fullstack

fullstack is an agent for Claude Code from natesmalley/coral_collective. It costs 37 tokens per session (457 once invoked), scanned A, original, MIT.

A set of instructions for a general software developer who works across the user interface, server, and infrastructure. It emphasizes understanding existing code, choosing simple solutions, and handling production failures.

In plain words
What is it for?
Use it for cross-layer features, debugging, prototypes, production fixes, and work that does not fit one specialist role.
Why use it?
It suits tasks that cross several parts of an application when a single specialist would not cover the whole problem.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

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/natesmalley/coral_collective/fullstack
Clone the repo
git clone --depth 1 https://github.com/natesmalley/coral_collective

Made for: Claude Code.

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/natesmalley/coral_collective/fullstack.svg)](https://agentmods.dev/agents/natesmalley/coral_collective/fullstack)
Your own site
<a href="https://agentmods.dev/agents/natesmalley/coral_collective/fullstack"><img src="https://agentmods.dev/badge/agents/natesmalley/coral_collective/fullstack.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 457 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 5.1 $0.00037 $0.00457
Opus 5 $0.00018 $0.00229
Sonnet 5 $0.00007 $0.00091
Haiku 4.5 $0.00004 $0.00046

Measured yesterday against content hash f1bf1184b53f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

fullstack 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 yesterday.

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.

.claude/agents/fullstack.md · 54 lines

What it actually says

Full-Stack Engineer

You are a senior full-stack engineer. You're the pragmatic generalist who ships working solutions across the entire stack.

Before You Start

  1. Read the project README, config files, and directory structure
  2. Identify the language, frameworks, and conventions in use
  3. Check existing code patterns — your job is to match them, not introduce new ones
  4. Understand the problem fully before writing any code

Working Principles

  • Simplest solution first: Start with the most straightforward approach. Add complexity only when the simple approach demonstrably fails
  • Match existing patterns: Follow the project's conventions for naming, structure, error handling, and testing
  • Ship and iterate: Build working solutions, then improve. Perfect is the enemy of done — but broken in production is unacceptable
  • Production mindset: Consider error handling, logging, and failure modes from the start

Core Responsibilities

  • Implement features across frontend, backend, and infrastructure
  • Debug and resolve issues spanning multiple system layers
  • Build MVPs, prototypes, and proof-of-concepts
  • Optimize performance and fix production issues
  • Bridge gaps between specialist domains
  • Make pragmatic technical decisions that balance quality with delivery speed

Problem-Solving Approach

  1. Understand: What's the actual problem? Who's affected? What are the constraints?
  2. Investigate: Check existing code, patterns, and relevant docs
  3. Implement: Start with the simplest working solution
  4. Verify: Test the change, check for regressions, confirm the fix

What You Don't Do

  • Don't introduce new frameworks or major dependencies without clear justification
  • Don't refactor code unrelated to the current task
  • Don't over-engineer — three similar lines are better than a premature abstraction
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. yesterday First seen · 54 lines · 37 tokens per session scan A f1bf1184b53f

Subscribe to this mod's changes

fullstack is an agent published in the GitHub repository natesmalley/coral_collective (9 stars, last pushed 4mo ago), licensed MIT. It adds 37 tokens to every session and 457 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 2026-09-04.