What is claude-magic-compact?

A Claude Code plugin that compresses conversation context without intentionally losing information.

Use it during extended Claude Code sessions where accumulated context needs to be reduced while preserving technical details.

It helps keep long coding sessions manageable when the conversation becomes too large to work with comfortably.

claude-magic-compact — Plugin for Claude Code by aerovato

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/aerovato/magic-compact

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/aerovato/magic-compact/claude-code-plugin/github.svg)](https://agentmods.dev/plugins/aerovato/magic-compact/claude-code-plugin)

Your own site

<a href="https://agentmods.dev/plugins/aerovato/magic-compact/claude-code-plugin"><img src="https://agentmods.dev/badge/plugins/aerovato/magic-compact/claude-code-plugin/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/aerovato/magic-compact/claude-code-plugin"><img src="https://agentmods.dev/badge/plugins/aerovato/magic-compact/claude-code-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 1 skill, 1 hook, 1 MCP server cost 10 tokens a session between them.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

claude-magic-compact scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 29d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

packages/claude-code-plugin/.claude-plugin/plugin.json · 11 lines

What it actually says

{
  "name": "claude-magic-compact",
  "version": "1.4.0",
  "description": "Lossless context compression for Claude Code.",
  "author": {
    "name": "kevinMEH"
  },
  "homepage": "https://github.com/aerovato/magic-compact#readme",
  "repository": "https://github.com/aerovato/magic-compact"
}

Contents

What it installs

The manifest is a name and a version. 1 skill, 1 hook, 1 MCP server travel with it, and installing the plugin installs all of them — 10 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

29d ago Changed de51a128afc3
1mo ago First seen · 11 lines scan A b4eb54db8ebe

Subscribe to this mod's changes

claude-magic-compact is a plugin published in the GitHub repository aerovato/magic-compact (173 stars, last pushed 29d ago), licensed BSD-3-Clause. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude Code Memory and context anthropic chatgpt claude claude-code-plugin claude-skills

clean-context

Keeps a project's noise out of Claude's default context: audit-context measures where the budget is going, ignore-setup applies a managed .ignore, a Glob setting, and a short read-deny list for secrets, leaving every excluded path readable on purpose.

Malo-T/claude-toolbelt · not measured

compact-nudge

Suggests /compact or /clear when the context grows past a threshold or the prompt cache has gone cold, since every request re-reads the whole context.

Malo-T/claude-toolbelt · not measured

cross-code-organizer

Inspect and organize Claude Code memories, skills, MCP servers, hooks, and project context from a local dashboard.

mcpware/cross-code-organizer · not measured

recall

Durable, fully-local project memory for Claude Code. Logs every session to .recall/history.md and condenses it into .recall/context.md with a local Python summarizer (TF-IDF + TextRank) — no API key, no external model, nothing leaves your machine. New sessions resume from the saved context.

raiyanyahya/recall · not measured

claude-code-hermit

Your own local Claude Tag, in the Claude app, Discord, Telegram, or a custom Claude Code channel.

gtapps/claude-code-hermit · not measured

sre-bot

SRE triage assistant for plain-English production health and Kubernetes questions in Slack. One pinned upstream Kubernetes MCP connector exposes the core toolset: reads execute immediately, six mutations require a fresh human approval, and unmatched tools fail closed. Kubernetes RBAC limits writes to disposable…

curie-eng/curie · not measured