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 kling-kolors-imagegit 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/kling-kolors-image)<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/kling-kolors-image"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/kling-kolors-image/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/kling-kolors-image"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/kling-kolors-image.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 749 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00133 | $0.12423 |
| Opus 5 | $0.00067 | $0.06212 |
| Sonnet 5 | $0.00027 | $0.02485 |
| Haiku 4.5 | $0.00013 | $0.01242 |
Grade A, and why
kling-kolors-image scanned grade A 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
from urllib.parse import urlsplit Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
proc = subprocess.Popen(argv, shell=False, stdin=subprocess.DEVNULL, How it starts
The opening of the file, as written. The whole thing — 781 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Produce still images with Kling and Kolors
Begin by resolving the name. “Kling image,” “Kolors,” and “可图” now refer to related but non-interchangeable surfaces.
| Surface | What it is | Appropriate use |
|---|---|---|
| Kling AI IMAGE 3.0 | Current hosted still-image generation and natural-language editing, with multi-reference support | Single stills, product/character continuity, restyling, localized edits |
| Kling AI IMAGE 3.0 Omni | Current hosted narrative-image model with image-series workflows and direct 2K/4K options | Storyboards, connected image sequences, high-resolution masters |
| Kling IMAGE O1 / 2.1 and older Open Platform pages | Earlier hosted workflows that may remain account/API dependent | Reproduce an existing approved pipeline only after live capability discovery |
| Open Kolors checkpoint | A 2024 Kuaishou latent-diffusion model distributed as weights and code | Local bilingual text-to-image and the separately released img2img, IP-Adapter, ControlNet, inpainting, FaceID, and DreamBooth-LoRA workflows |
Documented fact, verified 2026-07-10: Kling’s overview says its hosted image capabilities are based on Kuaishou’s Kolors technology, but it does not publish evidence that IMAGE 3.0, IMAGE 3.0 Omni, or O1 is the same checkpoint or API contract as Kwai-Kolors/Kolors-diffusers. Never move parameters, licenses, or benchmark conclusions between those surfaces without direct support.
Frame the production decision
Record a short brief before opening a generation surface:
- deliverable, placement, crop/aspect, required pixels, number of final images, and deadline;
- subject, action, environment, composition, lighting, materials, palette, and any exact visible text;
- whether references control identity, product geometry, pose/composition, environment, or style;
- which details must remain invariant and which may change;
- rights to every reference, trademark/logo constraints, likeness consent, and privacy classification;
- hosted versus local execution, region/account, retention requirement, and cost ceiling;
- pass/fail criteria at full resolution.
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 · 781 lines · 133 tokens per session scan A 8112ec311eb0
kling-kolors-image is a skill published in the GitHub repository calesthio/generative-media-skills (170 stars, last pushed 2mo ago), licensed MIT. It adds 133 tokens to every session and 12,423 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). 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…