Coding Tools
TokenLab Agent Skills
Install TokenLab skills for images, video, audio, 3D, decisions, and API integration in Claude Code, Codex, or any agent
Let my agent set this up
Copy this task to an agent already running on your computer:
Read this guide and install the TokenLab Agent Skills I need in my current agent:
https://tokenlab.sh/docs/en/integrations/coding-agent-skill
Check my installed version and active configuration first.
Preserve existing accounts, providers, permissions and other settings.
Back up local files and show proposed changes.
Have me enter any API key locally; never ask for, print or paste it in chat.
Check configuration loading first.
Explain any paid request test separately before running it.What the skills do
A skill is a folder with a SKILL.md file that teaches an agent one job. The agent loads only the skill's name and description until a request matches, then reads the full instructions.
TokenLab skills cover a result, not a model. Ask for a product photo, a voiceover, or a 3D asset; the skill picks a model from the live TokenLab catalog, reads its model details, estimates the price, makes the call, and waits for async results.
The skills are free and MIT-licensed. The API calls they make are billed at the normal TokenLab price. The source is in tokenlab-skills.
Install
Add the marketplace and install the plugin:
/plugin marketplace add hedging8563/tokenlab-skills
/plugin install tokenlab@tokenlab-toolsSkill names are namespaced, for example /tokenlab:tokenlab-run. The plugin also adds the TokenLab MCP connections described in the repository README.
To confirm installation, ask the agent to list its available skills.
Paid calls need an API key. Create one in Console → API keys and set it as TOKENLAB_API_KEY in the environment that starts the agent. Never paste a key into a prompt.
Skill catalog
This table is generated from catalog.json in the skills repository. Operations are the TokenLab model operations a skill can call.
skill | group | operations |
|---|---|---|
tokenlab-run | foundation | — |
tokenlab-model-picker | foundation | — |
tokenlab-prompting | foundation | — |
tokenlab-product-photography | image | text-to-image, image-to-image, image-edit |
tokenlab-edit-image | image | image-edit, image-to-image |
tokenlab-restore-and-upscale | image | image-edit |
tokenlab-text-in-image | image | text-to-image, image-edit |
tokenlab-character-consistency | image | image-to-image, text-to-image, reference-to-video |
tokenlab-photoreal-stills | image | text-to-image |
tokenlab-logos-and-vectors | image | text-to-image, image-edit |
tokenlab-animate-image | video | image-to-video |
tokenlab-product-ad-video | video | image-to-video, reference-to-video, text-to-video |
tokenlab-keyframe-transition | video | start-end-to-video |
tokenlab-extend-video | video | video-extension |
tokenlab-edit-video | video | video-to-video |
tokenlab-motion-control | video | motion-control |
tokenlab-talking-avatar | video | image-to-video, tts |
tokenlab-cinematic-video | video | text-to-video, image-to-video |
tokenlab-voiceover | audio | tts |
tokenlab-transcribe-and-subtitle | audio | stt, translation |
tokenlab-music | audio | music |
tokenlab-image-to-3d-asset | 3d | image-to-3d, text-to-3d |
tokenlab-world-generation | 3d | world-generation |
tokenlab-decisions | decision | systemone |
tokenlab-api-integration | integration | chat |
tokenlab-native-endpoints | integration | chat, systemone |
tokenlab-cost-routing | integration | — |
tokenlab-openai-compatible-migration | integration | chat |
The Skills page shows each skill with the number of live models that serve its operations.
How model defaults stay current
A skill never depends on one fixed model. Each outcome skill lists a default model per stage, with alternatives and a low-cost option. The skills repository refreshes these defaults every day from the live TokenLab catalog.
Before each call, the skill reads the model's live details and supported fields with GET /v1/models/{model} and its price with GET /v1/models/{model}/pricing. When a model loses supply, the agent picks another model that serves the same operation.
To update an installation:
- Claude Code plugin:
/plugin marketplace update tokenlab-tools, then/plugin update tokenlab@tokenlab-tools. - Codex plugin:
codex plugin marketplace upgrade tokenlab-tools, thencodex plugin add tokenlab@tokenlab-tools. - Skills CLI:
npx skills update <skill-id> --projector--global, in the scope where you installed it.
Use skills with TokenLab MCP
Skills and MCP do different jobs and work well together:
- TokenLab MCP gives the agent callable tools such as
create_imageandget_task_status. - Skills give the agent the method: which model to pick, how to write the prompt, and how to check the result.
When the MCP server is connected, a skill can use its tools. Without MCP, the skill calls the HTTP API directly.
Example requests
Use the TokenLab product photography skill to put this bottle on a warm studio background in 1:1 and 9:16.Use the TokenLab API integration skill to add image generation to this Node.js app.
Read the current model details before choosing fields.
Keep the API key in TOKENLAB_API_KEY and add one runnable test.Help
For API or account questions, use in-app Support; review the preview and submit explicitly. For a particular request, start with Requests and follow the investigation guide. Report defects in a skill through GitHub Issues.