Agentplace

Find owned projects by name; follow pagination to resolve ambiguous names.

list_projects

List or get app Media, or import 1–20 public images in one batch. Use returned asset IDs and canonical URLs. Partial batches retain successful items; reconcile a lost reply before retrying. This does not publish the app.

manage_media

Open an existing authoring session or explicitly create an empty one. Reuse creationKey after a lost response; no model is started.

open_project_session

Read permitted project source, skills or the app's read-only Preview logs under logs/ (a project folder named logs is source/logs/), using line ranges for large files. A read without a range returns the start of a file; read the end of a log with viewRanges from the totalLines it reports.

read_files

Read one public website page with combined content, links, image candidates, branding and a temporary screenshot. Uses Agentplace credits with research consent. Request HTML only for a missing detail. Unknown outcomes must not be automatically retried.

firecrawl_scrape

Run a shell command on the app's saved source in Preview and wait for its result. The default limit is 30 seconds; set timeoutSeconds (max 45) for one slow step. Supported file changes are saved automatically. complete reports execution and changes separately; changes are saved, unchanged or not_saved. not_started means nothing ran; its message says why. failed means the outcome is unknown; tell the owner its message and read the affected files before running the command again. Repeating a call runs the command again, also after a lost reply.

execute_command

Keep the app's current saved state as one version in its history. Edits since the last checkpoint form that version. Call it when the app reaches a state worth returning to, such as a finished change that builds, and before a large or risky change; do not call it after every edit. Describe the state in a few words. unchanged means nothing changed since the last checkpoint.

checkpoint

Search permitted source, skills or Preview logs with regex; Preview logs are searched only with path "logs/". Inspect coverage before concluding a match is absent.

grep

Rewrite the full contents of a single file (replace the entire file content). WHEN TO USE: - You are making large, sweeping changes (e.g. rewriting a component, big refactor, many non-adjacent edits). - You want the final file to match your proposed content exactly. HOW TO CALL: - Provide "path" and the complete, final "content" for that file. - This tool replaces the entire file content (not a patch). Make sure the content includes all imports/exports and compiles. Read the file before you change it. The edit applies to the app's current saved text, and a save to another file never blocks it. Use UpdateFile for a new file or a full rewrite right after reading, because it replaces whatever is saved now; to change part of an existing file, use SearchReplace. The edit is saved when the call returns. After conflict, read the file again and make a new edit. After a failed or unconfirmed call, read the file to see whether the change is there before you edit again. A saved file is not a build or Preview check.

update_file

Retrieves and queries up-to-date documentation and code examples from Context7 for any programming library or framework. You must call 'Resolve Context7 Library ID' tool first to obtain the exact Context7-compatible library ID required to use this tool, UNLESS the user explicitly provides a library ID in the format '/org/project' or '/org/project/version' in their query. Do not call this tool more than 3 times per question. If you know the programming language the user is working in, pass it as `language` so the results match their setup.

query-docs

Resolves a package/product name to a Context7-compatible library ID and returns matching libraries. You MUST call this function before 'Query Documentation' tool to obtain a valid Context7-compatible library ID UNLESS the user explicitly provides a library ID in the format '/org/project' or '/org/project/version' in their query. Each result includes: - Library ID: Context7-compatible identifier (format: /org/project) - Name: Library or package name - Description: Short summary - Code Snippets: Number of available code examples - Source Reputation: Authority indicator (High, Medium, Low, or Unknown) - Benchmark Score: Quality indicator (100 is the highest score) - Versions: List of versions if available. Use one of those versions if the user provides a version in their query. The format of the version is /org/project/version. For best results, select libraries based on name match, source reputation, snippet coverage, benchmark score, and relevance to your use case. Selection Process: 1. Analyze the query to understand what library/package the user is looking for 2. Return the most relevant match based on: - Name similarity to the query (exact matches prioritized) - Description relevance to the query's intent - Documentation coverage (prioritize libraries with higher Code Snippet counts) - Source reputation (consider libraries with High or Medium reputation more authoritative) - Benchmark Score: Quality indicator (100 is the highest score) Response Format: - Return the selected library ID in a clearly marked section - Provide a brief explanation for why this library was chosen - If multiple good matches exist, acknowledge this but proceed with the most relevant one - If no good matches exist, clearly state this and suggest query refinements For ambiguous queries, request clarification before proceeding with a best-guess match. IMPORTANT: Do not call this tool more than 3 times per question. If you cannot find what you need after 3 calls, use the best result you have.

resolve-library-id