Claude Code / Codex skill that reads a project's auto-memory vault and generates a self-contained HTML explorer to visualize what the agent has remembered — MEMORY.md plus topic files — without editing or managing it.
Install it with:
npx skills add Mark-Life/agent-skills -g --skill memory-viewThen run /memory-view to open a cross-project explorer of everything Claude Code has remembered on this machine, or /memory-view [project] to scope it to one repo — "show me my Claude memory", "what does the agent remember about this project". It reads the per-project memory vault at ~/.claude/projects/<slug>/memory/: the always-loaded MEMORY.md index plus the topic files (markdown + YAML frontmatter, cross-linked via [[wikilinks]]), and renders a single self-contained HTML report it opens in your browser.
The report is built to debug what memory the agent actually sees: a budget gauge for MEMORY.md showing fill against the 200-line / 25 KB cliff — with anything below the fold greyed out and marked "INVISIBLE TO CLAUDE" — a type donut (user/feedback/project/reference), a sortable/searchable browse table you can expand row-by-row, an index-vs-files diff that surfaces orphaned and dangling entries, and a link graph of the wikilinks between memories.
Like its sibling session-report, it's a zero-dependency script rather than a prompt — the agent just runs it, so it's near-instant and costs no tokens. It detects whether Node or Bun is available and the model's role is strictly to run the script and open the report; it never reads, edits, or curates memory. The HTML is self-contained (no network, no CDN) with best-effort secret redaction on by default, so it's safe to open — though it still warns you to review before sharing, since the bodies are embedded.