mcpbeat

Guard

ruya-ai/guard

> Protect Claude Code sessions from context overflow by running a background daemon that monitors session size and auto-prunes before compaction hits. Use when the user says "guard", "protect session", "context getting long", "prevent compaction", "session management", or is running agent teams that need continuous context protection.

436 tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
364
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository 
npx skills add https://github.com/Ruya-AI/cozempic --skill guard

The instruction itself

4 sections, as written by the author

Start the cozempic guard daemon for continuous session protection.

Default (recommended)

cozempic guard --daemon --threshold 50 -rx standard --interval 30

This runs in the background and:

  • Checkpoints team state every 30 seconds
  • At 60% of threshold (30MB): applies gentle prune, no reload
  • At threshold (50MB): applies full prescription + auto-reload with team state preserved

For agent teams

Guard mode is essential for sessions running agent teams. Without it, auto-compaction triggers and the lead agent loses team state (TeamCreate, SendMessage, tasks are discarded).

Options

  • --threshold N — hard threshold in MB (default: 50)
  • --soft-threshold N — soft threshold in MB (default: 60% of hard)
  • --threshold-tokens N — hard threshold in tokens (fires whichever hits first)
  • --no-reload — prune without restarting Claude
  • --no-reactive — disable kqueue/polling file watcher
  • -rx NAME — prescription at hard threshold (default: standard)

Check status and stop

The daemon writes to /tmp/cozempic_guard_*.log. Check with:

ls /tmp/cozempic_guard_*.pid 2>/dev/null        # is it running?
tail -20 /tmp/cozempic_guard_*.log 2>/dev/null   # recent activity
kill "$(cat /tmp/cozempic_guard_*.pid)"           # stop it

How to use it

Copy the folder

Take ruya-ai/guard from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.