Agent skill

Cozempic Session Guard

Starts a background daemon that watches a Claude Code session's size and prunes it before auto-compaction can discard context or agent-team state.

MITAuto-check passedAgent Workflows

Install Cozempic Session Guard

skills CLI

$ npx skills add Ruya-AI/cozempic --skill guard -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install Ruya-AI/cozempic guard --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/Ruya-AI/cozempic.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugin/skills/guard .claude/skills/guard && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "guard" agent skill from https://github.com/Ruya-AI/cozempic/tree/main/plugin/skills/guard into .claude/skills/guard/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "guard", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/Ruya-AI/cozempic/tree/main/plugin/skills/guard

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add Ruya-AI/cozempic --skill guard -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install Ruya-AI/cozempic guard --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Ruya-AI/cozempic.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugin/skills/guard .agents/skills/guard && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "guard" agent skill from https://github.com/Ruya-AI/cozempic/tree/main/plugin/skills/guard into .agents/skills/guard/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "guard", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add Ruya-AI/cozempic --skill guard -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install Ruya-AI/cozempic guard --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Ruya-AI/cozempic.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugin/skills/guard .cursor/skills/guard && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "guard" agent skill from https://github.com/Ruya-AI/cozempic/tree/main/plugin/skills/guard into .cursor/skills/guard/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "guard", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/Ruya-AI/cozempic.git --path plugin/skills/guard

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add Ruya-AI/cozempic --skill guard -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install Ruya-AI/cozempic guard --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Ruya-AI/cozempic.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugin/skills/guard .gemini/skills/guard && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "guard" agent skill from https://github.com/Ruya-AI/cozempic/tree/main/plugin/skills/guard into .gemini/skills/guard/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "guard", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install Ruya-AI/cozempic guard

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add Ruya-AI/cozempic --skill guard -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/Ruya-AI/cozempic.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugin/skills/guard .github/skills/guard && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "guard" agent skill from https://github.com/Ruya-AI/cozempic/tree/main/plugin/skills/guard into .github/skills/guard/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "guard", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add Ruya-AI/cozempic --skill guard -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install Ruya-AI/cozempic guard --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Ruya-AI/cozempic.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugin/skills/guard .opencode/skills/guard && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "guard" agent skill from https://github.com/Ruya-AI/cozempic/tree/main/plugin/skills/guard into .opencode/skills/guard/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "guard", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: guard
GitHub stars: 423
Token cost: ~434 tokens
SKILL.md length: 133 words
Files: 1
Skills in repo: 5
Repo updated: Jul 3, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Starts a background daemon that watches a Claude Code session's size and prunes it before auto-compaction can discard context or agent-team state.

Works in 3 steps: Checkpoints team state every 30 seconds → At 60% of threshold (30MB): applies… → At threshold (50MB): applies full…
Running agent teams that must not lose state to auto-compaction
SKILL.md covers Default (recommended), For agent teams, Options and Check status and stop
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

The skill launches the cozempic guard daemon with a hard size threshold, a prescription name and a check interval. By default it saves team state every 30 seconds, applies a gentle prune without a reload at 60% of the threshold (30MB), and at the threshold of 50MB applies the full prescription and reloads the session with team state preserved.

It matters most for sessions running agent teams, because without it auto-compaction can make the lead agent lose team state such as created teams, sent messages and tasks. Options set the hard and soft thresholds in MB, a token-based threshold, skipping the reload, turning off the file watcher and choosing the prescription. The daemon logs to files under /tmp, and the skill shows how to check whether it is running, read recent activity and stop it.

When your agent uses it

Running agent teams that must not lose state to auto-compaction
Keeping a long Claude Code session under a size limit
Checking whether the guard daemon is running or stopping it

Example prompts

“Start the cozempic guard for this session so compaction does not wipe my agent team.”
“Run the guard with a lower threshold and no automatic reload.”
“Check whether the cozempic guard is still running and show its recent log lines.”

Requirements

The cozempic CLI
A Claude Code session to protect
Pre-approved tools (allowed-tools): Bash(cozempic *)

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

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

What it can do on your machine

Read from SKILL.md and the folder at commit fd41e95. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
- Bash(cozempic *)
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Cozempic Session Guard loads about 434 tokens when it runs. Until then it costs about 85 tokens; SKILL.md has 133 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~85
When it runs · the whole SKILL.md, loaded when a task matches: ~434

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Ruya-AI/cozempic at commit fd41e95, republished under its MIT licence (© Ruya-AI). 133 words, ~434 tokens.

Download SKILL.mdSave it as .claude/skills/guard/SKILL.md (or your agent's skills folder).

name: guard
description: 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.
allowed-tools: Bash(cozempic *)
disable-model-invocation: true

Start the cozempic guard daemon for continuous session protection.

Default (recommended)

bash

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:

bash

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

Files

Just SKILL.md in plugin/skills/guard of Ruya-AI/cozempic.

Open the folder on GitHubat commit fd41e95

Compare with similar skills

Cozempic Session Guard next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Cozempic Session Guard compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Cozempic Session Guard this skillRuya-AI/cozempic	423	—	~434	Automated safety check: Pass	MIT	3 mo ago
Project Developmentguanyang/open-agent-hub	977	2 repos	~4.7k	Automated safety check: Pass	MIT	yesterday
Harness Engineering10xChengTu/harness-engineering	102	1 repos	~1k	Automated safety check: Pass	None	2 mo ago
Filesystem Contextguanyang/open-agent-hub	977	1 repos	~4k	Automated safety check: Pass	MIT	yesterday
Durable Session StateZaxbyHub/opencode-swarm	493	—	~896	Automated safety check: Pass	MIT	today
OpenRig Mental Model Primermvschwarz/openrig	6.2k	—	~4k	Automated safety check: Pass	Apache-2.0	today

Similar skills

Project Development
guanyang/open-agent-hub
This skill should be used for project-level decisions about LLM-powered systems: whether an LLM is the right primitive for the task at hand, the shape of a multi-stage batch or agent pipeline, token…
977 GitHub starsUsed in 2 repos~4.7k tokens
Agent WorkflowsAuto-check passed
Harness Engineering
10xChengTu/harness-engineering
Set up and improve harness engineering (AGENTS.md, docs/, lint rules, eval systems, project-level prompt engineering) for AI-agent-friendly codebases.
102 GitHub starsUsed in 1 repo~1k tokens
Agent WorkflowsAuto-check passed
Filesystem Context
guanyang/open-agent-hub
This skill should be used when agent work needs file-backed context: durable scratchpads, tool-output offloading, just-in-time discovery, cross-agent handoff files, filesystem memory, or cleanup…
977 GitHub starsUsed in 1 repo~4k tokens
Agent WorkflowsAuto-check passed
Durable Session State
ZaxbyHub/opencode-swarm
Keeps plans, decisions, evidence and reviewer verdicts in small files so long multi-phase tasks survive context compaction and session resumes.
493 GitHub stars~896 tokensUpdated today
Agent WorkflowsAuto-check passed
OpenRig Mental Model Primer
mvschwarz/openrig
Gives a fast orientation to OpenRig for an agent that just booted into a seat, covering rigs, topologies, layers and where context and skills come from.
6.2k GitHub stars~4k tokensUpdated today
Agent WorkflowsAuto-check passed
Coordinated Agent Teams
jacob-dietle/context-os
This skill should be used when decomposing a spec into a multi-agent implementation plan with dependency ordering, parallelism decisions, contract testing, and verification strategy.
111 GitHub stars~4.2k tokensUpdated 1 mo ago
Agent WorkflowsAuto-check passed

Questions about Cozempic Session Guard

What does Cozempic Session Guard do?

Starts a background daemon that watches a Claude Code session's size and prunes it before auto-compaction can discard context or agent-team state. The skill launches the cozempic guard daemon with a hard size threshold, a prescription name and a check interval. By default it saves team state every 30 seconds, applies a gentle prune without a reload at 60% of the threshold (30MB), and at the threshold of 50MB applies the full prescription and reloads the session with team state preserved.

When should I use Cozempic Session Guard?

Cozempic Session Guard fits situations like: running agent teams that must not lose state to auto-compaction; keeping a long Claude Code session under a size limit; checking whether the guard daemon is running or stopping it.

How do I install Cozempic Session Guard in Claude Code?

Run `npx skills add Ruya-AI/cozempic --skill guard -a claude-code`. Or copy the skill folder (plugin/skills/guard in Ruya-AI/cozempic) into .claude/skills/guard in your project. Claude Code loads it when a task matches its description.

How do I install Cozempic Session Guard in Codex?

Run `npx skills add Ruya-AI/cozempic --skill guard -a codex`. Or copy the skill folder (plugin/skills/guard in Ruya-AI/cozempic) into .agents/skills/guard in your project. Codex loads it when a task matches its description.

Can I use Cozempic Session Guard in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Ruya-AI/cozempic --skill guard -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/guard, .gemini/skills/guard, .github/skills/guard and .opencode/skills/guard in your project.

What does Cozempic Session Guard need to run?

SKILL.md names no scripts, command-line tools or credentials: Cozempic Session Guard is instructions for the agent only. Our summary lists: The cozempic CLI; A Claude Code session to protect. Its frontmatter pre-approves these tools: Bash(cozempic *).

Does Cozempic Session Guard access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Cozempic Session Guard safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Cozempic Session Guard use?

Cozempic Session Guard is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Cozempic Session Guard use?

About 434 tokens (SKILL.md is roughly 1.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Cozempic Session Guard?

Skills that share tags, products or a category with Cozempic Session Guard: Project Development (guanyang/open-agent-hub, 977 stars), Harness Engineering (10xChengTu/harness-engineering, 102 stars), Filesystem Context (guanyang/open-agent-hub, 977 stars) and Durable Session State (ZaxbyHub/opencode-swarm, 493 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Cozempic Session Guard?

Ruya-AI (a GitHub organization) maintains it in Ruya-AI/cozempic, which has 423 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on July 3, 2026.

Source: Ruya-AI/cozempic on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Cozempic Session Guard

Install Cozempic Session Guard

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Default (recommended)

For agent teams

Options

Check status and stop

Files

Compare with similar skills

Similar skills

Project Development

Harness Engineering

Filesystem Context

Durable Session State

OpenRig Mental Model Primer

Coordinated Agent Teams

More from Ruya-AI/cozempic

Cozempic Session Pruning

Cozempic Doctor

Diagnose

Session Reload and Prune

Questions about Cozempic Session Guard

Install Cozempic Session Guard

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Default (recommended)

For agent teams

Options

Check status and stop

Files

Compare with similar skills

Similar skills

More from Ruya-AI/cozempic

Related

Questions about Cozempic Session Guard