# Mnemosyne Memory Override

> Stricter, user-selected override that forces Mnemosyne for all durable memory storage, including small standing rules. Apply it only when the user has consciously chosen this policy; installation, this skill appearing in the skills index, or an ordinary memory task is not that choice. Without it, the default applies: bulk durable facts go to Mnemosyne, and small standing rules and context anchors may stay in the always-injected memory tier.

- Skill: `openclaw-cn-dev/mnemosyne-memory-override` (Agent Skill)
- Install (CLI): `npx get-skill add openclaw-cn-dev/mnemosyne-memory-override`
- Raw SKILL.md: https://api.skillmd.com/api/skills/openclaw-cn-dev/mnemosyne-memory-override/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Productivity
- Author: openclaw-cn-dev (https://skillmd.com/u/openclaw-cn-dev)
- Updated: 2026-11-14
- Page: https://skillmd.com/skills/openclaw-cn-dev/mnemosyne-memory-override

---


# Mnemosyne Memory Override

## Activation and precedence

This skill is a stricter policy than Mnemosyne's default. It is in effect only
when the user has consciously selected it. Installing the plugin, finding this
skill in the skills index, or being asked to remember something does not select
it. When it is not selected, follow the default: use Mnemosyne for bulk durable
facts, preferences, and insights, and leave small standing rules and context
anchors in the always-injected memory tier, which is bounded and loaded per
session.

Once the user has selected it, the rules below replace that default exception.

## CRITICAL RULE

**NEVER use the `memory` tool for durable facts.**

The legacy `memory` system is deprecated. It has a tiny 2,200 character limit
and does not use vector search. Mnemosyne is the single source of truth for
all durable user data.

## Mapping

| Old (FORBIDDEN) | New (REQUIRED) |
|-----------------|----------------|
| `memory(action="add", target="user", ...)` | `mnemosyne_remember(content=..., importance=0.9+, source="preference")` |
| `memory(action="add", target="memory", ...)` | `mnemosyne_remember(content=..., importance=0.7+, source="fact")` |
| `memory(action="replace", ...)` | Use the relevant Mnemosyne update flow: recall the current entry, then store corrected content with `mnemosyne_remember`; use an explicit update tool/flow when the integration exposes one. |
| `memory(action="remove", ...)` | Use the relevant Mnemosyne invalidation/forget flow: mark the obsolete fact invalid, supersede it with corrected content, or call the integration's forget/remove tool when available. Do not rely on passive aging for known-wrong durable data. |

## When to use legacy memory (rare)

- Ephemeral session state (current todo list, temp flags)
- When Mnemosyne is explicitly confirmed down

## Muscle Memory / Reflex Problem

You will reflexively reach for `memory` out of old habit. This is a known bug
in your training. Before EVERY memory tool call, pause and ask:

> "Is this durable? Would I want this next session?"

If yes → use Mnemosyne
If no (temp flag, todo state) → `memory` is acceptable

## Migration Cleanup

Migrate only under this selected policy. Under the default, small standing rules
and context anchors stay in the always-injected tier and are not migrated.

When moving data from legacy memory to Mnemosyne:
1. Save to Mnemosyne first with `mnemosyne_remember`
2. Then REMOVE the old entry from `memory` with `memory(action="remove")`
3. This prevents stale duplicates and confusion

## Enforcement

If you catch yourself typing `memory(action=` for durable data:
1. CANCEL that tool call
2. Use Mnemosyne instead
3. Set importance >= 0.7 for anything that matters later
4. If you already polluted legacy memory, remove the entry immediately

