This bundle is our two Claude Code add-ons in one purchase. The Persistent Memory Kit gives Claude a folder of small Markdown notes and loads the ones that fit the project you're in at the start of every session. The Safety Hooks Pack keeps long tool output out of context, warns you when a session gets large, and blocks writes to folders you list.

Bought separately they cost $29 and $19. The bundle is $39. You get both buyer zips, the same files each product ships on its own.

Claude Code Persistent Memory Kit (normally $29)

The loader runs at session start, after /clear and after every compaction. It loads your standing rules, your profile, a one-line index of your recent projects and the full note for the project folder you're in. It is capped at 24,000 characters (about 6,000 tokens), and if something has to be trimmed, it trims project detail and leaves your rules alone.

• install.py: one command installs, one uninstalls. It backs up settings.json first and keeps the hooks you already have.
• The loader hook (SessionStart), with --preview to show exactly what will load.
• A dump hook (PreCompact and SessionEnd) that saves the end of each transcript to a raw/ folder with common key and token shapes redacted, and rotates old dumps.
• A weekly hygiene check that flags stale projects and possible duplicate notes.
• 8 templates, settings.json snippets for Windows and for macOS/Linux, 22 unit tests and a 10-page PDF guide.

Claude Code Safety Hooks Pack (normally $19)

• Protected-path guard (PreToolUse). List folders in a JSON file. Edits, rm, mv, redirects, git clean, Remove-Item, Set-Content and similar writes into them are refused, or you're asked first. Reading still works. If the guard crashes or times out, the call is blocked.
• Output truncation (PostToolUse). Bash, PowerShell or MCP output over 15,000 characters is saved to a file. Claude sees the first 2,500 characters, the last 1,500 and the file path. In our test, a 38,590-character log went into context as 4,303 characters.
• Token sentinel (UserPromptSubmit). A one-line warning when the context passes 150,000 tokens (you choose the number), once per 25,000-token step.
• Cache pruning (SessionStart). Clears truncation files older than 3 days and nothing else.
• Transcript dump (PreCompact, SessionEnd). Saves the last 160 transcript lines before compaction and at exit, with known key and token formats redacted.
• settings.json snippets for Windows (Git Bash or PowerShell) and macOS/Linux, an example protected-folder list, 76 pytest cases (75 passed, 1 skipped on our Windows machine), a README and a 6-page PDF guide.

Using both together

Both kits include a transcript dump hook. They write to different folders and don't clash, so if you install both you can leave the Hooks Pack's dump hook out.

Before you buy

• Memory Kit: Claude Code with hooks support and Python 3.8 or newer (standard library only), on Windows 10/11, macOS or Linux.
• Hooks Pack: Claude Code v2.1.295 or later and Python 3 on your PATH. We ran its test suite on Windows 11. The macOS and Linux settings use the same scripts with python3.
• Both are Python code and text files. You'll run commands in a terminal and edit a few files.

What they don't do

• The Memory Kit has no cloud sync and no vector search, sends nothing over the network, and doesn't read or change other apps' memory, including your CLAUDE.md files.
• The guard reads the command line only. It can't see inside scripts, doesn't decode obfuscated commands and doesn't cover MCP tools. It's a guard rail against mistakes, not a security boundary. Keep backups.
• The sentinel warns. It never compacts or clears for you.
• Redaction in both dump hooks catches known key and token formats. It's best effort, so keep secrets out of your chats and treat the dump folders as private.
• A future change to Claude Code's hook format may need an update.

Licence

Each kit keeps its own licence. Memory Kit: use it on any number of machines you own or control, for personal or commercial work, and change it for your own use. Hooks Pack: use on your own machines for personal and client work. No resale, redistribution or sharing of either.

How it was made

Written with AI help (Claude) and reviewed by AmagiLabs before release. AmagiLabs isn't affiliated with Anthropic; Claude and Claude Code are Anthropic's trademarks.

Refunds

All sales are final. You get this digital download right away, so we don't give cash refunds. If a file won't open or the product doesn't match this page, email us within 7 days of purchase. We'll fix it or send a replacement. If we can't, you'll get store credit for the full price.

EU and UK buyers: you'd normally have 14 days to withdraw from this purchase. You lose that right once your download or access starts, because you ask for immediate access at checkout. If the product is faulty or not as described, the 7-day limit doesn't apply to you. If we can't fix it, you can choose a refund instead of store credit.

Nothing in this policy limits your rights under the law where you live. You can ask us for a written copy of this policy at any time.