Andrey Markin
  • home
  • services
  • projects
  • blog
  • directory
    • Tool
    • Library
    • Repo
    • Article
    • XTweet
    • Guideline
    • Video
  • courses
  • resume
  • about
  • contact
  • meet

Mark Life Ltd

  1. Home
  2. Directory
  3. Memory View
Meet

Mark Life Ltd

BG208147965

HomeContactPrivacyLLM-friendlyBlog RSSDirectory RSS
  1. Directory
  2. memory-view
GuidelineAI CodingDev Toolsagentscliobservability

memory-view

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.

Added June 27, 2026
Visit guideline

Install it with:

npx skills add Mark-Life/agent-skills -g --skill memory-view

Then 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.

Related

  • session-reportClaude Code / Codex skill that generates a self-contained HTML report debugging what is in a session's context window and how every token is spent — context budget, retained thinking, the dumb-zone cutoff, loaded CLAUDE.md and skills, and full history.
  • It's Time To Rethink EverythingTheo Browne's CascadiaJS 2026 talk arguing that AI is a "new cloud moment" — just as the cloud removed the cost of provisioning servers, agents remove the cost of building, so the sacred rules of software (file systems, codebases, packages, git, deployment) are worth tearing down and rebuilding from first principles.
  • EveOpen-source agent framework from Vercel — define agents as directories of TypeScript and Markdown config and deploy them as standard Vercel projects.
  • FlueTypeScript framework for building durable AI agents and workflows with no vendor lock-in — write once, deploy anywhere, run on any LLM.