agnes-ai

agnes-ai is a skill for Claude Code from guihai24/openskills. It costs 224 tokens per session (1,445 once invoked), scanned B, original, MIT.

A skill for generating images and videos with Agnes AI models from text or existing images. Video generation can use text, images, multiple images, or keyframes.

In plain words
What is it for?
Use it to make images, edit images, create videos from descriptions, animate an image, or build a video from several images or keyframes.
Why use it?
It provides a defined way to create or transform visual media and save the results locally.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool; positional $N argument.

Good fit Use it to make images, edit images, create videos from descriptions, animate an image, or build a video from several images or keyframes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/guihai24/openskills/agnes-ai
Install

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.

Any agent
npx skills add guihai24/openskills --skill agnes-ai
Clone the repo
git clone --depth 1 https://github.com/guihai24/openskills

Made for: Claude Code.

Wrote 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.

agentmods badge for agnes-ai

README.md
[![agentmods](https://agentmods.dev/badge/skills/guihai24/openskills/agnes-ai/github.svg)](https://agentmods.dev/skills/guihai24/openskills/agnes-ai)
Your own site
<a href="https://agentmods.dev/skills/guihai24/openskills/agnes-ai"><img src="https://agentmods.dev/badge/skills/guihai24/openskills/agnes-ai/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.

agentmods 80×15 button for agnes-ai

Your own site · 80×15
<a href="https://agentmods.dev/skills/guihai24/openskills/agnes-ai"><img src="https://agentmods.dev/badge/skills/guihai24/openskills/agnes-ai.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 224 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,445 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00224 $0.01445
Opus 5 $0.00112 $0.00723
Sonnet 5 $0.00045 $0.00289
Haiku 4.5 $0.00022 $0.00145

Measured 9d ago against content hash 9f1012060dcb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

agnes-ai scanned grade B with 1 finding 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.

The scan reads SKILL.md. This mod also ships 7 executable files (bin/_image.py, bin/_video.py, bin/generate-image.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

> ~/.config/agnes-ai/config && chmod 600 ~/.config/agnes-ai/config # 2) config file
skills/agnes-ai/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agnes AI — Image & Video Generation

Generate visual media through the Agnes AI API:

  • Imagesagnes-image-2.1-flash (text-to-image, image-to-image)
  • Videosagnes-video-v2.0 (text / image / multi-image / keyframe; asynchronous)

Setup

Needs an Agnes AI API key (get one at https://agnes-ai.com → API Platform). Provide it either way:

export AGNES_API_KEY="your-key"                                  # 1) environment variable
mkdir -p ~/.config/agnes-ai && printf 'AGNES_API_KEY=your-key\n' \
  > ~/.config/agnes-ai/config && chmod 600 ~/.config/agnes-ai/config  # 2) config file

Optional: AGNES_OUTPUT_DIR (where results are saved, default ~/agnes-output).

Workflow

  1. Decide image vs video from the request.
  2. Craft a vivid English prompt (see Prompt Crafting) — translate from any language.
  3. Run the matching script below.
  4. Read the output file to show the user the result.
  5. Report the saved local path (for video, also mention the duration).

Commands

Image

bash ${CLAUDE_SKILL_DIR}/bin/generate-image.sh "<english_prompt>" [size] [input_image]
Param Required Default Notes
prompt yes English works best
size no 1024x1024 e.g. 1024x768, 1024x1792
input_image no public URL / data URI / local path → runs image-to-image

Prints the saved .png path to stdout on success.

Video (asynchronous)

bash ${CLAUDE_SKILL_DIR}/bin/generate-video.sh "<english_prompt>" [image] [duration_seconds]
Param Required Default Notes
prompt yes English works best
image no one URL/path → image-to-video; comma-separate 2+ → multi-image / keyframe
duration_seconds no 5 ~3 / 5 / 10 / 18s; mapped to a valid frame count automatically

Advanced options (environment variables): AGNES_VIDEO_FPS (24), AGNES_VIDEO_WIDTH (1152), AGNES_VIDEO_HEIGHT (768), AGNES_VIDEO_MODE (keyframes), AGNES_VIDEO_NEGATIVE, AGNES_VIDEO_SEED.

Read the full file on GitHub · 121 lines

Files

What ships with it

8 files 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.

Changes

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.

  1. 9d ago First seen · 121 lines · 224 tokens per session scan B 9f1012060dcb

Subscribe to this mod's changes

agnes-ai is a skill published in the GitHub repository guihai24/openskills (2 stars, last pushed 4d ago), licensed MIT. It adds 224 tokens to every session and 1,445 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

webgl-holographic-foil

A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.

nexu-io/open-design · 41 tokens

general-video

Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…

heygen-com/hyperframes · 92 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

diagnostic-stem-delivery

Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.

HKUDS/OpenSpace · 23 tokens

chengfeng-check-updates

An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.

Agentchengfeng/chengfeng-videocut-skills · 120 tokens