01 · Brief the agent
Copy one prompt. Keep the full context.
Paste this into Claude, Codex, Cursor, ChatGPT, or another coding agent. It already includes the domain, the evidence to inspect, the expected output, and the approval boundary. If this is your first run, complete the one-time setup first; your agent can handle those commands too.
02 · Review the run
Know what happens before you paste.
The agent follows this sequence and reports the evidence in plain English. Any step that sends, uploads, or changes something waits for your explicit approval.
- 01
Check eligibility
Run
vdr sites:monitor --dailyto confirm owner-scoped monitoring eligibility. - 02
Track movement
Run
vdr trackto summarize whether authority is improving. - 03
Export
Run
vdr sites:exportwhen the evidence feeds a dashboard, script, or report. - 04
Explain
Run
vdr explainto turn the latest movement into a plain-English operating note.
03 · Inspect the commands
Nothing hidden behind the prompt.
These are the commands the prompt asks the agent to run. Copy the whole chain or execute it yourself. Read-only analysis runs immediately; consequential actions keep their approval gate.
# 1. Confirm owner-scoped monitoring eligibilityvdr sites:monitor yourwebsite.com --daily # 2. Summarize whether authority is improvingvdr track yourwebsite.com # 3. Export evidence for dashboards or client reportingvdr sites:export yourwebsite.com # 4. Explain the latest movement in plain Englishvdr explain yourwebsite.comNext job
