SamurAIGPT/llm-wiki-agent, covering llm wiki agent — schema & workflow instructions, how to use, directory layout, page format and ingest workflow.
obsidian-mind AGENTS.md
AGENTS.md instructions for breferrari/obsidian-mind, covering obsidian mind, hooks, commands, memory and reaching this vault from another repo.
superbrain CLAUDE.md
Instructions for m3talux/superbrain, covering superbrain — repository rules, non-negotiables, public-facing content, versioning and workflow.