# Agent Memory Kit: what to keep, what to forget, a memory file format and a checker for stale or conflicting facts

> Keep or forget rules for six kinds of agent memory, a one-line-per-fact format with source, dates and status, a way to change a fact without losing its history, and mem_check.py, which flags stale entries, passed review dates, two active values for one key, duplicates, stored keys or card numbers, sensitive personal data and lines that read like instructions.

- URL: https://paperchasewebb.ai/bots/marketplace/items/agent-memory-kit-keep-or-forget-rules-and-memory-checker/
- Type: Prompt pack
- Category: Vibe coding
- By: PaperChaseWebb
- Works with: Claude Code, Codex, Grok Bot, Cursor (named in the listing); Plain .md and Python 3.8 or newer scripts, standard library only; unit tested on Python 3.8 to 3.13
- Price: $29 USD
- Difficulty: Beginner
- Setup time: 20 min
- Time to result: A checked memory file in under an hour
- Format: Markdown (.md) file, agent-memory-kit-keep-or-forget-rules-and-memory-checker.md
- Version: 1.0, updated 2026-10-31
- License: Use for your own work and for clients. Do not resell or republish the pack itself.

## What you end up with

Agent memory that stays true: every fact has a source and a review date, old values are retired, and secrets and injected instructions are caught.

## What you get

- 8 sections in one .md file
- Keep or forget rules with a lifetime per kind
- The memory file format and a filled example
- How to supersede and retire facts
- mem_check.py: check, due and active
- A monthly review
- AGENTS.md memory rules
- 21 unit tests

## Who it is for

Anyone whose agent remembers things between sessions and who wants that memory to stay current, sourced and free of secrets.

## Tools needed

- Claude Code, Codex, Cursor, Grok Bot or your own agent: reads and writes the memory file under the AGENTS.md rules
- Python 3.8 or newer: runs mem_check.py; standard library only
- You need: An agent that keeps notes between sessions
- You need: Python 3.8 or newer

Cost to run: The pack is the only purchase. The scripts use no hosted model tokens.

## Sample prompt: Check memory (Claude Code, Codex, Cursor, Grok Bot or your own agent)

```
Run python3 mem_check.py check MEMORY.md, fix every FAIL, and list the WARN lines for me to decide.
```

From the pack.

## Free preview of agent-memory-kit-keep-or-forget-rules-and-memory-checker.md

````markdown
# Agent Memory Kit: what your agent should remember, what it should forget, and a checker for both

A PaperChaseWebb pack, version 1.0, 2026-10-31. For any agent that keeps notes between sessions: Claude Code, Codex, Cursor, ChatGPT or Claude projects, Grok Bot, and your own agents. Plain Markdown plus one small Python script (3.8 or newer, nothing to install).

Agent memory goes wrong slowly. An old price stays "true" for a year, two time zones sit side by side and the agent picks one at random, a pasted key lives in a notes file, a line from a web page turns into a standing order. This kit gives you rules for what to keep and what to forget, one line format that carries its own source and review date, and a checker that flags stale, conflicting, duplicated and dangerous entries before your agent acts on them.

## What is in the kit

| Section | What it is for |
|---|---|
| 01 Keep or forget | What belongs in agent memory, what never does, and how long each kind should live |
| 02 The memory file format | One line per fact, with key, value, kind, source, dates and status, and a filled example file |
| 03 Changing your mind | How to update a fact without losing the history, and how to retire old ones |
| 04 The checker | `mem_check.py check`, `due` and `active`: every code and what to do about it |
| 05 A monthly review | Fifteen minutes a month that keeps memory true |
| 06 AGENTS.md | Rules an agent follows when it reads and writes memory |
| 07 How we tested it | Fixtures, unit tests, Python versions, and what was not tested |
| 08 The files | The script, its unit tests, and a good and a bad sample memory file |

## What you get

- **Keep or forget rules** for six kinds of memory (preference, fact, decision, project, person, temporary), with a lifetime for each.
- **A memory file format** that works in any Markdown file the agent already reads, and still reads well to a person.
- **A checker** that flags stale entries, passed review dates, two active values for one key, duplicates, stored keys or card numbers, sensitive personal data, lines that read like instructions, and missing sources.
- **A `due` list** of what to confirm in the next 30 days, and an **`active` view** that gives the agent only what is current.
````

## Test record

- Date: Oct 31, 2026
- What was run: 21 unit tests on Python 3.8, 3.9, 3.11, 3.12 and 3.13 with warnings as errors, from the source files and from the files extracted out of the pack, with a good and a bad sample memory file.
- Result: All 21 tests passed on every version from both copies.
- Not run: Detection of every possible secret or personal detail; the checks use patterns and word lists.

Copied from this item's dated test notes. What was not run stays in.

## Worth knowing

- Pattern checks can miss some secrets and flag some harmless lines; read the WARN lines yourself.
- Tested 2026-10-31: 21 unit tests on Python 3.8, 3.9, 3.11, 3.12 and 3.13 with warnings as errors, from the source files and from the files extracted out of the pack, with a good and a bad sample memory file. Result: All 21 tests passed on every version from both copies. Not run: Detection of every possible secret or personal detail; the checks use patterns and word lists.

## Questions

**Which agents does it work with?** Any agent that reads a Markdown file at the start of a session.

## How to buy

$29 one time at https://paperchasewebb.ai/bots/marketplace/items/agent-memory-kit-keep-or-forget-rules-and-memory-checker/. Stripe checkout, then an instant download page; the download link is also in your emailed receipt.

Seller: PaperChaseWebb Inc., mgmt@paperchasewebb.com