fireworks-training

fireworks-training is a skill for Claude Code from fw-ai/cookbook. It costs 67 tokens per session (207 once invoked), scanned A, original, Apache-2.0.

A coding-agent skill for training and fine-tuning machine-learning models on Fireworks, a hosted AI model platform. It covers several training methods, dataset preparation, evaluation, and training workflows.

In plain words
What is it for?
Use it to prepare datasets, choose models and training shapes, run managed or custom training jobs, evaluate results, and resume or clean up training workflows.
Why use it?
It helps manage the planning, commands, recipes, settings, and cost checks needed to train models without assembling the process from scratch.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Codex.

Part of the fireworks-training plugin — 5 skills shipped together

Good fit Use it to prepare datasets, choose models and training shapes, run managed or custom training jobs, evaluate results, and resume or clean up training workflows.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/fw-ai/cookbook/fireworks-training
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.

Any agent
npx skills add fw-ai/cookbook --skill fireworks-training
Clone the repo
git clone --depth 1 https://github.com/fw-ai/cookbook

Made for: Claude Code.

Or install fireworks-training, the plugin that ships this one along with the rest of its 5 skills.

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 fireworks-training

README.md
[![agentmods](https://agentmods.dev/badge/skills/fw-ai/cookbook/fireworks-training/github.svg)](https://agentmods.dev/skills/fw-ai/cookbook/fireworks-training)
Your own site
<a href="https://agentmods.dev/skills/fw-ai/cookbook/fireworks-training"><img src="https://agentmods.dev/badge/skills/fw-ai/cookbook/fireworks-training/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 fireworks-training

Your own site · 80×15
<a href="https://agentmods.dev/skills/fw-ai/cookbook/fireworks-training"><img src="https://agentmods.dev/badge/skills/fw-ai/cookbook/fireworks-training.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 207 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00067 $0.00207
Opus 5 $0.00034 $0.00103
Sonnet 5 $0.00013 $0.00041
Haiku 4.5 $0.00007 $0.00021

Measured 2d ago against content hash 5e5f7bc14ddb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

fireworks-training 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 2d 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.

skills/fireworks-training/SKILL.md · 26 lines

What it actually says

Fireworks training

This workflow is split into three focused skills:

Goal Skill
Choose method, data, evaluation, and cookbook entry research
Plan, run, monitor, deploy, or resume training configure
Diagnose a failed, stuck, or low-quality run debug

Do not execute a training workflow from this file. Route to the matching skill.

This directory also carries shared detailed references used by configure and debug. Cursor and Codex installs must include fireworks-training alongside the three entry skills.

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. 2d ago Changed · -441 lines · -99 tokens per session 5e5f7bc14ddb
  2. 12d ago First seen · 467 lines · 166 tokens per session scan A 908c63377202

Subscribe to this mod's changes

fireworks-training is a skill published in the GitHub repository fw-ai/cookbook (205 stars, last pushed today), licensed Apache-2.0. It adds 67 tokens to every session and 207 once invoked, about $0.0003 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 2026-08-30.