Agnes Free Model Skills
Three skills call the free Agnes AI models: chat, images and video through Python scripts and a key from an environment variable
- 202 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Prompts, images and the key go to the external Agnes AI service, and the scripts download results into a local folder
- The key is read from environment variables and leaks into output if printed or saved to shell history by mistake
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/agnes-free-model-skillsDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Prompts, images and the key go to the external Agnes AI service, and the scripts download results into a local folder
- The key is read from environment variables and leaks into output if printed or saved to shell history by mistake
This is third-party code. Review the repository files before installing.
What it does
A set of three skills for Codex and other agents that call the free Agnes AI models. `agnes-free-text` calls the Agnes-2.0-Flash text model: chat, streaming replies, coding help and tool-calling experiments. `agnes-free-image` works with Agnes Image 2.1 Flash: a picture from a description, editing or image-based generation with the result downloaded. `agnes-free-video` uses Agnes-Video-V2.0: it creates an asynchronous task, polls it and downloads the finished video. Each skill has a Python script (`agnes_text.py`, `agnes_image.py`, `agnes_video.py`), an API reference and an `agents/openai.yaml` file. The agent activates a skill on requests such as "use the free model" or "Agnes image". The key is read from the `AGNES_API_KEY` variable (`AGNES_TOKEN` as a fallback), the API address can be overridden through `AGNES_API_BASE`, and the `--dry-run` flag checks the request shape without calling the API.
Who it is for. People with an Agnes AI key who want an agent to call the free text, image and video models itself instead of typing API requests by hand.
Good fit when
- You want a free text answer or code, and the Agnes-2.0-Flash model with streaming fits
- A cover or illustration comes from a description or a source picture and the result is downloaded to a folder
- A short clip is ordered from the video model and the script waits for it and saves the file itself
- You want to check the shape of an Agnes API request in advance without spending quota: the `--dry-run` flag
Not a fit when
- You need another model or vendor: the skills work only with the Agnes AI API
- You have no Agnes AI key: without `AGNES_API_KEY` the scripts do nothing
- Private material cannot go to a third party: prompts and images go to an external service
- You need guaranteed video quality and stable timing: free models may lag behind paid ones
Example request
Use the free Agnes model: make a light, tech-style illustration for an article cover about skills and download the resultLimitations
- An Agnes AI key is needed in the `AGNES_API_KEY` or `AGNES_TOKEN` variable, and the repository has none. Keep the key out of skills, scripts and shell history.
- The skills wrap a third-party API: terms, free-tier limits and model availability are set by Agnes AI, not the repository.
- Video is created asynchronously and the task status has to be polled, which the script does with the `--wait` flag.
- The README is in Chinese, with an English version in `README.en.md`.
How to disable. Delete the `agnes-free-text`, `agnes-free-image` and `agnes-free-video` folders from `~/.codex/skills/` or your agent's skills directory. Remove the key from the environment with `unset AGNES_API_KEY` and from shell profile files.
FAQ
How do I install the Agnes skills in Codex?
Copy the needed folders: `cp -R agnes-free-text ~/.codex/skills/`, plus `agnes-free-image` and `agnes-free-video`. Then set the key with `export AGNES_API_KEY="..."`.
Where do I get the key and how do I set it?
The Agnes AI service issues the key. The scripts read it from `AGNES_API_KEY`, with `AGNES_TOKEN` as a fallback. The repository contains no keys, and they should stay out of skills and shell history.
How do I make a video and wait for the result?
With `python3 agnes-free-video/scripts/agnes_video.py create --prompt "..."`, then `status --task-id <id> --wait --download-dir downloads`: the script polls the task and downloads the file.
How do I check the scripts without calling the API?
Run `python3 -m py_compile` on the three scripts and `--help` on each, and a text request can be run with `--dry-run` without calling the API.
Does the set suit agents other than Codex?
The skills install as ordinary folders with `SKILL.md`, and the README allows use in any runtime that reads a `SKILL.md` file. The detailed install is written for Codex.
Discussion
No questions or reviews yet.
Related
SkillsA Python script calls the Agnes AI API for text, images and video from a prompt, a photo or keyframes, and polls for the result
Scenario Agent Skills
scenario-labs-skills
Skills for the paid Scenario service: images, video, audio and 3D from an agent, model and price selection before spending, sets for game assets and brands
A skill that takes an agent from a generated picture to a game asset: sprites, video-to-frames animation and pre-release checks
A skill collection guides AI agents through Blender modeling, materials, animation and asset checks using supplied Python scripts.
Three skills for the Meshy CLI: the agent makes 3D models from text and photos, textures them and prepares them for 3D printing
The official SpicyAPI skill: an agent runs image, video and audio generation tasks through the MCP server, CLI or SDK
README in short
The README says the repository holds only skill files, API references and helper scripts, with no keys or outputs. It has a table of three skills with models and trigger phrases, install by copying, key setup, a script check, examples for text, image and video, and a list of safety boundaries.
README badge
Original SKILL.md
--- name: agnes-free-text description: Call the free Agnes text model API for chat completions, streaming answers, coding help, tool-calling experiments, and OpenAI-compatible text generation. Use when the user asks for 免费文本, 免费的文本模型, free text API, Agnes text, Agnes-2.0-Flash, free LLM calls, or wants to use a free chat/completion model through an Agent skill. --- # Agnes Free Text Use this skill to call Sapiens AI's Agnes-2.0-Flash text model through the Agnes API. ## Credential Rule Read the API key from the environment. Do not hardcode keys in prompts, scripts, skill files, commits, or shell history. Preferred variable: ```bash export AGNES_API_KEY="..." ``` The helper also accepts `AGNES_TOKEN` as a fallback. ## Quick Start Run a normal chat completion: ```bash python3 scripts/agnes_text.py chat \ --prompt "用三句话解释 Agent 为什么需要工具调用" ``` Use a system prompt and save the raw response JSON: ```bash python3 scripts/agnes_text.py chat \ --system "You are a concise technical writer." \ --prompt "Explain tool calling for a beginner." \ --output-json ./outputs/agnes-free-text/response.json ``` Pass tool definitions from JSON: ```bash python3 scripts/agnes_text.py chat \ --prompt "Decide whether a weather tool is needed." \ --tools-json ./tools.json \