Tools provided
Tools the agent exposes — your AI client calls them automatically when it needs them.
- app_get — Get detailed app info including input/output schemas and version historywrite
- app_list — Search and filter available apps on inference.shwrite
- app_run — Run an app on inference.sh. Creates a task that executes the app with the given input.write
- artifact_asset_delete — Permanently delete one file stored beside an artifact. Anything on the page still pointing at it stops loading, so delete only a file nothing references.write
- artifact_asset_list — List the files stored beside an artifact, with the URL each is referenced by and what the artifact is using against its budget.write
- artifact_asset_upload — Store an image, video, audio file, font or PDF beside an artifact and get back the URL its page references it by. Use this instead of a data: URI for anything sizeable: a data URI costs a third more than the bytes it carries, and a page has a 16 MiB ceiling. The page must be published with the "assets" capability or its CSP will refuse to load the file. Uploading the same bytes twice returns the asset already there.write
- artifact_comments — Read the comment threads people left on an artifact. Each thread says whether it was sent to you: you may reply to and resolve those, and only those. Threads not sent to you are other people's conversations — read them for context, mention them to the user if they need action, but do not answer them.write
- artifact_get — Get an artifact's metadata and page source by id, short id, or namespace/name[@version]write
- artifact_guidance — Everything needed to write a good artifact page, assembled in one call: the page contract plus the skills that carry the detail, resolved from the registry so they are always the current version. Call this BEFORE writing a page. Narrow it with topics; omit topics for all of them.write
- artifact_list — List artifacts you own or that were shared with you, newest firstwrite
- artifact_publish — Publish a self-contained HTML(+JS) or Markdown page as an artifact: a live page at a private URL that can be shared with a team, an org, or publicly, and that updates in place when published again. Pass artifact_id (or reuse the same name) to publish a new version. Returns the artifact id, url, and version. ## Before you write the page Load the skill for what you are about to build, with whichever skill tool this session has (`skill_get`, `skill_use`, or `belt skill use infsh/<name>`): - `belt-write
- artifact_reply — Reply into one comment thread on an artifact. Only works on a thread that was sent to you. Your reply is shown as written by you on behalf of the person who sent the thread. Say what you changed, briefly; if you made the change, resolve the thread afterwards.write
- artifact_resolve — Mark a comment thread resolved once you have acted on it: the change is made, or you established none was needed. Only works on a thread that was sent to you. Do not resolve feedback you did not act on, and leave a thread open while the person still needs an answer from you.write
- knowledge_create — Create a new knowledge entry (concept, observation, preference, reference, etc.)write
- knowledge_delete — Delete a knowledge entry by IDdestructive
- knowledge_get — Get detailed information about a knowledge entry by namespace/name or IDwrite
- knowledge_list — List your knowledge entries, optionally filtered by typewrite
- knowledge_search — Search your knowledge entries by querywrite
- mcp_connect — Initiate a connection to an MCP server. For OAuth servers, returns an authorization URL to open in a browser.write
- mcp_disconnect — Remove connection to an MCP serverdestructive
- mcp_get — Get details about an MCP server including connection statuswrite
- mcp_list — Browse available MCP servers that can be connected towrite
- mcp_run — Call a tool on a connected MCP server. The server must be connected first via mcp_connect.write
- mcp_search — Search available MCP servers by querywrite
- mcp_tools — List available tools on a connected MCP server, or get details for a specific toolwrite
- skill_files — List supplementary files for a skill (references, scripts, etc.)write
- skill_search — Search the public skill storewrite
- skill_store — Browse approved skills in the public skill storewrite
- skill_upload — Create or update a skill with SKILL.md content and optional supporting fileswrite
- skill_use — Fetch a skill's assembled SKILL.md content. Tries the inference.sh store first, falls back to GitHub. Returns the full skill content for the agent to consume.write
- skill_view — View a specific supplementary file from a skill's manifestwrite
- task_cancel — Cancel a running or queued taskdestructive
- task_get — Get status and output of a taskwrite
- task_list — List your tasks on inference.shwrite
- task_logs — Get execution logs for a taskwrite
