export-monitor

export-monitor is a command for Claude Code from jmanhype/claude-code-plugin-marketplace. It costs 0 tokens per session (886 once invoked), scanned A, original, MIT.

A command that packages an optimized AI monitor as a reusable Claude Skill, which is a portable workflow that can be loaded and shared across projects. It can export the monitor configuration and optionally its fine-tuned weights.

In plain words
What is it for?
Use it to export a monitor model to a named skill file, with an option to include fine-tuned model weights.
Why use it?
It makes a trained monitor easier to reuse in other Claude Code sessions and projects. The exported skill can also be version controlled and combined with other skills.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Claude Code.

Part of the code-safety-monitor plugin — 8 commands, 6 agents shipped together

Good fit Use it to export a monitor model to a named skill file, with an option to include fine-tuned model weights.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/jmanhype/claude-code-plugin-marketplace/export-monitor
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.

Clone the repo
git clone --depth 1 https://github.com/jmanhype/claude-code-plugin-marketplace

Made for: Claude Code.

Or install code-safety-monitor, the plugin that ships this one along with the rest of its 8 commands, 6 agents.

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 export-monitor

README.md
[![agentmods](https://agentmods.dev/badge/commands/jmanhype/claude-code-plugin-marketplace/export-monitor/github.svg)](https://agentmods.dev/commands/jmanhype/claude-code-plugin-marketplace/export-monitor)
Your own site
<a href="https://agentmods.dev/commands/jmanhype/claude-code-plugin-marketplace/export-monitor"><img src="https://agentmods.dev/badge/commands/jmanhype/claude-code-plugin-marketplace/export-monitor/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for export-monitor

Your own site · 80×15
<a href="https://agentmods.dev/commands/jmanhype/claude-code-plugin-marketplace/export-monitor"><img src="https://agentmods.dev/badge/commands/jmanhype/claude-code-plugin-marketplace/export-monitor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 886 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00886
Opus 5 $0.00000 $0.00443
Sonnet 5 $0.00000 $0.00177
Haiku 4.5 $0.00000 $0.00089

Measured 11d ago against content hash 90cbfb8b184e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

export-monitor 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 11d ago.

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.

plugins/code-safety-monitor/.claude/commands/export-monitor.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Export Monitor Command

Export the optimized monitor as a reusable Claude Skill for integration with other projects.

Usage

/export-monitor --model models/gepa_optimized.json --output monitors/safety-monitor.skill [--include-weights]

Arguments

  • --model: Path to trained monitor model
  • --output: Output path for Claude Skill
  • --include-weights: Include fine-tuned weights (default: false)

What Is a Claude Skill?

A Claude Skill is a portable, reusable AI workflow that can be:

  • Loaded in any Claude Code session
  • Shared across projects
  • Version controlled
  • Composed with other skills

Example

# Export GEPA-optimized monitor
/export-monitor \
  --model models/gepa_optimized.json \
  --output monitors/safety-monitor-v1.skill

# Export with fine-tuned weights
/export-monitor \
  --model models/gepa_finetuned.json \
  --output monitors/safety-monitor-v1-ft.skill \
  --include-weights

Output

Exporting monitor to Claude Skill...

Model: models/gepa_optimized.json
Output: monitors/safety-monitor-v1.skill

✓ Extracted optimized prompt
✓ Packaged configuration
✓ Generated skill manifest

Skill exported successfully!

Usage:
  claude skill load monitors/safety-monitor-v1.skill
  /scan-code your_code.py

Using Exported Skills

In Another Project

cd /path/to/another-project

# Load the skill
claude skill load /path/to/monitors/safety-monitor-v1.skill

# Use it
/scan-code src/api_handler.py

Share with Team

# Commit skill to git
git add monitors/safety-monitor-v1.skill
git commit -m "Add trained safety monitor skill"
git push

# Teammate uses it
git pull
claude skill load monitors/safety-monitor-v1.skill

Programmatic Usage

from claude_code.skills import load_skill

# Load skill
monitor_skill = load_skill("monitors/safety-monitor-v1.skill")

# Use it
result = monitor_skill.run(
    command="scan-code",
    args={"file_path": "code.py"}
)

Skill Contents

The exported skill includes:

Read the full file on GitHub · 167 lines

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. 11d ago First seen · 167 lines · 0 tokens per session scan A 90cbfb8b184e

Subscribe to this mod's changes

export-monitor is a command published in the GitHub repository jmanhype/claude-code-plugin-marketplace (27 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 886 tokens. 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.