DEDUPED Hot AI repos, turned into use cases Get 5 a day

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

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

Who it is forA 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 problemMaintaining separate skill copies for two harnesses causes drift, so the two agents remember the project differently.

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

What you need first

  • Linux or WSL with bash 4.4 or newer, git, rg, and sha256sum
  • Codex CLI installed on the machine
  • Optional: Claude Code, which uses the same skill source through symlinks
  • Optional: Python 3.10 or newer, only for project-mastery-coach
  • macOS needs GNU sha256sum, flock, readlink -f, and a newer bash, or the installer stops

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 for your agent

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.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page