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 leonardo-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/leonardo-image)<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/leonardo-image"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/leonardo-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/leonardo-image"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/leonardo-image.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
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 →
- high Tool Misuse · line 124 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 603 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 603 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00118 | $0.10438 |
| Opus 5 | $0.00059 | $0.05219 |
| Sonnet 5 | $0.00024 | $0.02088 |
| Haiku 4.5 | $0.00012 | $0.01044 |
Grade A, and why
leonardo-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 urlparse Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
subprocess.run([*scanner_command, tmp], check=True, timeout=120, How it starts
The opening of the file, as written. The whole thing — 651 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Leonardo image production
Operate Leonardo.Ai's official Production API for still images. Keep native Leonardo models, partner models hosted by Leonardo, realtime-canvas endpoints, and legacy endpoints visibly separate: they have different routes and schemas.
Start with a production brief
Collect or propose:
- Deliverable: subject, setting, style, composition, aspect/dimensions, output count, and acceptance criteria.
- Operation: text-to-image, image-to-image, reference guidance, masked edit, upscale, background removal, or custom training.
- Source media: local paths or Leonardo image IDs, whether each is uploaded or generated, and the intended role of each reference.
- Rights: ownership/licence, likeness consent, privacy classification, and whether public visibility is allowed.
- Runtime: direct REST, official Python SDK, or official TypeScript SDK.
- Spend: calculator estimate, hard budget, concurrency ceiling, and whether auto-top-up is disabled.
Default to a one-image private preview at a conservative dimension. Before any paid call, state the exact route, model/model ID, settings, sample count, calculator estimate, and why. Wait for explicit approval. Never silently change model, visibility, reference method, quality mode, or sample-to-batch scope.
Evidence snapshot and boundaries
The contracts below were checked against first-party Leonardo documentation, the official SDK repositories, changelog, policies, and legal pages on 2026-07-10. Recheck them before production: Leonardo is actively moving API pricing to PAYG, adds model-specific v2 contracts, and publishes occasional conflicting examples.
This skill covers:
- Native Leonardo still models on
POST /api/rest/v1/generations. - Still-image references, uploaded inputs, image-to-image, current
controlnets, and LCM inpainting. - Still-image upscalers and custom image Elements/models.
It excludes video endpoints, 3D generation, Blueprints as a general orchestration system, the Leonardo web editor itself, MCP proxies, and unofficial SDKs. Some partner image models are available inside Leonardo's API; label them as partner models and use their own v2 guide rather than treating them as Lucid/Phoenix variants.
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 · 651 lines · 118 tokens per session scan A 50eefa89f869
leonardo-image is a skill published in the GitHub repository calesthio/generative-media-skills (170 stars, last pushed 2mo ago), licensed MIT. It adds 118 tokens to every session and 10,438 once invoked, about $0.0006 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…