How claude-mem works (memory plugin explainer)
Explains the claude-mem plugin — how observations are captured, when memory injection kicks in, where data lives
- What
- Explains the claude-mem plugin — how observations are captured, when memory injection kicks in, where data lives
- Cost
- Free
- Needs
- nothing for this explainer — to get the memory capability itself, install the claude-mem plugin separately (memory is local to one machine)
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — @thedotmack's explainer skill for the claude-mem plugin: how every Read/Edit/Bash becomes a compressed observation, how observations get summarized at session end, when memory injection starts (second session in a project — the first seeds memory), where everything lives (`~/.claude-mem`, SQLite + vector index, machine-local), and the privacy boundary (nothing leaves the machine except calls to the AI provider configured for compression; local installs contact cmem.ai at signup, sharing your email and an optional note if you provide them when the installer asks, plus a numbers-only usage summary (observation counts and token totals; no prompts, paths, or project names) when setup creates a sign-in link). By @thedotmack, listed here with credit to its creator. Honest caveats: this is an explainer doc for the claude-mem plugin — install the actual claude-mem plugin to get the memory capability itself; memory is local to one machine, not synced. Apache-2.0 licensed. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Quick answer
How claude-mem works is a free Muse skill explainer for the claude-mem plugin, describing observation capture, memory injection timing, and data location. Every Read, Edit and Bash becomes a compressed observation, summarized at session end, memory injection starts on a project's second session since the first seeds memory, and everything lives machine-local in claude-mem storage, SQLite and a vector index.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 18, 2026📌 Pinned version: commit 1bccc41Step 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: nothing for this explainer — to get the memory capability itself, install the claude-mem plugin separately (memory is local to one machine) Install "How claude-mem works (memory plugin explainer)" for me. It gives the agent @thedotmack's explanation of the claude-mem plugin: how observations are captured from Read/Edit/Bash, summarized at session end, auto-injected into future sessions, where data lives (~/.claude-mem, machine-local), and the privacy boundary — useful when the user asks "how does claude-mem work?". Apache-2.0 licensed. Repository: https://raw.githubusercontent.com/thedotmack/claude-mem/1bccc41ed44a70cdc4cf8674db0c1e151b97da32/plugin/skills/how-it-works/SKILL.md Pinned version: install the code at commit 1bccc41ed44a70cdc4cf8674db0c1e151b97da32 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "how-it-works". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. nothing for the explainer — install the claude-mem plugin itself if you want the memory capability). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- 1bccc41 · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 18, 2026 · Observed during the install test: registry.npmjs.org
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.