PreCompact

PreCompact is a hook for Claude Code from Ruya-AI/cozempic. Its token cost is not measured, scanned A, original, MIT.

A pair of hooks that run before the agent's context is compacted, meaning the conversation history is about to be shortened.

In plain words
What is it for?
Creating a context checkpoint, flushing a transcript digest, and confirming that the context was saved.
Why use it?
They save a checkpoint and digest first, so important session information can be restored afterward.

Hook for Claude Code

One of 6 entries in settings.json — they are configured in one file and arrive together.

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.

agentmods
npx agentmods add hooks/ruya-ai/cozempic/pre-compact
Clone the repo
git clone --depth 1 https://github.com/Ruya-AI/cozempic

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.

agentmods badge for PreCompact

README.md
[![agentmods](https://agentmods.dev/badge/hooks/ruya-ai/cozempic/pre-compact.svg)](https://agentmods.dev/hooks/ruya-ai/cozempic/pre-compact)
Your own site
<a href="https://agentmods.dev/hooks/ruya-ai/cozempic/pre-compact"><img src="https://agentmods.dev/badge/hooks/ruya-ai/cozempic/pre-compact.svg" alt="Measured on agentmods" height="20"></a>
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

PreCompact 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 5d ago.

A static scan of the commands this hook runs, not an audit. A hook is shell that executes on your machine at the event it names, which is why every command in it is printed with what was found.

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.

.claude/settings.json · 22 lines

What it actually says

{
  "PreCompact": [
    {
      "matcher": "",
      "hooks": [
        {
          "type": "command",
          "command": "cozempic checkpoint 2>/dev/null || true"
        }
      ]
    },
    {
      "matcher": "",
      "hooks": [
        {
          "type": "command",
          "command": "export COZEMPIC_NO_AUTO_INIT=1; TRANSCRIPT=$(cat | PYTHONIOENCODING=utf-8 python3 -c \"import sys,json; print(json.load(sys.stdin).get('transcript_path',''))\" 2>/dev/null); { cozempic checkpoint 2>/dev/null || python3 -m cozempic checkpoint 2>/dev/null; } || true; { cozempic digest flush ${TRANSCRIPT:+--session \"$TRANSCRIPT\"} 2>/dev/null || python3 -m cozempic digest flush ${TRANSCRIPT:+--session \"$TRANSCRIPT\"} 2>/dev/null; } || true; echo 'Cozempic: context checkpointed' # cozempic-hook-schema=v14"
        }
      ]
    }
  ]
}
Same file

What else settings.json configures

This page is one entry in a file that holds 6. Installing the file brings all of them; each is measured and scanned on its own page.

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. 5d ago First seen · 22 lines scan A e2d6b6010e9a

Subscribe to this mod's changes

PreCompact is a hook published in the GitHub repository Ruya-AI/cozempic (379 stars, last pushed 2mo ago), licensed MIT. Its token cost is not measured: a hook is shell that never enters the context. 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.