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 stability-ai-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/stability-ai-image)<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/stability-ai-image"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/stability-ai-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/stability-ai-image"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/stability-ai-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 471 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 | $0.00095 | $0.08197 |
| Opus 5 | $0.00048 | $0.04098 |
| Sonnet 5 | $0.00019 | $0.01639 |
| Haiku 4.5 | $0.00010 | $0.00820 |
Grade A, and why
stability-ai-image scanned grade A with 0 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 498 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stability AI Image Production
Use this skill to choose the correct Stability AI image surface, make schema-correct calls, preserve production evidence, and avoid confusing the hosted API with self-hosted weights.
Evidence legend and freshness
- Documented means stated by a linked first-party Stability AI source or the live first-party OpenAPI document.
- Inference means a conclusion drawn from documented behavior; verify it when the consequence matters.
- Production heuristic means operational advice, not a provider guarantee.
- Volatile API facts in this skill were verified 2026-07-09. Re-check the API reference, pricing, and release notes before committing spend or shipping a long-lived integration.
Route the job before writing a prompt
- Decide between hosted and self-hosted execution.
- Use the hosted Platform API for managed Stable Image services, edits, controls, upscalers, moderation, and provider-signed provenance.
- Use open weights only when local data control, custom inference, fine-tuning, or deployment control justifies operating the model and its license obligations.
- Do not imply that Stable Image Core or all Stable Image microservices are downloadable weights. The downloadable SD3.5 checkpoints and the hosted service catalog overlap only partly.
- Match the intent to one operation rather than forcing every job through generation.
- Confirm output size, input constraints, cost, and synchronous/asynchronous behavior.
- Confirm rights, consent, privacy, and the current Acceptable Use Policy before uploading source images.
- Generate a small approved sample before a batch. Record endpoint, parameters, seed returned by the API, request ID, input hashes, output hash, cost estimate, and policy/QA disposition.
Current hosted surface
Documented, verified 2026-07-09: REST v2beta is the primary feature surface. Stability says REST v1, gRPC, and v2alpha remain maintained but receive no new features or parameters; it recommends changing equivalent v2alpha URLs to v2beta. Treat legacy APIs as maintenance/migration surfaces, not sources for new designs. API reference
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 · 498 lines · 95 tokens per session scan A b463407e23a7
stability-ai-image is a skill published in the GitHub repository calesthio/generative-media-skills (170 stars, last pushed 2mo ago), licensed MIT. It adds 95 tokens to every session and 8,197 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. 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…