Skills flux-2-klein

📦

flux-2-klein

Name: flux-2-klein
Author: agentspace-so

Content revision r1 Low Risk ⚙️ External commands🌐 Network access📁 Filesystem access

Generate Flux 2 Klein Images

Creative teams need fast image drafts without losing control over prompt structure and model settings. This skill guides Claude, Codex, and Claude Code to use RunComfy Flux 2 Klein variants for rapid concepts and polished outputs.

Supports: Claude Codex Code(CC)

📊 75 Adequate

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

Review the Skillstore skill "flux-2-klein" from https://skillstore.io/skills/agentspace-so-flux-2-klein.md and its manifest at https://skillstore.io/api/skills/agentspace-so-flux-2-klein/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/agentspace-so-flux-2-klein.md Signed manifest GET /api/skills/agentspace-so-flux-2-klein/manifest Signed lockfile GET /api/skills/agentspace-so-flux-2-klein/lockfile

Test it

Using "flux-2-klein". Generate a fast concept for a hiking backpack ad.

Expected outcome:

A concise RunComfy CLI plan using the Flux 2 Klein 4B endpoint, a subject-first prompt, and a local output directory.

Using "flux-2-klein". Make the final image more detailed and ready for review.

Expected outcome:

Switch to the 9B endpoint.
Use about 25 steps.
Keep the prompt under the documented token guidance.
Use dimensions within the aspect ratio and resolution limits.

Using "flux-2-klein". Why did my wide poster crop badly?

Expected outcome:

An explanation that Flux 2 Klein is capped near 16:9, with a recommendation to revise dimensions or choose a different model.

Security Audit

Low Risk

v7 • 7/9/2026 Open versioned report

The static findings are almost entirely Markdown examples, documented RunComfy CLI usage, expected RunComfy URLs, or documentation shorthand. No prompt injection, covert command execution, or malicious filesystem behavior was found, but the skill does send prompts and media references to a third-party hosted model service.

Files scanned

224

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (1)

Low

SKILL.md:206-222

Third-party prompt and media disclosure

The skill sends user prompts and optional image or video URLs to RunComfy hosted model infrastructure. This is disclosed, but users may expose private creative briefs, reference assets, or sensitive media if they use untrusted inputs.

The skill explicitly documents API submission, bearer-token use, external media fetching, and outbound RunComfy endpoints. The risk is contextual data disclosure rather than hidden malicious behavior.

Risk Factors

⚙️ External commands (42)

🌐 Network access (5)

SKILL.md:17 SKILL.md:23 SKILL.md:76 SKILL.md:202 SKILL.md:207

📁 Filesystem access (5)

SKILL.md:208 SKILL.md:209 SKILL.md:210 SKILL.md:219 SKILL.md:219

Audited by: claude View Audit History →

Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report

Copy report link

https://skillstore.io/skills/agentspace-so-flux-2-klein/audits/7?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/agentspace-so-flux-2-klein/security.svg)](https://skillstore.io/skills/agentspace-so-flux-2-klein?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/agentspace-so-flux-2-klein?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/agentspace-so-flux-2-klein/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/agentspace-so-flux-2-klein.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Academic citations (APA · BibTeX · CFF)

APA citation

agentspace-so. (2026). flux-2-klein security audit report (audit version 7) [Author version unspecified]. Skillstore. https://skillstore.io/skills/agentspace-so-flux-2-klein/audits/7

BibTeX citation

@techreport{agentspace-so-agentspace-so-flux-2-klein-2026,
  author = {agentspace-so},
  title = {flux-2-klein security audit report (audit version 7)},
  institution = {Skillstore},
  year = {2026},
  number = {7},
  url = {https://skillstore.io/skills/agentspace-so-flux-2-klein/audits/7},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "flux-2-klein security audit report (audit version 7)"
version: "unspecified"
type: report
authors:
  - name: "agentspace-so"
date-released: "2026-07-09"
url: "https://skillstore.io/skills/agentspace-so-flux-2-klein/audits/7"
identifiers:
  - type: other
    value: "skillstore:agentspace-so-flux-2-klein:audit:7"
    description: "Skillstore immutable audit report identifier"

Compare variants

3 installable variants

Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.

Why this variant is first

Highest Skillstore Score

Author / source Skillstore Score Evidence Confidence Skillstore usage Updated

agentspace-so Recommended Current

agentspace-so-flux-2-klein

Skillstore Score 75

Evidence Confidence High

Skillstore usage 7

Updated

2026-08-21

doany-ai

doany-ai-flux-2-klein

Skillstore Score 50

Evidence Confidence High

Skillstore usage 20

Updated

2026-08-21

runcomfy-com

runcomfy-com-flux-2-klein

Skillstore Score 50

Evidence Confidence High

Skillstore usage 8

Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: High

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Create fast visual concepts

Use the 4B variant to explore product, campaign, or illustration ideas with short feedback cycles.

Polish selected image prompts

Move a strong concept to the 9B variant with higher step counts for more detail.

Standardize prompt writing

Apply the documented subject-first prompt grammar across image generation requests.

Try These Prompts

Generate a simple concept

Use Flux 2 Klein to generate a fast concept image of a modern desk lamp on a clean studio background.

Create a polished product image

Use Flux 2 Klein 9B to create a polished product photo of a ceramic mug. Use soft window light, shallow depth of field, and a square output.

Compare fast and final variants

Help me iterate with Flux 2 Klein 4B first, then prepare the final Flux 2 Klein 9B command for the best prompt.

Use reference style guidance

Use Flux 2 Klein with reference images to keep the same lighting and composition while changing the product color and label text.

Best Practices

Use the 4B variant for quick exploration and the 9B variant for final polish.
Keep prompts specific, subject-first, and within the documented length guidance.
Use trusted reference image URLs and review generated outputs before publishing.

Avoid

Do not paste secrets or private data into image prompts or reference URLs.
Do not request unsupported 4K or extreme aspect ratio outputs from this model.
Do not mix unrelated visual styles across multiple reference images.

Frequently Asked Questions

Does this skill generate images locally?

No. It uses the RunComfy CLI and hosted Flux 2 Klein model endpoints.

Which Flux 2 Klein variant should I use first?

Use 4B for fast concepting. Use 9B when you want a more polished final image.

Does it work with Claude Code?

Yes. The skill declares support for Claude, Codex, and Claude Code.

Can it use reference images?

Yes. The skill documents support for up to four reference images through the RunComfy endpoint.

Is it suitable for precise logo or text rendering?

Not always. The skill recommends other models when embedded text precision is critical.

What credentials are required?

You need RunComfy CLI authentication through login or a RUNCOMFY_TOKEN environment variable.

Developer Details

Author

agentspace-so

License

MIT

Skillstore revision

Version notice

The author did not declare a version.

Repository

https://github.com/agentspace-so/runcomfy-agent-skills/tree/main/flux-2-klein/

Ref

7db9b9f06e0ab79c575b58bc48c4d8dc9849f424

Maintenance freshness

7/18/2026

Usage

3 downloads · 57 views

File structure

📄 SKILL.md