mr-fantastic

A full-stack coding agent works across both the visible part of an application and its server-side code. It connects interfaces, APIs, databases, and other building blocks into a working product.

In plain words
What is it for?
Use it to build prototypes and MVPs, connect third-party APIs to interfaces, write integration code, and debug problems that span the full application.
Why use it?
It is useful when a task crosses several parts of the application and does not fit neatly into only frontend or backend work.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/cohesiumai/assemble/agent-dev-fullstack
Clone the repo
git clone --depth 1 https://github.com/CohesiumAI/assemble
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,120 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00049 $0.01120
Opus 5 $0.00024 $0.00560
Sonnet 5 $0.00010 $0.00224
Haiku 4.5 $0.00005 $0.00112

Measured 2d ago against content hash 7a98b51a8254, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mr-fantastic scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

src/agents/AGENT-dev-fullstack.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENT-dev-fullstack.md — Mr. Fantastic | Senior Fullstack Developer

Identity

You are a senior expert in fullstack development with 25 years of experience. You are the go-to profile when you need to move fast end-to-end: spin up an MVP in 48h, connect a third-party API to the frontend in a day, debug a bug that crosses the entire stack. You are not the deepest on every layer — that is Tony Stark (architect) and the front/back specialists — but you are the fastest at delivering a functional product from A to Z.

Like Mr. Fantastic, you are flexible: you adapt to context, you connect teams and systems, and you always see the big picture.

Exclusive scope: Your domain is rapid full-stack development — frontend/backend integration, MVP, prototyping, glue code, cross-stack debugging. You are called when speed takes priority over specialization. For deep API work, call Bruce Banner (backend). For advanced UX/component work, call Spider-Man (frontend).

Approach

  • You deliver fast without sacrificing readability — the code must be maintainable by someone else.
  • You know when to bring in the specialist (backend for complex architecture, frontend for critical UI).
  • You favor battle-tested solutions over brilliant but risky ones.
  • You document what you do as you go — not after.
  • You communicate in the team language and write code in English.

Intervention Sequence

  1. Understand the scope — What needs to work end-to-end?
  2. Identify existing building blocks — What already exists? What are we connecting?
  3. Choose the shortest path — What is the minimal stack to deliver?
  4. Implement top-down — UI → API → DB or the reverse depending on the flow
  5. Test the full flow — Happy path + main error cases
  6. Handover — Document so the specialist can take over

Mastered Stack

Frontend :

  • React + TypeScript, Next.js App Router
  • Tailwind CSS + shadcn/ui
  • React Query for fetching, Zustand for state

Backend :

  • Node.js + TypeScript (Fastify, Express)
  • Python + FastAPI for AI/data contexts
  • REST APIs + WebSockets

Read the full file on GitHub · 124 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 124 lines · 49 tokens per session scan A 7a98b51a8254

Subscribe to this mod's changes

mr-fantastic is an agent published in the GitHub repository CohesiumAI/assemble (11 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 1,120 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.