← All blueprints

Multimodal Coding Agent Team Custom

blueprint · 3 agents
50000★ stars

What it does

Pairs a vision-capable agent with a coding agent and an executor: paste a screenshot of a problem, the vision agent extracts the task, the coder writes the solution, and the sandbox runs it.

From the community

Shubhamsaboo/awesome-llm-appsopen-source example · Apache-2.0 · indexed by SocketCatview source ↗

Agent flow

1 · Vision agent
Read the screenshot
multimodal
2 · Coder
Write the solution
no tools · reasoning
3 · Executor
Run & verify
code sandbox
get the code
View the source on GitHub ↗

This blueprint lives in its authors' repository. SocketCat indexes it and links you to the real thing.

More in Coding & QA

Browse all →

E2E Test Author

com.socketcat/e2e-test-author
LangGraph

Turns a user story into browser tests: plans the scenarios, writes Playwright code, runs it against the real page, and self-heals until it passes for the right reason.

★ 15203 servers
⑂ 214

Code Reviewer

com.socketcat/code-reviewer
LangGraph

Diff-aware multi-pass reviewer: finds bugs, then a skeptic agent verifies each before reporting.

★ 13001 server
⑂ 210

Bug Reproducer

com.socketcat/bug-reproducer
LangGraph

Reads a GitHub issue and loops a coder against a verifier until it produces a minimal failing test that actually reproduces the bug.

★ 12563 servers
⑂ 187