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 amazon-nova-canvasgit 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/amazon-nova-canvas)<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/amazon-nova-canvas"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/amazon-nova-canvas/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/amazon-nova-canvas"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/amazon-nova-canvas.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00100 | $0.07911 |
| Opus 5 | $0.00050 | $0.03955 |
| Sonnet 5 | $0.00020 | $0.01582 |
| Haiku 4.5 | $0.00010 | $0.00791 |
Grade A, and why
amazon-nova-canvas 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 — 592 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Amazon Nova Canvas
Build against the native Amazon Bedrock InvokeModel API. Treat every inference as a paid, synchronous image-generation operation and preserve the returned bytes unchanged.
Start with the lifecycle gate
As verified on 2026-07-09, AWS lists amazon.nova-canvas-v1:0 as Legacy in its supported Regions and gives it an end-of-life date of 2026-09-30. Do not start a new production dependency on it. New customers cannot use Legacy models; existing customers may lose access after 15 days of inactivity. On or soon after EOL, requests fail unless the customer has a documented private arrangement with the provider. Stakeholder acceptance does not extend service availability.
AWS also forbids new fine-tuning jobs and new Provisioned Throughput endpoints after a foundation model enters Legacy. Public extended access, when offered, may carry higher provider-set pricing. Before any continued use by an eligible existing customer:
- Query
GetFoundationModelorListFoundationModelsin the intended Region. - Confirm the account is still eligible and active, verify the current billing rate, and make a separately authorized low-cost canary only before EOL or under a documented private arrangement when paid inference is allowed.
- Recheck the Nova Canvas model page for lifecycle, endpoint, Region, and successor information.
- Refuse to guess a replacement model ID. Record a named migration owner and cutover date.
Current production facts (verified 2026-07-09):
| Item | Value |
|---|---|
| Base model ID | amazon.nova-canvas-v1:0 |
| Runtime | bedrock-runtime |
| API | Native synchronous InvokeModel; not Converse, Responses, Chat Completions, or Bedrock Mantle |
| Inference route | In-Region only; no geo or global inference profile |
| Base-model service tier | Standard only |
| Base-model provisioned throughput | Not supported |
| In-Region availability | us-east-1, eu-west-1, ap-northeast-1 |
| Prompt language | English |
| Inputs / output | Text and image / image |
| Lifecycle | Legacy in all currently supported Regions; EOL 2026-09-30 |
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 · 592 lines · 100 tokens per session scan A 94a11a2ab9d1
amazon-nova-canvas is a skill published in the GitHub repository calesthio/generative-media-skills (170 stars, last pushed 2mo ago), licensed MIT. It adds 100 tokens to every session and 7,911 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…