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/jaronlu/llm-wiki-mcp/agents-mdgit clone --depth 1 https://github.com/jaronlu/llm-wiki-mcpWrote 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/jaronlu/llm-wiki-mcp/agents-md)<a href="https://agentmods.dev/instructions/jaronlu/llm-wiki-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/jaronlu/llm-wiki-mcp/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 5.1 | $0.00629 | $0.00629 |
| Opus 5 | $0.00315 | $0.00315 |
| Sonnet 5 | $0.00126 | $0.00126 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
llm-wiki-mcp 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 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
This repository contains a Python MCP server for maintaining local LLM wiki
projects. Runtime code lives in src/llm_wiki_mcp/; server.py registers MCP
tools, while focused modules such as raw.py, pages.py, sync.py,
candidates.py, and advanced.py implement tool behavior. Tests live in
tests/ and mirror the feature areas. Configuration examples live in config/.
CI configuration is in .github/workflows/ci.yml.
Architecture & Design Source
Use docs/wiki-mcp/README.md as the design entrypoint. It links to the personal wiki design docs when the local symlink target is available. This repo uses design-driven coding: for tool, permission, workflow, or data-shape changes, read the spec before editing code. If the spec is wrong or incomplete, update it first, then implement code and tests to match it.
Build, Test, and Development Commands
Use uv for this project.
uv sync --dev
uv run llm-wiki-mcp
uv run ruff check .
uv run pytest
uv sync --dev installs runtime and development dependencies. uv run llm-wiki-mcp starts the MCP server over stdio. ruff check runs linting.
pytest runs the full test suite.
Coding Style & Naming Conventions
Target Python 3.11+. Keep modules small and behavior-oriented. Prefer explicit
helper functions over broad utility layers. Use snake_case for functions,
modules, and test names; use PascalCase for dataclasses and exceptions. Keep
tool return values structured, JSON-serializable, and consistent with
responses.py. Do not add dependencies unless the standard library or existing
dependencies cannot reasonably solve the problem.
Testing Guidelines
Tests use pytest. Add focused tests for every tool helper and update
tests/test_server_tools.py when adding or changing public MCP tools. Name tests
as test_<behavior>. Prefer behavior assertions over implementation details.
Run uv run pytest and uv run ruff check . before committing.
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 · 66 lines · 629 tokens per session scan A 519043822725
llm-wiki-mcp AGENTS.md is an instructions file published in the GitHub repository jaronlu/llm-wiki-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 629 tokens to every session, about $0.0031 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
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.
GhidrAssistMCP CLAUDE.md
Claude Code instructions for symgraph/GhidrAssistMCP, covering claude.md, build and development commands, building the extension, set ghidrainstalldir environment variable first and build the extension.
kaas CLAUDE.md
Claude Code instructions for bybit-exchange/kaas, covering claude.md, behavioral guidelines, 1. think before coding, 2. simplicity first and 3. surgical changes.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
intervals-icu-mcp CLAUDE.md
Claude Code instructions for hhopke/intervals-icu-mcp, covering claude.md, project overview, development commands, architecture (quick reference) and tool categories.
Kompl AGENTS.md
AGENTS.md instructions for tuirk/Kompl, covering agents.md — kompl operator guide, what is kompl?, agent rules — wiki safety (read before any docker command), never without explicit user confirmation and if a destructive action is going to happen anyway.