Is the Claude Memory Kit skill free?

Yes. The skill itself is free from awrshift/claude-memory-kit. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Claude Memory Kit SkillProof Score?

8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 4/5.

How do I install Claude Memory Kit?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Claude Memory Kit with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Claude Memory Kit

Persistent layered memory for Claude Code, with a /close-session audit ritual

by awrshift · awrshift/claude-memory-kit

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 8.4/10
Tested: Jul 20, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Jul 30, 2026 · e62d571

⚠ This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (repo unreachable/deleted). The test below is what we measured on Jul 20, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.

Ran the bundled SessionStart hook live and it emits valid Claude Code hook JSON with real memory-health stats (11/180 lines, 0.5/32 KB, max-line 68/3000) plus the latest handoff and knowledge index, and the /close-session audit correctly treats a pattern seen on 3+ distinct dates as a promotion candidate, which a plain 'save my notes' baseline never does. Real friction: this is a whole project scaffold, so a standard copy into ~/.claude/skills leaves the hooks dormant, you must adopt its settings.json hooks (clone-as-project) to get the automation; zero external dependencies as claimed, though the stale-ref detector ran but missed a planted broken path so its regex is conservative.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 7/10
Docs & honesty 4/5

What Claude Memory Kit does

A zero-dependency memory scaffold for Claude Code: a size-capped hot cache (MEMORY.md), per-session handoffs, topical knowledge articles, and canonical rules, wired to SessionStart/Stop/PreCompact hooks. The /close-session ritual audits dated patterns, proposes promotions for anything seen on 3+ distinct dates, refreshes the header, and writes a handoff. Triggers on persistent-memory, context-continuity, and end-of-session wrap-up requests.

How to install Claude Memory Kit

Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.

Commands — how to trigger Claude Memory Kit

/claude-memory-kit Persistent layered memory for Claude Code, with a /close-session audit ritual

It also activates on plain-language prompts like these:

Set up persistent memory for Claude Code across all my sessions
Run the close-session ritual and audit what patterns should be promoted
Write a handoff note summarizing everything we did this session

Frequently asked questions

Is the Claude Memory Kit skill free?: Yes. The skill itself is free from awrshift/claude-memory-kit. SkillProof publishes the install command and an independent test verdict at no cost.
Does Claude Memory Kit work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 20, 2026. Verdict: Works with setup. Ran the bundled SessionStart hook live and it emits valid Claude Code hook JSON with real memory-health stats (11/180 lines, 0.5/32 KB, max-line 68/3000) plus the latest handoff and knowledge index, and the /close-session audit correctly treats a pattern seen on 3+ distinct dates as a promotion candidate, which a plain 'save my notes' baseline never does. Real friction: this is a whole project scaffold, so a standard copy into ~/.claude/skills leaves the hooks dormant, you must adopt its settings.json hooks (clone-as-project) to get the automation; zero external dependencies as claimed, though the stale-ref detector ran but missed a planted broken path so its regex is conservative.
What is the Claude Memory Kit SkillProof Score?: 8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 4/5.
How do I install Claude Memory Kit?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Claude Memory Kit with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.