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 calesthio/generative-media-skills --skill black-forest-labs-fluxgit clone --depth 1 https://github.com/calesthio/generative-media-skillsWrote 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/calesthio/generative-media-skills/black-forest-labs-flux)<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/black-forest-labs-flux"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/black-forest-labs-flux/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/calesthio/generative-media-skills/black-forest-labs-flux"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/black-forest-labs-flux.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 | $0.00111 | $0.07397 |
| Opus 5 | $0.00056 | $0.03698 |
| Sonnet 5 | $0.00022 | $0.01479 |
| Haiku 4.5 | $0.00011 | $0.00740 |
Grade B, and why
black-forest-labs-flux 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 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.
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.
job = requests.post( "https://api.bfl.ai/v1/flux-2-pro", headers=headers, json=payload, timeout=60 Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
job = requests.post( How it starts
The opening of the file, as written. The whole thing — 355 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Produce images with Black Forest Labs FLUX
Use this evidence notation throughout your work:
- [Documented] means BFL documentation, a BFL model card/repository, BFL legal terms, or a BFL-authored paper states the fact.
- [Inference] means a conclusion follows from documented facts but BFL does not state it directly.
- [Heuristic] means production advice to validate against actual outputs.
Treat all endpoint names, limits, prices, licenses, and terms as volatile. The facts below were verified 2026-07-09. Recheck the current BFL API reference, release notes, model card, and governing license before a consequential run.
Keep the execution surfaces separate
Identify the surface before selecting parameters or stating rights.
- BFL direct API — requests go to an official
api.bfl.aiendpoint with anx-key. BFL defines the request schema, moderation, billing, asynchronous result contract, and service terms. [Documented: D1, D2, D9] - Third-party hosted gateway — the gateway, not BFL's direct API, defines model slugs, accepted parameters, retention, moderation, pricing, and version pinning. Never assume a BFL field or limit works unchanged. Verify that provider's current documentation and contract. [Inference]
- Local/open-weight deployment — weights and inference run on infrastructure under the checkpoint's own license. There is no automatic BFL API moderation, retention policy, or signed-result URL. Implement filtering, provenance, storage controls, and capacity planning yourself. [Documented: D10, D11]
Do not call every downloadable FLUX checkpoint “open source.” FLUX.2 [klein] 4B is Apache-2.0; FLUX.2 [klein] 9B and FLUX.2 [dev] are downloadable/open-weight but governed by the FLUX Non-Commercial License unless a commercial weights license applies. [Documented: D10]
Select the family deliberately
Current FLUX.2 paths
| Need | Choose | Surface and consequential facts |
|---|---|---|
| Most production generation/editing | FLUX.2 [pro] | BFL's recommended starting point. Direct endpoints include mutable flux-2-pro-preview and pinned flux-2-pro. Up to 8 references through the API and 10 in the BFL playground. [Documented: D1, D2] |
| Hardest edit, strongest adherence, highest final quality | FLUX.2 [max] | Direct API/Playground, up to 8 API references. It is the FLUX.2 path with grounding search. Use only when that quality or current-context feature justifies its cost. [Documented: D1, D2] |
| Typography, small-detail preservation, tunable sampling | FLUX.2 [flex] | Direct API. Exposes guidance 1.5–10 and steps 1–50; supports prompt upsampling and up to 8 API references. Higher guidance can trade realism for adherence. [Documented: D1, D2] |
| Latency-sensitive preview, interactive tool, high volume | FLUX.2 [klein] 4B or 9B | Direct API and downloadable weights; up to 4 references. No prompt upsampling, so write complete prompts. 4B is Apache-2.0; 9B is FLUX NCL unless separately licensed. [Documented: D1, D10] |
| Local customization or research with full sampling control | FLUX.2 [dev] or a [klein] Base checkpoint | Local/open-weight, not the BFL public API. BFL recommends at most 6 references for [dev]. Distilled klein is a short-step production path; Base variants retain full training signal for fine-tuning and diversity. Verify the exact checkpoint license. [Documented: D1, D10] |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 355 lines · 111 tokens per session scan B d60dea1e0c5a
black-forest-labs-flux is a skill published in the GitHub repository calesthio/generative-media-skills (170 stars, last pushed 2mo ago), licensed MIT. It adds 111 tokens to every session and 7,397 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
cliptalk-cover-director
Produces evidence-backed cover candidates and reviewable cover variants for a ClipTalk video. Use when the user asks for a cover, poster frame, thumbnail, or multiple cover directions; do not use for timeline editing or social-video reframing.
cliptalk-smart-reframe
Creates a subject-aware, time-varying crop track and a review-only social-format preview from an accepted ClipTalk cut. Use for automatic vertical, square, or portrait reframing; do not use for a fixed manual crop or before content editing is accepted.
cliptalk-content-extractor
Locates and assembles source passages matching a semantic request. Use for extracting explanations, topics, quotes, demonstrations, or other specifically described content.
cliptalk-interview-editor
Produces a coherent interview edit by combining speaker discovery, topic selection, dialogue context, cleanup, subtitles, and preview. Use for interviews, podcasts, testimonials, or question-and-answer recordings.
cliptalk-shortform-hook-director
Finds and assembles a reviewable short-form cut with a strong opening hook. Use for Shorts, Reels, social clips, talking-head cutdowns, or requests for a punchier opening.
cliptalk-social-reframe-exporter
Creates a review-only 9:16, 4:5, 1:1, or 16:9 version from an existing accepted ClipTalk cut, then checks the rendered preview. Use only when a cut already exists and the user asks to adapt it for Shorts, Reels, Douyin, Xiaohongshu, WeChat Channels, or square feeds; do not use when the user still needs content found…