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/s60yucca/mnemos/gemini-mdgit clone --depth 1 https://github.com/s60yucca/mnemosWrote 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/s60yucca/mnemos/gemini-md)<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>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 | $0.00406 | $0.00406 |
| Opus 5 | $0.00203 | $0.00203 |
| Sonnet 5 | $0.00081 | $0.00081 |
| Haiku 4.5 | $0.00041 | $0.00041 |
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.
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
skillif the command/procedure is non-obvious or project-specific. Don't storegit status,ls,cd. Do store project-specific commands with flags, paths, or ordering requirements.
Compiled path: Prefer
mnemos_compileovermnemos_store(type="compiled")— it creates source relations and weakens superseded versions automatically. Usemnemos_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
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.
- 6d ago First seen · 41 lines · 406 tokens per session scan A d1943db80b27
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.
Other instructions, from other repositories
aeon CLAUDE.md
Claude Code instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
cognirepo CLAUDE.md
Claude Code instructions for ashlesh-t/cognirepo, covering claude.md, key rules, session start sequence (run in this order), behavioral confirmation rule and personas (cognirepo-402, cognirepo-403).
wayland-core copilot-instructions.md
Copilot instructions for FerroxLabs/wayland-core, covering ijfw rules, output discipline, memory routing, context discipline and cross-audit.
mcp-structured-memory CLAUDE.md
Claude Code instructions for nmeierpolys/mcp-structured-memory, a project described as: Structured Memory MCP Server.
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.
RNR-Enhanced-Cognee AGENTS.md
AGENTS.md instructions for vincentspereira/RNR-Enhanced-Cognee, covering rnr enhanced cognee implementation for codex, critical requirements, 1. ascii-only output (no unicode encoding), 2. dynamic categories (no hardcoded categories) and 3. standard memory mcp interface.