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.
git clone --depth 1 https://github.com/jmanhype/claude-code-plugin-marketplaceWrote 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.
[](https://agentmods.dev/commands/jmanhype/claude-code-plugin-marketplace/finetune-monitor)<a href="https://agentmods.dev/commands/jmanhype/claude-code-plugin-marketplace/finetune-monitor"><img src="https://agentmods.dev/badge/commands/jmanhype/claude-code-plugin-marketplace/finetune-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.
<a href="https://agentmods.dev/commands/jmanhype/claude-code-plugin-marketplace/finetune-monitor"><img src="https://agentmods.dev/badge/commands/jmanhype/claude-code-plugin-marketplace/finetune-monitor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00528 |
| Opus 5 | $0.00000 | $0.00264 |
| Sonnet 5 | $0.00000 | $0.00106 |
| Haiku 4.5 | $0.00000 | $0.00053 |
Grade A, and why
finetune-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 12d 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.
What it actually says
Finetune Monitor Command
Bootstrap fine-tune the monitor after GEPA optimization to further improve performance.
Usage
/finetune-monitor --base-model models/gepa_optimized.json --dataset control_tax.json [--samples 200]
When to Finetune
- After GEPA optimization (not before!)
- When you need the absolute best performance
- For production deployments
- When audit budget is very tight (<0.5%)
What It Does
- Loads GEPA-optimized monitor
- Generates predictions on training set
- Filters for correct predictions (attack > honest)
- Creates fine-tuning dataset from trajectories
- Fine-tunes model weights via OpenAI API
- Saves fine-tuned model
Example
/finetune-monitor \
--base-model models/gepa_optimized.json \
--dataset datasets/control_tax.json \
--samples 200
Output
Loading GEPA-optimized model...
Generating predictions on 200 samples...
Filtering correct predictions: 178/200 (89%)
Creating fine-tuning dataset...
Uploading to OpenAI...
Starting fine-tuning job: ftjob-abc123...
[Progress: ████████████████░░░░] 80%
Fine-tuning complete!
Model: ft:gpt-4.1-nano-2025-04-14:abc123
Saved to: models/gepa_finetuned.json
Performance Impact
GEPA Only:
Safety @ 0.5%: 80%
Safety @ 1.0%: 90%
GEPA + Finetune:
Safety @ 0.5%: 85% (+5%)
Safety @ 1.0%: 90% (same)
Fine-tuning helps most at very low audit budgets.
Cost Considerations
- GEPA: ~$5-10 (API calls for reflection)
- Fine-tuning: ~$50-100 (model training)
Use GEPA first, only finetune if needed.
Programmatic Usage
from code_safety_monitor.src.trainer import FinetuneTrainer, train_pipeline
# Full pipeline with fine-tuning
monitor = train_pipeline(
trainset=train_examples,
run_finetune=True # Enable fine-tuning
)
Related Commands
/optimize-gepa: Run this first/validate-safety: Evaluate fine-tuned model
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.
- 12d ago First seen · 91 lines · 0 tokens per session scan A 9cde96ae34fa
finetune-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 528 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.
Other commands, from other repositories
music-suno-prompt
Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.
laravel-ai-sdk
Build AI features with the first-party Laravel AI SDK (Laravel 13+); use the laravel:ai-sdk skill exactly as written.
audit-prompt
Evaluate an existing prompt for clarity, effectiveness, and edge cases.
develop-image-prompt.eval
Generates a detailed image generation prompt from a document or content description. Good output: a prompt that is specific, visual, non-abstract, includes style/composition/lighting guidance, and is calibrated to the specified dimensions and style options.
dare-llm-integration
Integração segura e eficiente com LLMs (Gemini, Claude, OpenAI, Ollama) em projetos DARE.
prompt-create
Create a new prompt following ground rules.