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

How to keep the HERO block active on overnight agent runs with HERO Anti Over Defense

Put the block in an always-loaded file so long unattended runs keep the scope limits.

Who it is forA researcher or engineer who starts an agent on a long unattended task, such as a multi-hour experiment or refactor, and comes back to a pile of defensive work.

The problemOver a long run the block can fade from the agent's working context, and an invoked copy is absent when nobody is there to invoke it.

The outcomeThe block sits in the agent's always-loaded config, and the hosts guide is used to pick a placement that survives long sessions.

What you need first

  • A coding agent that loads a config file automatically, such as CLAUDE.md, AGENTS.md, .github/copilot-instructions.md or .cursorrules
  • A terminal with curl, awk and grep to run the one-line install, or a text editor to paste the block by hand
  • A project where you can edit the agent config file

Steps

  1. Confirm that the block is in the always-loaded file for your host, using the hosts guide in the hosts/ folder.
  2. Run grep -qi 'scope.limits' CLAUDE.md in the project root, or use the filename for your host, to confirm it is present.
  3. Start the unattended run and check the output at the first checkpoint for over-defensive steps.
  4. If the block seems to have faded in a long session, follow the hook route described in hosts/README.md.

Prompt for your agent

Check that the HERO SCOPE LIMITS block is in the always-loaded config for this project. Then run <long task> and, at each checkpoint, list any hashing, extra review or scaffolding step and state which rule it falls under.

Caveat. The README says the block can fade on long runs and that the fix depends on the cause, so checking at checkpoints is needed, and the hook route is described only in hosts/README.md.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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