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 AnastasiyaW/codex-claude-code-config --skill flux2-lora-traininggit clone --depth 1 https://github.com/AnastasiyaW/codex-claude-code-configWrote 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/anastasiyaw/codex-claude-code-config/flux2-lora-training)<a href="https://agentmods.dev/skills/anastasiyaw/codex-claude-code-config/flux2-lora-training"><img src="https://agentmods.dev/badge/skills/anastasiyaw/codex-claude-code-config/flux2-lora-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.
<a href="https://agentmods.dev/skills/anastasiyaw/codex-claude-code-config/flux2-lora-training"><img src="https://agentmods.dev/badge/skills/anastasiyaw/codex-claude-code-config/flux2-lora-training.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 15 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
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 | $0.00073 | $0.05346 |
| Opus 5 | $0.00036 | $0.02673 |
| Sonnet 5 | $0.00015 | $0.01069 |
| Haiku 4.5 | $0.00007 | $0.00535 |
Grade A, and why
flux2-lora-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.
How it starts
The opening of the file, as written. The whole thing — 422 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FLUX.2 Klein 9B — LoRA Training Reference
Evidence boundary
This file is a route to evaluate a training plan, not a tested recipe. Model cards establish model identity and license; trainer repositories establish only the behavior of their pinned version. Numeric settings and BFS notes below are historical local experiment candidates unless an exact source is linked. Before training, record the model revision, trainer commit, dataset contract, hardware, and a small held-out acceptance set. Do not promote a historical score, memory estimate, slot order, or private result into a universal default.
Архитектура моделей
FLUX.2 Klein — Rectified Flow Transformer (DiT)
| Параметр | Klein 9B | Klein 4B | Qwen-Image-Edit | FLUX.1 dev |
|---|---|---|---|---|
| Blocks | 32 (8+24) | 25 (5+20) | 60 (MM-DiT) | 56 (8+48) |
| Embedding dim | 12,288 | 7,680 | — | 15,360 |
| VAE latent channels | 32 (128 packed features) | 32 (128 packed features) | verify the exact revision | 16 |
| Text encoder | Qwen3 (bundled) | Qwen3 | Qwen2.5-VL (7B) | Mistral-Small-3.1 |
| Guidance embeddings | НЕТ | НЕТ | — | Есть |
| Total params | 9B | 4B | 20B DiT + 7B VL | 12B |
FLUX.2 Klein VAE: AutoencoderKLFlux2, 32 latent channels (FLUX.1: 16) → после 2×2 patch packing в трансформере: 32×4 = 128 dims per token, 16× spatial compression. Несовместим с FLUX.1 LoRA — другой VAE, другой latent space. Tiling для больших разрешений: 1024px тайлы с 25% overlap, обрабатывает произвольное разрешение.
Klein editing механизм (Kontext-style): reference image VAE-кодируется и конкатенируется с noise latent вдоль sequence dim. Positional embeddings разделяют reference и output через 3D RoPE time offsets (ref1=t:1, ref2=t:2, output=t:0). Поддерживает до 10 reference images теоретически, обучен на 2.
Text encoder Klein: Qwen3 (встроен в 9B), выходы из слоёв 9, 18, 27.
Do not assume a trainer’s flux_guidance_* fields are no-ops or active from
their names. Verify their behavior against the pinned trainer release and the
selected model before relying on them.
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.
- 2d ago Changed · +13 lines · -169 tokens per session 5f09f1e6d652
- 10d ago First seen · 409 lines · 242 tokens per session scan A 1cb659c0702e
flux2-lora-training is a skill published in the GitHub repository AnastasiyaW/codex-claude-code-config (149 stars, last pushed yesterday), licensed MIT. It adds 73 tokens to every session and 5,346 once invoked, about $0.0004 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.
Other skills, from other repositories
ai-content-filter
Professional Ai Content Filter Expert skill. Integrate LLM API workflows, safe system prompt guidelines, and agentic workflows.
ai-engineer
Professional Ai Engineer skill. Integrate LLM API workflows, safe system prompt guidelines, and agentic workflows.
embedding-architect
Professional Embedding Architect skill. Integrate LLM API workflows, safe system prompt guidelines, and agentic workflows.
eval-harness
Professional Eval Harness Expert skill. Integrate LLM API workflows, safe system prompt guidelines, and agentic workflows.
few-shot-architect
Professional Few Shot Architect skill. Integrate LLM API workflows, safe system prompt guidelines, and agentic workflows.
fine-tuner
Professional Fine Tuner Expert skill. Integrate LLM API workflows, safe system prompt guidelines, and agentic workflows.