No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by aerovato · Claude Skill · ★ 171
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is magic-compact safe to install? View the security audit →
Magic Compact English | 中文 Lossless context compression for OpenCode and Claude Code. Why OpenCode and Claude Code's built-in compaction replaces an entire conversation with one summary blob. The user messages, the assistant's reasoning, tool calls, design decisions, and workflow are all flattened into a generic template (Goal, Progress, Key Decisions...). The agent wakes up with amnesia, forced to reconstruct its working state from an abstraction that captured a fraction of what mattered. Magic Compact takes a different approach: preserve the conversation skeleton, condense each old assistant turn into its own summary, prune bulky tool I/O, and keep everything retrievable. The agent retains its memory of what it did, why, and what comes next. How Instead of collapsing an entire session into a single generic summary, Magic Compact replaces old assistant turns with high-fidelity summaries while leaving user messages and tool calls in place. The assistant's thought process, decisions, and actions remain in context along with all your commands while unnecessary bloat is stripped away. Long tool calls are aggressively pruned but can be retrieved via a custom tool.
| Stars | 171 |
| Forks | 16 |
| Language | TypeScript |
| Category | Claude Skill |
| License | BSD-3-Clause |
| Quality Score | 72.5643695914193/100 |
| Open Issues | 3 |
| Last Updated | 2026-09-17 |
| Created | 2026-07-04 |
| Platforms | claude-code, codex, gemini, node |
| Est. Tokens | ~16k |
These tools work well together with magic-compact for enhanced workflows:
Looking for a magic-compact alternative? If you're comparing magic-compact with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
OpenCode plugin to use your Claude Max/Pro subscription with OpenCode via Meridian
DevOps discipline for AI coding agents: shape the work, track it as a graph, and get each change judged by a c
🏛 [UNDER CONSTRUCTION] A (roman) claude plugin marketplace
Debug your AI agents
Shell and coding agent on mcp clients
Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server
Explore other popular claude skill tools:
magic-compact is Lossless context compression plugin for Claude Code & OpenCode.. It is categorized as a Claude Skill with 171 GitHub stars.
magic-compact is primarily written in TypeScript. It covers topics such as anthropic, chatgpt, claude.
You can find installation instructions and usage details in the magic-compact GitHub repository at github.com/aerovato/magic-compact. The project has 171 stars and 16 forks, indicating an active community.
magic-compact is released under the BSD-3-Clause license, making it free to use and modify according to the license terms.
The top alternatives to magic-compact on Agent Skills Hub include opencode-with-claude, agentops, claude-emporium. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: