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

How to approve or deny each agent tool call visually with Percho

Review every tool request in a dock and allow or block it before it runs.

Authorization notice. Percho is dual-use. Only use it on software, sites and systems you own or have explicit permission to test.

Who it is forA developer who lets a coding agent act on files or commands and wants a visible checkpoint before each action.

The problemAn agent running tools without a clear review step can change files or run commands you did not expect.

The outcomeEach tool call waits in a visual dock until you approve or deny it, with rules applied per tool.

What you need first

  • A desktop computer running macOS, Windows, or Linux (x64), or Node.js 22.19 or newer for running from source
  • Access to a model provider through a supported subscription login or an API key
  • For the shared-session use case, Pi CLI sessions stored in ~/.pi/agent/ on the same machine

Steps

  1. Open a project in Percho and start a session.
  2. Send a prompt that asks the agent to use a tool, such as reading or editing a file.
  3. When the tool call appears in the approval dock, read the requested action.
  4. Click approve or deny for that call.
  5. Adjust the per-tool rules so that routine calls follow your chosen policy.

Prompt for your agent

Using the repo Jaxton07/percho, start a session in <project-folder> and send a prompt that triggers one tool call. Report the tool name and the approval decision you made, and verify that the tool did not run before approval.

Caveat. Approval rules only cover the tool calls Percho sees, so review the per-turn diff sidebar for changes made during a turn.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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