/export

description: "Export memories to CLAUDE.md"
argument-hint: "[--replace]"

/nemp:export

Export all project memories to `CLAUDE.md`. Use `--replace` to overwrite the entire file, or run without flags to append/update the Nemp section only.

Usage

/nemp:export           # Append or update Nemp section in CLAUDE.md
/nemp:export --replace # Replace entire CLAUDE.md with Nemp content only

Arguments

• (no args): Append or update the Nemp section in `CLAUDE.md`
• `--replace`: Replace the entire `CLAUDE.md` instead of appending/updating

Instructions

When the user invokes `/nemp:export`, follow these steps:

Step 1: Parse Arguments

Identify which flag (if any) the user provided:

(no args)    → Export to CLAUDE.md (append/update)
--replace    → Export to CLAUDE.md (full replace)

If the argument is unrecognised, display the Usage block above and stop.

---

Memory Loading (shared by all export paths)

Before generating any export file, perform these steps to load and prepare memories.

Step 2: Read memories.json

Read `.nemp/memories.json`:

[ -f ".nemp/memories.json" ] && cat .nemp/memories.json

If the file does not exist, stop and show:

❌ No memories to export.

Save some memories first:
  /nemp:save stack Next.js 15 with TypeScript
  /nemp:init  (auto-detect project stack)

Step 3: Parse Format (with Backward Compatibility)

The file may use either format:

**New array format:**

{
  "memories": [
    {
      "key": "version",
      "value": "0.3.0",
      "created": "2026-02-26T16:00:00.000Z",
      "updated": "2026-02-26T16:00:00.000Z",
      "tags": ["auto-detected"],
      "type": "fact",
      "vitality": { "state": "active" }
    }
  ]
}

**Legacy flat-object format:**

{
  "stack": { "value": "Next.js", "created": "...", "updated": "..." },
  "auth":  { "value": "NextAuth", "created": "...", "updated": "..." }
}

If the parsed JSON does not have a `memories` array, treat each top-level key as a memory entry with:

key      = the JSON key name
value    = entry.value
created  = entry.created
updated  = entry.updated
type     = entry.type (if present, else undefined)
vitality = entry.vitality (if present, else undefined)

Step 4: Filter Out Extinct Memories

Skip any memory where `vitality.state === "extinct"`. Absent `vitality` means the memory is active — do not skip it.

If `memories.json` cannot be parsed as valid JSON, stop and report:

❌ memories.json is not valid JSON. Check the file for syntax errors.

---

/nemp:export (no args) and /nemp:export --replace

Step 5a: Parse and Organize Memories for CLAUDE.md

Group memories by semantic key names:

• **Tech Stack**: keys containing `stack`, `framework`, `database`, `auth`, `styling`, `orm`, `testing`, `deployment`
• **Project Info**: keys containing `project`, `description`, `name`, `structure`, `version`, `type`, `subproject`
• **Global Preferences**: keys containing `prefer`, `style`, `convention`, `no-`, `favorite`, `team`, `workspace`
• **Other**: everything else

Step 6a: Generate CLAUDE.md Section Content

Create a clean, professional markdown section.

Use the **table format** for short values (< 80 chars):

## Project Context (via Nemp Memory)

> Auto-generated by Nemp Memory. Last updated: [YYYY-MM-DD HH:MM]

### Tech Stack

| Key | Value |
|-----|-------|
| **stack** | Next.js 15, TypeScript, Prisma, PostgreSQL |
| **auth** | NextAuth with JWT |

---

Use the **prose format** for longer values:

**project-description:** A SaaS starter kit for building subscription-based applications.

**structure:**
- Commands defined in /commands/*.md
- Plugin config in .claude-plugin/

Use the table format for short values (< 80 chars) and the prose format for longer values. Emit a section heading (`### Tech Stack`, etc.) only for groups that have at least one memory.

Step 7a: Check for Existing CLAUDE.md

[ -f "CLAUDE.md" ] && cat CLAUDE.md

Step 8a: Handle CLAUDE.md Updates

**If `--replace` flag:** Write the Nemp section as the entire CLAUDE.md, replacing all existing content.

**If no flag (append/update mode):**

• **CLAUDE.md does not exist:** Create a new file with just the Nemp section.
• **CLAUDE.md exists with a Nemp section:** Find `## Project Context (via Nemp Memory)`, find where the section ends (next `## ` heading, a line containing only `---`, or end of file), and replace only that section. Preserve all other content.
• **CLAUDE.md exists without a Nemp section:** Append the Nemp section at the end with a blank line before it for clean separation.

Step 9a: Write CLAUDE.md

Use the Write tool to save the updated content.

Step 10a: Confirm to User

✅ Exported to CLAUDE.md

   Memories exported: 5
   File: ./CLAUDE.md

   Exported keys:
   • stack
   • auth
   • styling
   • database
   • project-description

💡 CLAUDE.md is automatically read by Claude Code at session start.

---

Example

User: `/nemp:export`

Given `.nemp/memories.json` with 2 memories:

{
  "stack": { "value": "Next.js 15 with TypeScript, Prisma, PostgreSQL", "created": "2024-01-20T10:00:00Z", "updated": "2024-01-20T10:00:00Z" },
  "auth":  { "value": "NextAuth with JWT", "created": "2024-01-20T10:00:00Z", "updated": "2024-01-20T10:00:00Z" }
}

Creates/updates CLAUDE.md:

## Project Context (via Nemp Memory)

> Auto-generated by Nemp Memory. Last updated: 2024-01-20 10:00

**stack:** Next.js 15 with TypeScript, Prisma, PostgreSQL

**auth:** NextAuth with JWT

---

Response:

✅ Exported to CLAUDE.md

   Memories exported: 2
   File: ./CLAUDE.md

   Exported keys:
   • stack
   • auth

💡 CLAUDE.md is automatically read by Claude Code at session start.

---

Section Detection Logic (CLAUDE.md update)

To find and replace an existing Nemp section:

1. Search for the line: `## Project Context (via Nemp Memory)` 2. Find where t