agentmods.dev

memory-import-guide

memory-import-guide is a skill for Claude Code from studiomeyer-io/studiomeyer-marketplace. It costs 52 tokens per session (886 once invoked), scanned A, original, MIT.

A guide for importing conversation history from ChatGPT, Claude, Gemini, Microsoft Copilot, or Perplexity into StudioMeyer Memory. It explains which exported files to use and how to preview an import.

In plain words
What is it for?
Use it to export conversations, analyze the proposed import, confirm the preview, and then add sessions, learnings, entities, and decisions to memory.
Why use it?
It helps preserve useful past conversations while reducing the risk of importing the wrong files or writing unexpected data.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

Part of the studiomeyer-memory plugin — 2 skills, 11 commands, 1 agent shipped together

not rated 2repo changed 5d ago A scan 52 tokens original MIT

Good fit Use it to export conversations, analyze the proposed import, confirm the preview, and then add sessions, learnings, entities, and decisions to memory.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/studiomeyer-io/studiomeyer-marketplace/memory-import-guide
View source ↗ studiomeyer-io/studiomeyer-marketplace studiomeyer.io
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.

Any agent
npx skills add studiomeyer-io/studiomeyer-marketplace --skill memory-import-guide
Clone the repo
git clone --depth 1 https://github.com/studiomeyer-io/studiomeyer-marketplace

Made for: Claude Code.

Or install studiomeyer-memory, the plugin that ships this one along with the rest of its 2 skills, 11 commands, 1 agent.

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 memory-import-guide

README.md
[![agentmods](https://agentmods.dev/badge/skills/studiomeyer-io/studiomeyer-marketplace/memory-import-guide/github.svg)](https://agentmods.dev/skills/studiomeyer-io/studiomeyer-marketplace/memory-import-guide)
Your own site
<a href="https://agentmods.dev/skills/studiomeyer-io/studiomeyer-marketplace/memory-import-guide"><img src="https://agentmods.dev/badge/skills/studiomeyer-io/studiomeyer-marketplace/memory-import-guide/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.

agentmods 80×15 button for memory-import-guide

Your own site · 80×15
<a href="https://agentmods.dev/skills/studiomeyer-io/studiomeyer-marketplace/memory-import-guide"><img src="https://agentmods.dev/badge/skills/studiomeyer-io/studiomeyer-marketplace/memory-import-guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 886 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00052 $0.00886
Opus 5 $0.00026 $0.00443
Sonnet 5 $0.00010 $0.00177
Haiku 4.5 $0.00005 $0.00089

Measured 5d ago against content hash 1657c32debff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

memory-import-guide 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 5d 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.

plugins/studiomeyer-memory/skills/memory-import-guide/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memory Import Guide

StudioMeyer Memory can ingest conversation history from five platforms via nex_import. This skill is the recipe book for each one.

How import works

  1. Export the conversation history from the source platform to a file on disk.
  2. Analyze: nex_import with action: "analyze" shows a preview of what would be imported without writing anything.
  3. Confirm the preview with the user.
  4. Import: nex_import with action: "import" writes sessions, learnings, entities, and decisions into the user's tenant.

Always run analyze first. Imports are append-only but still worth confirming, especially when there are thousands of messages.

Platform-specific export recipes

ChatGPT

  1. Settings → Data Controls → Export Data
  2. You get a ZIP by email. Unzip it.
  3. The file you want is conversations.json (sometimes conversations.jsonl on newer exports).
  4. Run nex_import with platform: "chatgpt" and the file path.

Claude

  1. Settings → Account → Export Data
  2. Unzip. Use conversations.json.
  3. nex_import with platform: "claude".

Gemini

  1. Google Takeout → Select "Gemini" → Export
  2. You get a ZIP with an HTML or JSON bundle.
  3. nex_import with platform: "gemini".

Microsoft Copilot

  1. Copilot settings → Activity → Export
  2. JSON file.
  3. nex_import with platform: "copilot".

Perplexity

  1. Perplexity settings → Export conversations
  2. JSON file.
  3. nex_import with platform: "perplexity".

What gets extracted

nex_import uses Haiku (fast, cheap) to extract:

  • Sessions: one per conversation, with start/end timestamps from the source
  • Learnings: salient facts, insights, and patterns from the conversation
  • Entities: people, projects, tools, services mentioned
  • Decisions: explicit choices the user made with stated rationale
  • Relations: links between extracted entities

The extraction is conservative. It will not invent facts. If a conversation is pure chit-chat, very little will be saved.

Read the full file on GitHub · 91 lines

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. 5d ago Changed 1657c32debff
  2. 10d ago First seen · 91 lines · 52 tokens per session scan A 09f713226ab6

Subscribe to this mod's changes

memory-import-guide is a skill published in the GitHub repository studiomeyer-io/studiomeyer-marketplace (2 stars, last pushed 6d ago), licensed MIT. It adds 52 tokens to every session and 886 once invoked, about $0.0003 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.

Claude CodeMemory and contextagent-personasai-memoryclaude-code-plugincrmgeo
Related

Other skills, from other repositories

memory-protocol

A shared set of rules for using a persistent memory service across coding-agent sessions.

vbcherepanov/total-agent-memory · 120 tokens

memory

Activate this skill when starting a new session, beginning a new task, saving knowledge, recalling past decisions, or after completing significant work. Also activate on errors to log them for pattern analysis. Relevant when the user asks about memory, past context, lessons learned, decisions history, project…

vbcherepanov/total-agent-memory · 65 tokens

engram

Read and write the project's durable reasoning memory (decisions, principles, cautions, problems, insights) through the Engram MCP tools. Recall relevant memory before non-trivial work; capture only durable, high-value knowledge silently at natural stopping points; keep the graph honest (judge suspects, close answered…

techtheist/engram · 78 tokens

engram-digest

Seed or top up this project's Engram graph from the existing codebase — an explicit, user-invoked digestion of the current working tree into typed memory nodes (decisions, principles, cautions, problems, insights, intents). Use when the user says "digest this project", "ingest the codebase into memory", "seed the…

techtheist/engram · 98 tokens

garden-tending

Tend the knowledge garden — diagnose vault health, condense project memos into project.md overviews, create/merge cross-project topics, fix broken links, archive superseded notes, extend trails. Trigger on "tend the garden", "condense", "update project overview", "check vault health", "where are we with X?", "what…

linxule/memex-plugin · 131 tokens

curator-practice

Operating philosophy for autonomous memex curator tending — orientation protocol, signal triage, bounded work units, initiative thresholds, logging conventions. Trigger on cron-launched runs with no user prompt, "use your judgment", "tend without instructions", "do a pass on the vault", "I'll be away — do what needs…

linxule/memex-plugin · 153 tokens