Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Claude Mem

ASecurity

Persistent memory system - automatically activates every session. Captures session context, maintains continuity across conversations, tracks what was worked on, and injects relevant history into new sessions.

3 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsgobash

Works with

claude code

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add satishkc7/claude-config --skill claude-mem --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Claude Mem?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Claude Mem
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/satishkc7-claude-mem/badge)](https://www.skillsdirectory.com/skills/satishkc7-claude-mem)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: claude-mem
description: "Persistent memory system - automatically activates every session. Captures session context, maintains continuity across conversations, tracks what was worked on, and injects relevant history into new sessions."
---

# Claude-Mem: Persistent Session Memory

Automatically maintain continuity across Claude Code sessions. Every session start: read prior context. Every session end: save what was done.

## Auto-Activation (Every Session)

On every session start, do these steps silently without announcing:

1. **Read last context** - check `~/.claude-mem/last-context.md` for prior session state
2. **Read recent sessions** - scan `~/.claude-mem/sessions/` for recent daily logs (last 3 days)
3. **Read memory index** - check `~/.claude/projects/-Users-satishkc/memory/MEMORY.md` for persistent memories
4. **Orient silently** - understand what the user was last working on, what's pending, what context carries forward

Do NOT announce this process. Just be aware of the context. If the user starts a conversation related to prior work, you already know the background.

## Session Context Capture

At the START of meaningful work (not casual questions), silently run:

```bash
~/.claude-mem/capture.sh
```

Then read the generated `~/.claude-mem/last-context.md` to understand current state.

## Session Summary Save

When the user explicitly ends a session or says goodbye, or when significant work is completed, run:

```bash
~/.claude-mem/summarize.sh
```

This appends to the daily session log at `~/.claude-mem/sessions/YYYY-MM-DD.md`.

## What to Track

**Always note silently:**
- Which project/directory is active
- What task was being worked on
- Key decisions made
- Blockers encountered
- Files modified
- What's left to do

**Save to memory (via memory system) when:**
- User shares new project context, preferences, or corrections
- A significant architectural decision is made
- A new workflow or tool is established
- Something surprising or non-obvious is learned

## Context Injection Rules

**DO:**
- Reference prior session context naturally when relevant
- Pick up where the user left off without asking "what were you working on?"
- Connect current work to past context silently

**DON'T:**
- Announce "I'm loading your session history"
- Dump prior context unprompted
- Reference old context that's clearly stale
- Slow down the session with memory operations

## Privacy

Content wrapped in `<private>` tags is never persisted or referenced in future sessions.

## Storage Layout

```
~/.claude-mem/
  last-context.md          # Current session context (auto-generated)
  capture.sh               # Session start script
  summarize.sh             # Session end script
  sessions/
    2026-05-03.md          # Daily session logs
    2026-05-02.md
    ...
```

## Integration with Memory System

Claude-mem handles **short-term session continuity** (what happened today/this week).
The memory system at `~/.claude/projects/-Users-satishkc/memory/` handles **long-term knowledge** (user preferences, project details, feedback).

Both work together: claude-mem provides session context, memory provides project/user context.

Attribution

satishkc7satishkc7
View sourceMore from satishkc7 →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →