What is llm-wiki-monorepo AGENTS.md?

Repository instructions for llm-wiki-monorepo, a codebase that turns source documents into a persistent, cross-linked Markdown knowledge base. A monorepo is one repository containing several related components, such as its agent skill, MCP server, and graph engine.

Use them when modifying the wiki, agent workflows, MCP tools, graph analysis, or build and test setup in this monorepo.

They explain the repository's package map, shared file-based state, architecture, and build commands so changes fit the whole system.

How JeanBaissari/llm-wiki-monorepo configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to JeanBaissari/llm-wiki-monorepo. 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/JeanBaissari/llm-wiki-monorepo/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/JeanBaissari/llm-wiki-monorepo

Made for: Codex, OpenCode.

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/jeanbaissari/llm-wiki-monorepo/agents-md/github.svg)](https://agentmods.dev/instructions/jeanbaissari/llm-wiki-monorepo/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/jeanbaissari/llm-wiki-monorepo/agents-md"><img src="https://agentmods.dev/badge/instructions/jeanbaissari/llm-wiki-monorepo/agents-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/jeanbaissari/llm-wiki-monorepo/agents-md"><img src="https://agentmods.dev/badge/instructions/jeanbaissari/llm-wiki-monorepo/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 4,500 This file is loaded in full into every session.

When invoked 4,500 The same file — it is already loaded in full.

Security scan C 1 finding. 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	$0.04500	$0.04500
Opus 5.5	$0.01800	$0.01800
Sonnet 5.5	$0.00900	$0.00900
Haiku 4.5	$0.00450	$0.00450

Measured 1mo ago against content hash 3bb3063bd766, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

llm-wiki-monorepo AGENTS.md scanned grade C with 1 finding 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 1mo 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf /tmp/test-wiki

AGENTS.md · 299 lines

How it starts

The opening of the file, as written. The whole thing — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — LLM Wiki Monorepo

Read this first. It tells you what this repo is, how it's organized, and how to work on it.

What this repo is

A complete knowledge base operating system. It takes raw source documents and AI agents produce and maintain a persistent, cross-linked Markdown wiki. Knowledge compounds over time.

One repo. Any agent. Any machine. git clone and you have everything.

Architecture

                    wiki/ directory (markdown files)
                              │
        ┌─────────────────────┼─────────────────────┐
        ▼                     ▼                     ▼
   Agent Skill          MCP Server           Graph Engine
   (Python + MD)        (TypeScript)         (TypeScript)
   in-conversation      programmatic         relevance model
    workflows            15 tools via stdio    Louvain communities
                                             graph insights

The wiki directory is the shared state. Every component reads/writes the same markdown files. No database. No API lock-in. Just files.

Package Map

Dir	Language	Tier	What it does	When to touch it
`skill/`	Python + MD	adapter	Agent skill: SKILL.md + 26 scripts + 12 references	Agent operations, scripts, docs
`mcp-server/`	TypeScript	programmatic-access	MCP server: 15 tools via stdio	Programmatic wiki access
`graph-engine/`	TypeScript	analysis	Knowledge graph: build, relevance, Louvain, insights	Graph analysis, community detection
`src/llm_wiki/templates/`	MD + JSON	core	20 domain templates for scaffold.py (single canonical tree)	Adding/modifying project templates
`web-viewer/`	TypeScript	optional	Local preview server: mermaid, KaTeX, feedback	UI changes
`extension/`	JavaScript	optional	Chrome web clipper	Browser clipping
`audit-shared/`	TypeScript	core	Audit file format library	Audit schema changes
`plugins/obsidian-audit/`	TypeScript	optional	Obsidian plugin	Vault integration
`src/llm_wiki/`	Python	core	CLI, version, core Python library	CLI operations, version bumps
`packages/shared-types/`	TypeScript	core	Shared TypeScript types and schemas	Schema changes, cross-package types

Read the full file on GitHub · 299 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.

1mo ago Changed · -5 lines · -589 tokens per session 3bb3063bd766
2mo ago First seen · 304 lines · 5,089 tokens per session scan C 656df2acd093

Subscribe to this mod's changes

llm-wiki-monorepo AGENTS.md is an instructions file published in the GitHub repository JeanBaissari/llm-wiki-monorepo (3 stars, last pushed 1mo ago), licensed MIT. It adds 4,500 tokens to every session, about $0.0180 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Documents Writing and docs ai-agents community-detection concurrency fts5 hermes-agent knowledge-base

llm-wiki-monorepo AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
llm-wiki-monorepo AGENTS.mdJeanBaissari/llm-wiki-monorepo	Instructions file	3	1mo ago	MIT	C	4,500	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

llm-wiki-monorepo: Instructions file for Codex