Borrowing it
Nothing to install: this file belongs to mnemoverse/mcp-memory-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mnemoverse/mcp-memory-server/main/GEMINI.mdgit clone --depth 1 https://github.com/mnemoverse/mcp-memory-serverWrote 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/mnemoverse/mcp-memory-server/gemini-md)<a href="https://agentmods.dev/instructions/mnemoverse/mcp-memory-server/gemini-md"><img src="https://agentmods.dev/badge/instructions/mnemoverse/mcp-memory-server/gemini-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/mnemoverse/mcp-memory-server/gemini-md"><img src="https://agentmods.dev/badge/instructions/mnemoverse/mcp-memory-server/gemini-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00305 | $0.00305 |
| Opus 5.5 | $0.00122 | $0.00122 |
| Sonnet 5.5 | $0.00061 | $0.00061 |
| Haiku 4.5 | $0.00030 | $0.00030 |
Grade A, and why
mcp-memory-server 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 17d 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
Mnemoverse memory discipline
A memory server is connected. Connecting it does not make it useful by itself; these standing rules do.
Recall before acting
Read memory before: starting work on a project you have touched before, choosing a library or pattern, writing tests or commits where conventions apply, answering "how do we usually do X here", and anything phrased as "again" or "like last time". Search with the user's actual words plus the project name. If the first search returns nothing useful, try one broader query, then proceed without memory rather than looping.
Do not recall for one-off factual questions or anything fully specified in the current message.
Save after deciding
Write to memory when: a decision was made that will still matter next week, the user corrected you (the strongest signal there is), an approach failed and you know why, a preference was stated that outlives this task, or a fact about the environment was discovered the hard way. One memory, one fact.
Do not save: file contents you can read again, restatements of the task, transient state, or anything containing secrets, tokens, or personal data. Never store secrets regardless of backend.
Keep the past intact
When something changes, the old fact is not wrong, it is closed. Mark it superseded and write the new one alongside; deleting it destroys the explanation for old work. If recall returns two entries that disagree, surface both with their dates instead of silently picking the closer match.
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.
- 17d ago First seen · 20 lines · 305 tokens per session scan A b13f35f9c923
mcp-memory-server GEMINI.md is an instructions file published in the GitHub repository mnemoverse/mcp-memory-server (26 stars, last pushed today), licensed MIT. It adds 305 tokens to every session, about $0.0012 per session on Opus 5.5. 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 2026-09-24.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode design-tokens.instructions.md
Design-system size tokens (spacing, corner radius, font size, codicon size, stroke). Use when writing or editing CSS to size, space, or round UI — prefer the --vscode- token vars over hardcoded px values.