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/wjohns989/muninn/gemini-mdgit clone --depth 1 https://github.com/wjohns989/MuninnWrote 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/wjohns989/muninn/gemini-md)<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>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 | $0.00815 | $0.00815 |
| Opus 5 | $0.00407 | $0.00407 |
| Sonnet 5 | $0.00163 | $0.00163 |
| Haiku 4.5 | $0.00081 | $0.00081 |
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.
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
- Production-Grade Only: NEVER use placeholders, stubs, or "samples" for core logic. All code must be production-ready, typed, and robust.
- 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). - Optimal Reasoning: Question every assumption. Understand the implications of every choice. Avoid illogical or unsound reasoning at all costs.
- Tool-First Execution: Always leverage the most powerful tools available (MCPs, research tools,
context7) to ensure a comprehensive grasp of the project before acting. - 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.mdphases rigorously.
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 · 65 lines · 815 tokens per session scan A 42177ff3f2cb
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.
Other instructions, from other repositories
remnic AGENTS.md
Instructions for joshuaswarren/remnic, covering remnic - agent guide, architecture boundaries (non-negotiable), upstream references, adapter implementation rules and openclaw compatibility window.
neurostack CLAUDE.md
Instructions for raphasouthall/neurostack, covering neurostack - claude code guide, quick reference, installation, mcp server (recommended for claude code) and openai-compatible api.
cli AGENTS.md
Instructions for konteks/cli, covering agent instructions, project overview, tech stack, repository layout and common commands.
nobrainr CLAUDE.md
Claude Code instructions for vicquick/nobrainr, covering nobrainr — collective agent memory service, what this is, canonical categories, architecture and routing (when using a reverse proxy).
mem0-mcp-selfhosted CLAUDE.md
Instructions for elvismdev/mem0-mcp-selfhosted, covering claude.md, mcp servers, build & test commands and architecture.
flux-memory CLAUDE.md
Instructions for harsh5i/flux-memory, covering flux memory v0.5 — claude.md, hard constraints (never deviate), repo layout, development rules and status.