AI agent setup

[sakerhetspartner]

Adds a custom "execution agent" to enforce a strict reasoning, planning, action, and reflection workflow, as requested by the user.

The user explicitly defined a general-purpose execution agent with specific operating principles and a required response format. This agent is implemented as a .github/agents/ custom agent for the Copilot CLI to ensure all interactions adhere to these rules, promoting structured and reliable task completion.

---

 

---

Note

Adds a new execution agent with strict plan–act–evaluate workflow and updates README with usage instructions.

• Agents:
  • Add /.github/agents/execution-agent.agent.md defining a general-purpose execution agent with explicit operating principles and required response format (🧠 Reasoning, 🗂️ Plan, ⚙️ Action, 🔁 Reflection).
• Docs:
  • Update README.md with a new section on using the custom execution-agent, including workflow description and example CLI commands (copilot, /agent execution-agent, and non-interactive --agent usage).

^{Written by Cursor Bugbot for commit c6962e5. This will update automatically on new commits. Configure here.}

[cursor]

Cursor Agent can help with this pull request. Just @cursor in comments and I'll start working on changes in this branch.
_{Learn more about Cursor Agents}