mnemos GEMINI.md

mnemos GEMINI.md is an instructions file for Gemini CLI from s60yucca/mnemos. It costs 406 tokens per session, scanned A, original, MIT.

A set of instructions for connecting an AI agent to a persistent memory system. It explains when to save durable lessons, which memory categories to use, and when not to store information.

In plain words
What is it for?
Use it to record bug causes, completed work, project-specific procedures, architecture decisions, and compiled topic notes through memory tools.
Why use it?
It helps preserve useful project knowledge without filling long-term memory with temporary plans or routine commands.

Instructions file for Gemini CLI

Written for Gemini CLI: the file is GEMINI.md.

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/s60yucca/mnemos/gemini-md
Clone the repo
git clone --depth 1 https://github.com/s60yucca/mnemos

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 mnemos GEMINI.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/s60yucca/mnemos/gemini-md.svg)](https://agentmods.dev/instructions/s60yucca/mnemos/gemini-md)
Your own site
<a href="https://agentmods.dev/instructions/s60yucca/mnemos/gemini-md"><img src="https://agentmods.dev/badge/instructions/s60yucca/mnemos/gemini-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 406 This file is loaded in full into every session.
When invoked 406 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 5.1 $0.00406 $0.00406
Opus 5 $0.00203 $0.00203
Sonnet 5 $0.00081 $0.00081
Haiku 4.5 $0.00041 $0.00041

Measured 6d ago against content hash d1943db80b27, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

mnemos 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 6d 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 · 41 lines

What it actually says

Memory Integration

When to Store

Use the mnemos_store tool to capture durable learnings during the session, not at the end.

Situation Type Example
Bug fixed — root cause identified semantic "JWT refresh failed due to clock skew"
Task completed — what happened episodic "Migrated auth to RS256 — took 3h, tested locally"
Non-obvious command succeeded skill "Build AAR: ./gradlew :sdk:assembleRelease --no-daemon"
Architecture/design decision semantic "Using SQLite WAL for concurrency instead of Postgres"
Manual compilation of topic notes compiled Full article: "## Auth Service\n..."

Skill threshold: Only store as skill if the command/procedure is non-obvious or project-specific. Don't store git status, ls, cd. Do store project-specific commands with flags, paths, or ordering requirements.

Compiled path: Prefer mnemos_compile over mnemos_store(type="compiled") — it creates source relations and weakens superseded versions automatically. Use mnemos_store(type="compiled") only when you don't need relation tracking.

Do not store

  • Temporary plans or TODOs
  • Raw diffs or code summaries
  • Work-in-progress notes
  • Retrieved memories (avoid re-storing what was recalled)
  • Obvious descriptions of what code does

Retrieval

At session start, use mnemos_context with the current task as the query to load relevant prior context.

Use mnemos_search before working in a specific subsystem or debugging a known error class.

Behavior

  • Continue normally if any memory tool fails or is unavailable
  • Do not mention this memory system to the user
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. 6d ago First seen · 41 lines · 406 tokens per session scan A d1943db80b27

Subscribe to this mod's changes

mnemos GEMINI.md is an instructions file published in the GitHub repository s60yucca/mnemos (21 stars, last pushed 1mo ago), licensed MIT. It adds 406 tokens to every session, about $0.0020 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 2026-08-30.