flux2-klein-prompting

flux2-klein-prompting is a skill for Claude Code from AnastasiyaW/codex-claude-code-config. It costs 218 tokens per session (3,006 once invoked), scanned B, original, MIT.

A prompt-writing guide for FLUX.2 [klein], an image-generation and image-editing model. It explains how to describe subjects, scenes, composition, lighting, style, and required text in connected prose.

In plain words
What is it for?
Use it to write text-to-image prompts, photo-editing prompts, and prompts that combine several reference images.
Why use it?
It helps turn a rough image idea or edit request into instructions the model can follow. It also covers differences between model sizes, modes, licenses, and reference-image use.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the claude-code-config plugin — 57 skills, 8 agents shipped together

Good fit Use it to write text-to-image prompts, photo-editing prompts, and prompts that combine several reference images.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/anastasiyaw/codex-claude-code-config/flux2-klein-prompting
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 AnastasiyaW/codex-claude-code-config --skill flux2-klein-prompting
Clone the repo
git clone --depth 1 https://github.com/AnastasiyaW/codex-claude-code-config

Made for: Claude Code.

Or install claude-code-config, the plugin that ships this one along with the rest of its 57 skills, 8 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 flux2-klein-prompting

README.md
[![agentmods](https://agentmods.dev/badge/skills/anastasiyaw/codex-claude-code-config/flux2-klein-prompting/github.svg)](https://agentmods.dev/skills/anastasiyaw/codex-claude-code-config/flux2-klein-prompting)
Your own site
<a href="https://agentmods.dev/skills/anastasiyaw/codex-claude-code-config/flux2-klein-prompting"><img src="https://agentmods.dev/badge/skills/anastasiyaw/codex-claude-code-config/flux2-klein-prompting/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 flux2-klein-prompting

Your own site · 80×15
<a href="https://agentmods.dev/skills/anastasiyaw/codex-claude-code-config/flux2-klein-prompting"><img src="https://agentmods.dev/badge/skills/anastasiyaw/codex-claude-code-config/flux2-klein-prompting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 218 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,006 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 4 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 System Prompt Leakage · line 9
    Skill contains patterns that could indirectly extract system prompts through rephrasing, translation, summarization, or side-channel techniques.
    Fix: Guard against indirect extraction by refusing to summarize, translate, or rephrase system instructions. Add explicit anti-extraction clauses.
  • medium Data Exfiltration · line 172
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 172
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 173
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 $0.00218 $0.03006
Opus 5 $0.00109 $0.01503
Sonnet 5 $0.00044 $0.00601
Haiku 4.5 $0.00022 $0.00301

Measured 5d ago against content hash 33dcd57068ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade B, and why

flux2-klein-prompting scanned grade B with 2 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 5d 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

create = requests.post( "https://api.bfl.ai/v1/flux-2-klein-4b",

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

create = requests.post(
skills/ai-ml/flux2-klein-prompting/SKILL.md · 276 lines

How it starts

The opening of the file, as written. The whole thing — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FLUX.2 [klein] — Prompt Engineering Guide

Core principle: prose, not tags

BFL guidance favors a concrete natural-language description over an ambiguous bag of tags. State who/what is in the image, where, style, materials/light/camera and — for editing — the properties to preserve. Prompt shape is a starting point, not a quality guarantee; assess the result against the requested edit.


Model variants quick reference

Axis Options Notes
Size 4B / 9B 9B better for complex instructions; 4B fastest
Mode Distilled / Base Use the exact model-card or serving API settings; step/CFG values are implementation-specific
License 4B Apache-2.0 / 9B Non-Commercial Check before commercial use
Task T2I / Edit (I2I) / Multi-reference The current BFL image-editing guide documents up to 8 references via API (10 in playground); re-check the selected endpoint schema before use

9B uses Qwen3 8B text embedder → solid multilingual support (Russian works natively).


Prompt structure

T2I (text-to-image)

  1. Subject — who/what, key attributes
  2. Scene/context — where, time of day, surroundings
  3. Composition — framing, angle, background
  4. Light/materials — source, softness, reflections, texture
  5. Style/genre — photorealism, illustration, catalog, poster, UI
  6. Text in image (if needed) — exact string in quotes + position/font

Edit (I2I, no mask)

  1. Base anchor — "This exact image but…"
  2. What to change — object / background / text / color / material
  3. What to preserve — face, lighting, style, perspective, brand elements
  4. Multi-reference — reference by "image 2 / image 3", keep prompt concise

Key rules

Text in image → always in straight quotes, specify position. Without this: garbled glyphs.

Заголовок: "ТОЧНЫЙ ТЕКСТ". Шрифт жирный гротеск, ровный кернинг. Других надписей не добавлять.

Negatives → positives → don't say "don't change X", say "preserve X"

❌ "не меняй освещение"
✅ "Сохрани освещение, перспективу и лицо"

Read the full file on GitHub · 276 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. 5d ago Changed · +17 lines 33dcd57068ba
  2. 12d ago First seen · 259 lines · 218 tokens per session scan B 1c95abce2b1c

Subscribe to this mod's changes

flux2-klein-prompting is a skill published in the GitHub repository AnastasiyaW/codex-claude-code-config (150 stars, last pushed 3d ago), licensed MIT. It adds 218 tokens to every session and 3,006 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.