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

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

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

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

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

The outcomeThe 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.

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. 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 for your agent

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.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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