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.
npx skills add cerebrixos-org/tuning-engines-cli --skill tuning-enginesgit clone --depth 1 https://github.com/cerebrixos-org/tuning-engines-cliWrote 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/skills/cerebrixos-org/tuning-engines-cli/tuning-engines)<a href="https://agentmods.dev/skills/cerebrixos-org/tuning-engines-cli/tuning-engines"><img src="https://agentmods.dev/badge/skills/cerebrixos-org/tuning-engines-cli/tuning-engines/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/skills/cerebrixos-org/tuning-engines-cli/tuning-engines"><img src="https://agentmods.dev/badge/skills/cerebrixos-org/tuning-engines-cli/tuning-engines.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 | $0.00035 | $0.00239 |
| Opus 5 | $0.00017 | $0.00120 |
| Sonnet 5 | $0.00007 | $0.00048 |
| Haiku 4.5 | $0.00003 | $0.00024 |
Grade A, and why
tuning-engines 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 9d 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
Tuning Engines
Use the tuning-engines MCP server when the user asks to inspect or operate
their Tuning Engines tenant.
Safety
- Treat API keys, provider credentials, OAuth secrets, and inference keys as secrets.
- Never echo or store secret values in traces, files, comments, or command output.
- Confirm destructive mutations before executing them.
- Use tenant-scoped public MCP tools only; never attempt internal proxy routes.
- Prefer metadata-only traces unless the user explicitly enabled a broader capture mode.
- Explain approval, policy, and compliance decisions using returned evidence; do not invent it.
Common Flows
- Inspect traces and usage before diagnosing runtime behavior.
- List pending approvals before attempting an approval-gated retry.
- Read registry resources before creating or updating references.
- Validate policies and resources before saving or enabling them.
- Keep generated datasets, policies, workflows, and fine-tuning actions in review state until explicitly approved.
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.
- 9d ago First seen · 27 lines · 35 tokens per session scan A caa4efc984f3
tuning-engines is a skill published in the GitHub repository cerebrixos-org/tuning-engines-cli (6 stars, last pushed 22d ago), licensed MIT. It adds 35 tokens to every session and 239 once invoked, about $0.0002 per session on Opus 5. 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 2026-08-31.
Other skills, from other repositories
llama-factory
Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support.
tinker-training-cost
Calculates training costs for Tinker fine-tuning jobs. Use when estimating costs for Tinker LLM training, counting tokens in datasets, or comparing Tinker model training prices. Tokenizes datasets using the correct model tokenizer and provides accurate cost estimates.
transformers
This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning…
llm-integration
LLM integration patterns for function calling, streaming responses, local inference with Ollama, and fine-tuning customization. Use when implementing tool use, SSE streaming, local model deployment, LoRA/QLoRA fine-tuning, or multi-provider LLM APIs.
fireworks-ai-inference
Fast inference and fine-tuning platform with serverless and on-demand GPU deployments. OpenAI-compatible API for chat completions, embeddings, function calling, vision, and structured output. Supports SFT, DPO, and RL fine-tuning. SOC2 + HIPAA compliant.
axolotl
Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support.