Confluence Page Viewer

npx confluence-cli

Arguments

• $ARGUMENTS[0]

  — Confluence page URL

• $ARGUMENTS[1]

  — (optional) Output directory for persisting the page content. Defaults to

  .implement-assets/confluence

implement

$ARGUMENTS[1]

.implement-assets/confluence

System Requirements

• Node.js and npm/npx available

• confluence-cli

  package (https://github.com/pchuri/confluence-cli) — invoked via

  npx confluence-cli

  to avoid asdf Node.js version conflicts

Execution

1. Pre-flight check: Run

   npx confluence-cli --help

   to verify the CLI works — if it fails, follow error handling in references/rules.md. Do NOT continue until the CLI is available. Auth errors are caught when the actual command runs.
2. Validate

   $ARGUMENTS[0]

   against references/rules.md
3. Run

   npx confluence-cli read $ARGUMENTS[0]

   via Bash
4. Format the output per references/output-format.md
5. Save output: Run

   mkdir -p $ARGUMENTS[1]

   via Bash, then save the full formatted output to

   $ARGUMENTS[1]/output.md

   using the Write tool. This ensures the complete output is persisted for the orchestrator to read.