Skip to content
Agentmart
Submit a tool

Alternatives to how-it-works

how-it-works is an agent skill by thedotmack: Explain how claude-mem captures observations, when memory injection kicks in, and where data lives. If it doesn't fit your setup, these 12 agent skills cover similar ground. They are ordered by how closely they match how-it-works and by our rank, which weighs adoption, freshness and documentation; money never changes the order. memory-poisoning-detection leads the list (published by the vendor). 5 of them are published by the company behind the product. Each entry shows data reasons to switch, and you can open a side-by-side comparison with how-it-works.

Updated Oct 26, 2026 · Built from catalog data; how we rank and grade

You're replacing

how-it-works

Explain how claude-mem captures observations, when memory injection kicks in, and where data lives.

12 alternatives

Ordered by how closely each matches how-it-works (shared product, category or stated alternative) and by rank.

  1. 1

    Detect persistent instruction injection or long-term memory poisoning.

    • Published by the vendor

    ★ 7.1KLast active Oct 22, 2026Claude Code, Claude apps, Codex, Cursor +6

  2. 2
    caveman-compress

    JuliusBrussee

    Compress a memory file such as CLAUDE.md or a todo list into caveman format to save input tokens, keeping a readable backup.

    • Supports Python

    ★ 114.8KLast active Oct 17, 2026Claude Code, Claude apps, Codex, Cursor +6

  3. 3
    mem-search

    thedotmack

    Use this when the user asks to search memory, "did we already solve this?", "how did we do X last time?", or wants work from previous sessions.

    • Repository has 102.8K stars
    • Active in the last 30 days

    ★ 102.8KLast active Oct 23, 2026Claude Code, Claude apps, Codex, Cursor +6

  4. 4
    remember

    langchain-aiOfficial

    Review the current conversation and capture valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback —…

    • Published by the vendor

    ★ 30.6KLast active Oct 23, 2026Claude Code, Claude apps, Codex, Cursor +6

  5. 5
    coding-prefs

    langchain-aiOfficial

    Read the user's coding preferences from /memory/coding-prefs.md before making non-trivial style decisions, and append new preferences when the user gives…

    • Published by the vendor

    ★ 30.6KLast active Oct 23, 2026Claude Code, Claude apps, Codex, Cursor +6

  6. 6
    apache-arrow

    terminal-skills

    Expert guidance for Apache Arrow, the cross-language columnar memory format for analytics workloads.

    • Active in the last 30 days
    • Open source (Apache-2.0)

    ★ 195Last active Sep 28, 2026Claude Code, Claude apps, Codex, Cursor +6

  7. 7

    APK/EXE/二进制:UniApp/DCloud/Flutter逆向,证书固定绕过,导出组件,内存破坏exploit链,IoT固件。Use when reversing APK/EXE, UniApp/Flutter, native .so, or memory-corruption exploits.

    • Repository has 8K stars
    • Active in the last 30 days

    ★ 8KLast active Oct 16, 2026Claude Code, Claude apps, Codex, Cursor +6

  8. 8

    Detect persistent-memory poisoning and RAG/knowledge-base contamination via dialogue testing.

    • Published by the vendor

    ★ 7.1KLast active Oct 22, 2026Claude Code, Claude apps, Codex, Cursor +6

  9. 9
    wiz-security-context

    henperezOfficial

    Automatically load this skill when investigating an operational anomaly on a cloud resource - CPU or memory spikes, latency, elevated error rates, unexpected…

    • Published by the vendor

    ★ 116Last active Oct 21, 2026Claude Code, Claude apps, Codex, Cursor +6

  10. 10

    Diagnose and clear CPU, memory, and disk contention on the maintainer's dev host.

    • Supports Python

    ★ 4.4KLast active Oct 19, 2026Claude Code, Claude apps, Codex, Cursor +6

  11. 11
    engram-memory

    Gentleman-Programming

    ALWAYS ACTIVE — Persistent memory protocol.

    • Repository has 7.6K stars
    • Active in the last 30 days

    ★ 7.6KLast active Oct 23, 2026Claude Code, Claude apps, Codex, Cursor +6

  12. 12
    neat-freak

    KKKKhazix

    Knowledge and governance closeout: reconcile project docs, rule files (CLAUDE.md/AGENTS.md), authorized agent memory, and workspace residue with what the code…

    • Supports TypeScript and JavaScript

    ★ 21.6KLast active Jul 19, 2026Claude Code, Claude apps, Codex, Cursor +6