Muninn GEMINI.md

Muninn GEMINI.md is an instructions file for Gemini CLI from wjohns989/Muninn. It costs 815 tokens per session, scanned A, original, Apache-2.0.

Project instructions for developing Muninn MCP, a local-first system that stores and retrieves persistent assistant memory. MCP is a standard way for AI assistants to use external tools.

In plain words
What is it for?
Use them when changing Muninn MCP, especially to understand its design, follow its development practices, and update the relevant project files.
Why use it?
They keep contributions aligned with the project's architecture, quality expectations, and requirement for production-ready code.

Instructions file for Gemini CLI

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/wjohns989/muninn/gemini-md
Clone the repo
git clone --depth 1 https://github.com/wjohns989/Muninn

Made for: Gemini CLI.

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.

agentmods badge for Muninn GEMINI.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/wjohns989/muninn/gemini-md.svg)](https://agentmods.dev/instructions/wjohns989/muninn/gemini-md)
Your own site
<a href="https://agentmods.dev/instructions/wjohns989/muninn/gemini-md"><img src="https://agentmods.dev/badge/instructions/wjohns989/muninn/gemini-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 815 This file is loaded in full into every session.
When invoked 815 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.

ModelPer sessionOnce invoked
Fable 5 $0.00815 $0.00815
Opus 5 $0.00407 $0.00407
Sonnet 5 $0.00163 $0.00163
Haiku 4.5 $0.00081 $0.00081

Measured 3d ago against content hash 42177ff3f2cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Muninn GEMINI.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.

GEMINI.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Muninn MCP — SOTA+ Development Context

Role: Muninn is a local-first, assistant-agnostic persistent memory infrastructure designed to outstrip existing systems (like Mem0 or Serena) through deterministic retrieval, neuroscience-inspired consolidation, and production-grade operational controls.

Core Mandate: This project is developed using Muninn to develop itself. Every contribution must meet SOTA+ (State of the Art Plus) standards of precision, quality, and logic.


🚀 SOTA+ Development Philosophy

  1. Production-Grade Only: NEVER use placeholders, stubs, or "samples" for core logic. All code must be production-ready, typed, and robust.
  2. Evidence-Driven Logic: Every decision must be grounded in the codebase's existing architecture (docs/ARCHITECTURE.md) or the SOTA+ implementation plan (SOTA_PLUS_PLAN.md).
  3. Optimal Reasoning: Question every assumption. Understand the implications of every choice. Avoid illogical or unsound reasoning at all costs.
  4. Tool-First Execution: Always leverage the most powerful tools available (MCPs, research tools, context7) to ensure a comprehensive grasp of the project before acting.
  5. Quality Over Speed: Never sacrifice precision for speed. A correctly implemented, well-tested feature is the only acceptable outcome.

🛠 Operational Guidelines (Always-On)

When working on Muninn, the following modes are strictly enforced:

  • --orchestrate: Manage multi-step implementations with clear planning and checkpoints.
  • --ultrathink: Perform deep, reflective reasoning on architectural impacts before modification.
  • --uc (Ultra-Compressed): Maintain maximum token efficiency in communication without losing clarity.
  • --delegate: Use sub-agents for parallel analysis or specialized investigation when appropriate.
  • --all-mcp: Utilize all available Model Context Protocol tools to verify state and context.
  • --task-manage: Track progress through the SOTA_PLUS_PLAN.md phases rigorously.

Read the full file on GitHub · 65 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.

  1. 3d ago First seen · 65 lines · 815 tokens per session scan A 42177ff3f2cb

Subscribe to this mod's changes

Muninn GEMINI.md is an instructions file published in the GitHub repository wjohns989/Muninn (1 stars, last pushed 9d ago), licensed Apache-2.0. It adds 815 tokens to every session, about $0.0041 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.