# AI use cases for AI Memory Skillpack (tudoumashu/ai-memory-skillpack)

Repo: [tudoumashu/ai-memory-skillpack](https://github.com/tudoumashu/ai-memory-skillpack) | Use cases: 5 | Page: https://dedupedai.com/use-cases/tudoumashu-ai-memory-skillpack/

A bounded project-memory skill pack that gives Codex CLI, and optionally Claude Code, a size-capped, attributed memory of each repository, installed by an agent-executable installer.

This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL.

- Give Codex a durable, size-capped memory of your repo: https://dedupedai.com/use-cases/tudoumashu-ai-memory-skillpack/set-up-bounded-repo-memory-codex/
- Resume a repo in a new session from one handoff page: https://dedupedai.com/use-cases/tudoumashu-ai-memory-skillpack/resume-repo-in-fresh-session/
- Check pack integrity and tests before trusting an install: https://dedupedai.com/use-cases/tudoumashu-ai-memory-skillpack/verify-pack-before-installing/
- Upgrade an older memory install and keep your own edits: https://dedupedai.com/use-cases/tudoumashu-ai-memory-skillpack/upgrade-memory-keep-your-edits/
- Use one skill source for both Codex and Claude Code: https://dedupedai.com/use-cases/tudoumashu-ai-memory-skillpack/share-skills-codex-claude-one-source/

## How to give Codex a durable, size-capped memory of your repo with AI Memory Skillpack

Repo: [tudoumashu/ai-memory-skillpack](https://github.com/tudoumashu/ai-memory-skillpack) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Install the memory pack so Codex keeps a one-page project card and handoff per repo.

**Who it is for:** A developer who uses Codex CLI on a repo and is tired of re-explaining the project at the start of every session.

**The problem:** Agent notes either vanish between sessions or grow without limit in handoff and changelog files, which costs context on every new session.

**The outcome:** Codex reads a small HOT snapshot (project card and handoff) and searches WARM sections with rg, while most of docs/ai/ stays unread.

### Steps

1. Run `git clone https://github.com/tudoumashu/ai-memory-skillpack.git`
2. Run `cd ai-memory-skillpack`
3. Run `sha256sum -c SHA256SUMS` and confirm every listed file reports OK before continuing
4. Tell Codex: Read `INSTALL.md` in this pack and follow it to install the memory system on this machine.
5. Enable the repo as the installer directs, then start a Codex session in that repo and confirm it reads docs/ai/project-card.md

### Prompt to paste into your agent

```text
In the ai-memory-skillpack repo, follow INSTALL.md to install the ai-project-memory skill for Codex on this machine, then enable the repo at <repo-path>. Report the install receipt location and the list of files created under docs/ai/ in <repo-path>. Verify that sha256sum -c SHA256SUMS passed before any install step ran.
```

### Caveat

The README says the installer skips llm-wiki and project-mastery-coach when there is no Obsidian vault, and that wiki lint and query scripts are not in this repo.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/tudoumashu-ai-memory-skillpack/set-up-bounded-repo-memory-codex/

## How to resume a repo in a new session from one handoff page with AI Memory Skillpack

Repo: [tudoumashu/ai-memory-skillpack](https://github.com/tudoumashu/ai-memory-skillpack) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Start a new Codex or Claude Code session from the repo's handoff instead of old chat logs.

**Who it is for:** An engineer picking up a repo after a few days away, or handing work to a new agent session that has no prior context.

**The problem:** A new session has no memory of what was in progress, and long append-only notes waste tokens before real work starts.

**The outcome:** The new session loads the project card and handoff, then uses rg to pull only the WARM section it needs, such as the runbook or gotchas.

### Steps

1. Confirm the repo has been enabled by the installer and that docs/ai/handoff.md exists
2. Open a new Codex session in the repo root
3. Ask the agent to read docs/ai/project-card.md and docs/ai/handoff.md first
4. Ask the agent to search WARM files with rg for the section it needs, not to read all of docs/ai/
5. Check that the agent states the current task from handoff.md before it edits any file

### Prompt to paste into your agent

```text
In the repo at <repo-path>, read docs/ai/project-card.md and docs/ai/handoff.md only, then search WARM files for <topic> with rg. Expected output: a three-line summary of the current task, the next step from handoff.md, and the file and section used. Verify that no COLD file under history/ was read unless I ask for it.
```

### Caveat

Claude Code support is described as optional and uses symlinks to the same skill source, so the Claude side depends on the second-harness setup.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/tudoumashu-ai-memory-skillpack/resume-repo-in-fresh-session/

## How to check pack integrity and tests before trusting an install with AI Memory Skillpack

Repo: [tudoumashu/ai-memory-skillpack](https://github.com/tudoumashu/ai-memory-skillpack) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README

Run the hash check and coach test suite to confirm the pack has not been altered.

**Who it is for:** A maintainer or security-minded developer who wants proof a copied or updated memory pack matches its published hashes before it runs on a machine.

**The problem:** A pack that was edited or corrupted in transit could install unexpected files, and a plain prompt gives no way to prove it is intact.

**The outcome:** A clear pass or fail from the hash check and regression tests, with failures stopping the install.

### Steps

1. Run `git clone https://github.com/tudoumashu/ai-memory-skillpack.git`
2. Run `cd ai-memory-skillpack`
3. Run `sha256sum -c SHA256SUMS` and stop if any line does not report OK
4. Run `bash tests/run.sh python3 skills/project-mastery-coach/scripts/project_mastery_state.py`
5. Read VERIFY.md and confirm the post-install assertions match what you expect before running the installer

### Prompt to paste into your agent

```text
In the ai-memory-skillpack repo, run sha256sum -c SHA256SUMS and the tests/run.sh command for project_mastery_state.py. Expected output: each hash line reported OK and the test runner exit status. Verify that the agent reports failure and makes no install changes if any hash fails.
```

### Caveat

The README says a changed listed file fails the installer integrity gate unless SHA256SUMS is regenerated, so local edits to the pack will fail this check.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/tudoumashu-ai-memory-skillpack/verify-pack-before-installing/

## How to upgrade an older memory install and keep your own edits with AI Memory Skillpack

Repo: [tudoumashu/ai-memory-skillpack](https://github.com/tudoumashu/ai-memory-skillpack) | Difficulty: Advanced | Time: 60 minutes | Basis: From the README

Move a machine to a newer pack while receipt hashes protect edited files.

**Who it is for:** A developer or team lead with an older pack already installed on a machine who needs the newer version without losing local changes.

**The problem:** A naive upgrade can overwrite memory files the user edited by hand, silently losing project knowledge.

**The outcome:** Files the pack did not change are updated, edited files are kept and reported, and the old pack is archived rather than destroyed.

### Steps

1. Read the migration/ folder in the new pack to find the procedure for machines with an older pack
2. Run `sha256sum -c SHA256SUMS` in the new pack and confirm all lines report OK
3. Tell Codex: Read `INSTALL.md` in this pack and follow the upgrade or migrate path for this machine.
4. Review the receipt report for any file whose hash mismatched, and confirm your edits were kept
5. Confirm the old pack was archived, not deleted, before you remove anything by hand

### Prompt to paste into your agent

```text
In the new ai-memory-skillpack checkout, follow INSTALL.md and the migration/ procedure to upgrade the memory install on this machine. Expected output: a list of files replaced, files kept because of local edits, and the archive path of the old pack. Verify that no file with a receipt hash mismatch was overwritten.
```

### Caveat

The README says the installer targets bash 4.4 or newer and GNU tools, so an older bash or a stock macOS shell will stop the upgrade before any file changes.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/tudoumashu-ai-memory-skillpack/upgrade-memory-keep-your-edits/

## How to use one skill source for both Codex and Claude Code with AI Memory Skillpack

Repo: [tudoumashu/ai-memory-skillpack](https://github.com/tudoumashu/ai-memory-skillpack) | Difficulty: Advanced | Time: 45 minutes | Basis: From the README

Keep one copy of the memory skills and point Claude Code at it with symlinks.

**Who it is for:** A developer who runs both Codex CLI and Claude Code on the same machine and does not want two forked copies of the same memory rules.

**The problem:** Maintaining separate skill copies for two harnesses causes drift, so the two agents remember the project differently.

**The outcome:** Codex holds the real files and Claude Code reads the same skills through symlinks, with per-harness rule sections kept separate.

### Steps

1. Install the pack for the primary harness, Codex, as described in INSTALL.md
2. Confirm the installer created symlinks for the second harness instead of copies
3. Check that the per-harness memory section for Claude Code lives in CLAUDE.md, separate from Codex AGENTS.md
4. Start a Claude Code session in an enabled repo and confirm it reads the same docs/ai/project-card.md
5. Run `sha256sum -c SHA256SUMS` again after any edit to a skill file so the integrity gate still passes

### Prompt to paste into your agent

```text
On this machine, after installing the ai-project-memory skill for Codex per INSTALL.md, confirm that the Claude Code skill directory contains symlinks to the Codex skill files and not copies. Expected output: a list of each skill path with its link target. Verify that no skill file exists as a separate copy in the Claude Code directory.
```

### Caveat

The README describes Claude Code support as optional and does not give the exact symlink paths, so the agent must read INSTALL.md for the adapter values on this machine.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/tudoumashu-ai-memory-skillpack/share-skills-codex-claude-one-source/