compact-focus

A plugin that reviews information gathered before a context compaction and proposes how it should be grouped. Context compaction shortens a long AI conversation while preserving its useful details.

In plain words
What is it for?
Use it when preparing to run /compact, especially when you want to inspect or refine the proposed groupings first.
Why use it?
It helps reduce the risk of losing important context when a conversation becomes too long. It can also pause for confirmation or discussion before continuing with the shortened context.

Plugin for Claude Code

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.

Claude Code
/plugin marketplace add divadbaroon/claude-plugins
agentmods
npx agentmods add plugins/divadbaroon/claude-plugins/compact-focus
Clone the repo
git clone --depth 1 https://github.com/divadbaroon/claude-plugins

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

compact-focus 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 yesterday.

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.

compact-focus/.claude-plugin/plugin.json · 28 lines

What it actually says

{
  "name": "compact-focus",
  "displayName": "Compact Focus",
  "version": "0.22.3",
  "description": "Review source-grounded clusters, then confirm or chat-refine the exact draft before one bare /compact continues.",
  "author": {
    "name": "Hudson Mitchell-Pullman"
  },
  "homepage": "https://github.com/divadbaroon/claude-plugins/tree/main/compact-focus",
  "repository": "https://github.com/divadbaroon/claude-plugins",
  "license": "MIT",
  "keywords": [
    "compaction",
    "context",
    "hooks",
    "memory",
    "human-in-the-loop"
  ],
  "userConfig": {
    "background_analysis": {
      "type": "boolean",
      "title": "Background proposal analysis",
      "description": "Let a bounded Claude worker prepare richer groupings before compaction. Cold /compact remains instant when disabled or unfinished.",
      "default": true
    }
  }
}
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.

  1. yesterday First seen · 28 lines scan A 4f6fa576eed5

Subscribe to this mod's changes

compact-focus is a plugin published in the GitHub repository divadbaroon/claude-plugins (4 stars, last pushed yesterday), licensed MIT. 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 2026-08-31.