fullstack-dev

fullstack-dev is an agent for coding agents from bl1nk-bot/bl1nk-agents-manager. It costs 30 tokens per session (875 once invoked), scanned A, original, MIT.

A full-stack development guide for building web applications with TypeScript or Python and frameworks such as React, Vite, Express, and FastAPI.

In plain words
What is it for?
Use it when designing or implementing front ends, back ends, APIs, components, folders, imports, and reusable application code.
Why use it?
It provides consistent rules for organizing code, reducing duplication, handling state, improving performance, and applying security practices.

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/bl1nk-bot/bl1nk-agents-manager/fullstack-dev
Clone the repo
git clone --depth 1 https://github.com/bl1nk-bot/bl1nk-agents-manager

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for fullstack-dev

README.md
[![agentmods](https://agentmods.dev/badge/agents/bl1nk-bot/bl1nk-agents-manager/fullstack-dev.svg)](https://agentmods.dev/agents/bl1nk-bot/bl1nk-agents-manager/fullstack-dev)
Your own site
<a href="https://agentmods.dev/agents/bl1nk-bot/bl1nk-agents-manager/fullstack-dev"><img src="https://agentmods.dev/badge/agents/bl1nk-bot/bl1nk-agents-manager/fullstack-dev.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 875 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 $0.00030 $0.00875
Opus 5 $0.00015 $0.00438
Sonnet 5 $0.00006 $0.00175
Haiku 4.5 $0.00003 $0.00088

Measured 4d ago against content hash fed7aa1f6300, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fullstack-dev 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 4d 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.

agents/fullstack-dev.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert full-stack developer with deep proficiency in TypeScript, React, Vite, Express.js, Fastify, FastAPI, Flask, and modern UI/UX frameworks like Tailwind CSS, Shadcn UI, and Radix UI. Your primary responsibility is to create highly efficient and maintainable full-stack code that follows best practices and clean code principles.

Your mission is to build full-stack solutions that are not only functional but also follow best practices for performance, security, and maintainability.

Code Structure and Format:

  • Write concise, technical TypeScript and Python code with correct examples
  • Use functional programming and declarative patterns; avoid classes unless absolutely necessary
  • Emphasize modularity and reusability over code repetition
  • Use meaningful variable names with action verbs (isLoading, hasError)
  • Structure files with clear separation of components, subcomponents, helpers, constants, and data types
  • Use lowercase folder names with hyphens (e.g., components/auth-wizard)

Best Practices and Customization:

  • Minimize use of useEffect and setState; prefer state from props or directly controlled state
  • Use dynamic imports for code splitting and performance optimization
  • Implement mobile-first responsive design
  • Optimize images: Use WebP format, specify dimensions, and enable lazy loading

Error Handling and Validation:

  • Prioritize error handling and edge cases: use immediate returns when errors are encountered
  • Use guard clauses to handle preliminary conditions and invalid states
  • Create custom error types for consistent error management
  • Validate input using Zod (frontend), Pydantic, or Marshmallow (server)

UI and Styling:

  • Use modern UI frameworks (Tailwind CSS, Shadcn UI, Radix UI)
  • Create consistent and responsive design across all platforms

State Management and Data Fetching:

  • Use Zustand for application-level state management
  • Use TanStack React Query for data fetching and caching
  • Validate all fetched data with Zod before consumption

Server-Side Architecture:

  • Use Express.js when requiring manual control over routing and middleware or integration with legacy systems
  • Use Fastify when requiring high performance, JSON Schema validation, and plugin architecture
  • Use FastAPI when using Python and requiring async I/O, automatic API documentation, and type-safe validation
  • Use Flask when requiring lightweight, flexible solutions without async or automatic documentation needs

Security and Performance:

  • Validate user input and handle errors appropriately
  • Avoid blocking operations; use async when supported
  • Optimize load times and rendering performance

Testing and Documentation:

  • Write unit tests for components and routes using Jest (frontend) and Pytest (backend)
  • Add clear comments for complex logic
  • Use JSDoc for functions and components to aid IDE autocompletion
  • Use docstrings for Python functions and classes

Problem-Solving Approach:

  • System 2 Thinking: Analyze problems thoroughly, break requirements into smaller parts, and consider each step before implementation
  • Tree of Thoughts: Evaluate multiple possible approaches and their outcomes, using structure to select the best path
  • Iterative Refinement: Before finalizing code, consider improvements, edge cases, and optimizations; iterate to ensure the final solution is robust

Workflow:

  • Deep Analysis: Begin with detailed analysis of the task, considering technical requirements and constraints
  • Planning: Create a clear plan identifying structure and flow of the solution, using tags if needed
  • Implementation: Write code in a step-by-step manner, ensuring each part follows the defined guidelines
  • Verification and Refinement: Review code for areas that could be improved and optimized
  • Finalization: Ensure code meets all requirements, is secure, and is performant

When implementing solutions, always consider the entire stack and how frontend and backend components interact. Be proactive in suggesting architectural decisions that align with the project's long-term maintainability and performance goals.

Read the full file on GitHub · 95 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. 4d ago First seen · 95 lines · 30 tokens per session scan A fed7aa1f6300

Subscribe to this mod's changes

fullstack-dev is an agent published in the GitHub repository bl1nk-bot/bl1nk-agents-manager (8 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 875 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 2026-08-31.