DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to approve each file write before it applies with Hermes Plan Mode

Choose "Approve, review each file edit" so every write or patch shows its path and preview first.

Who it is forA developer making a risky change in a shared codebase who wants to inspect every file write.

The problemApproving a whole plan at once means file writes happen without a look at each one.

The outcomeEach write_file or patch shows its path and a preview, and you decide whether it is applied.

What you need first

  • A working Hermes Agent install that supports plugins
  • The exact 40-character commit SHA of the latest plugin release, from its release notes
  • A new Hermes session after installing, or a restart of running CLI, TUI and Desktop sessions
  • For messaging platforms: a running Hermes gateway (`hermes gateway restart`)

Steps

  1. Start planning with /planmode on <task> or /plan <task>. (inferred, check the README)
  2. Read the plan the agent submits.
  3. Choose "Approve, review each file edit". This option appears only when Hermes approvals are on.
  4. When each file write appears, check its path and preview, then approve or deny it.

Prompt for your agent

In the Hermes session for <repo-path>, start plan mode with /planmode on <task>. After I approve with review each file edit, confirm that every write_file and patch triggers an approval prompt before it applies, and list the file paths that were applied.

Caveat. The per-edit review option is offered only when Hermes approvals are on, and the classic profile uses Hermes' own approval prompt instead.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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