how-it-works SKILL.md skillA

how-it-works from thedotmack/claude-mem is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add thedotmack/claude-mem/how-it-works@git:20260926.48f5739

Pins git:20260926.48f5739 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
thedotmack/claude-mem
Path
plugin/skills/how-it-works/SKILL.md
Versions recorded
2
Latest version
git:20260926.48f5739, committed Sep 26, 2026
First version recorded
May 2, 2026
Size
1,342 bytes
Repository stars
113,797
License
Apache-2.0

Explain how claude-mem captures observations, when memory injection kicks in, and where data lives. Use when the user asks "how does claude-mem work?" or "what is this thing doing?".

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# How claude-mem works

## What it does

Every Read, Edit, and Bash that Claude makes turns into a compressed observation. Observations get summarized at session end. Relevant ones get auto-injected into future prompts so the next session starts with context from the last one — no re-explaining the codebase, no re-discovering decisions.

## When it kicks in

Memory injection starts on your second session in a project.

The first session in a fresh project seeds memory; subsequent sessions receive auto-injected context for relevant past work. Run `/learn-codebase` if you want to front-load the entire repo into memory in a single pass (~5 minutes, optional).

## Where data lives

Everything stays in ~/.claude-mem on this machine.

Nothing leaves your machine except calls to whichever AI provider you configured for compression (Claude / OpenRouter / Gemini). Local installs contact cmem.ai once, at signup, to create the sign-in link; nothing else is sent to cmem.ai. The SQLite database, vector index, logs, and settings all live under that directory and are removed cleanly on `npx claude-mem uninstall`.

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add thedotmack/claude-mem/how-it-works@sha256:465a3433dce7c26b

The line at the top of this page pins the label git:20260926.48f5739, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_d3gp5sqmsl3rjaga.svg)](https://markdownregistry.com/a/art_d3gp5sqmsl3rjaga)

7 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between May 2, 2026 and Sep 26, 2026, about one every 147 days.

versioncommittedcommitsizeaudit
git:20260926.48f5739 latest2026-09-26 48f5739 1,342 BA view · diff
git:20260502.9e297302026-05-02 9e29730 1,233 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (1342 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

thedotmack/claude-mem · 113,797 stars · license Apache-2.0 · pushed 2026-11-06 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_d3gp5sqmsl3rjaga
GET https://markdownregistry.com/api/v1/resolve?ref=thedotmack/claude-mem/how-it-works
GET https://markdownregistry.com/api/v1/blob/465a3433dce7c26b32c80ce8da68f136e2e9c6914273e88f08f02b2c95ab1b3b

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from thedotmack/claude-mem

CLAUDE.md@.claude CLAUDE.md file
thedotmack/claude-mem · .claude/CLAUDE.md
git:20261101.f8bdd1a · audit A · 113,797 stars
Agent Cost Report SKILL.md skill
thedotmack/claude-mem · claude-mem-cursor/skills/agent-cost-report/SKILL.md · Believable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from…
git:20261005.57744a0 · audit A · 113,797 stars
claude-mem-install SKILL.md skill
thedotmack/claude-mem · claude-mem-cursor/skills/install/SKILL.md · Use this when setting up claude-mem on Cursor: local or remote worker, local host-login observer or remote cmem.ai…
git:20260902.1c7aaff · audit A · 113,797 stars
mem-search SKILL.md skill
thedotmack/claude-mem · claude-mem-cursor/skills/mem-search/SKILL.md · Use this when the user asks to search memory, "did we already solve this?", "how did we do X last time?", or wants work…
git:20260907.fd0ecf0 · audit A · 113,797 stars
Agent Cost Report SKILL.md skill
thedotmack/claude-mem · claude-mem-grok-bot/skills/agent-cost-report/SKILL.md · Believable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from…
git:20261005.57744a0 · audit A · 113,797 stars
host-observer SKILL.md skill
thedotmack/claude-mem · claude-mem-grok-bot/skills/host-observer/SKILL.md · Use this when fulfilling claude-mem observer jobs on Grok Bot: reply only skip_summary or one full observation XML…
git:20260902.1c7aaff · audit A · 113,797 stars
claude-mem-install SKILL.md skill
thedotmack/claude-mem · claude-mem-grok-bot/skills/install/SKILL.md · Use this when setting up claude-mem on Grok Bot: local worker plus CMEM Pro observer (default), optional host-login…
git:20260916.96f04a9 · audit A · 113,797 stars
mem-search SKILL.md skill
thedotmack/claude-mem · claude-mem-grok-bot/skills/mem-search/SKILL.md · Use this when the user asks to search memory, "did we already solve this?", "how did we do X last time?", or wants work…
git:20260916.96f04a9 · audit A · 113,797 stars
Agent Cost Report SKILL.md skill
thedotmack/claude-mem · cowork/skills/agent-cost-report/SKILL.md · Believable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from…
git:20261005.57744a0 · audit A · 113,797 stars
mem-search SKILL.md skill
thedotmack/claude-mem · cowork/skills/mem-search/SKILL.md · This skill should be used when the user asks to "search memory", "what do you remember about X", "check claude-mem"…
v0.1.0 · audit A · 113,797 stars
mem-setup SKILL.md skill
thedotmack/claude-mem · cowork/skills/mem-setup/SKILL.md · This skill should be used when the user asks to "set up claude-mem", "pair claude-mem", "connect cmem", "add my cmem…
v0.1.0 · audit A · 113,797 stars
openclaw SKILL.md skill
thedotmack/claude-mem · openclaw/SKILL.md
git:20261005.5dcf449 · audit C · 113,797 stars

Every file in thedotmack/claude-mem

Browse by kind, by grade A, or by owner.