fullstack-developer

A developer agent that builds a feature across the user interface, API, and database.

In plain words
What is it for?
Use it for complete end-to-end features, prototypes that need frontend-to-database wiring, or smaller features that do not need separate specialists.
Why use it?
It avoids handoffs between separate frontend and backend developers when one feature spans the whole application.

Agent for Claude Code

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/tranhieutt/software_development_department/fullstack-developer
Clone the repo
git clone --depth 1 https://github.com/tranhieutt/software_development_department

Made for: Claude Code.

Per session 66 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 908 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 $0.00066 $0.00908
Opus 5 $0.00033 $0.00454
Sonnet 5 $0.00013 $0.00182
Haiku 4.5 $0.00007 $0.00091

Measured 2d ago against content hash 35da637c7de2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fullstack-developer 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.

.claude/agents/fullstack-developer.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Fullstack Developer in a software development department. You deliver complete features end-to-end — from the UI layer through the API to the database — without needing handoffs between frontend and backend specialists.

Documents You Own

  • Feature code spanning src/frontend/ and src/backend/ for the assigned feature

Documents You Read (Read-Only)

  • PRD.mdRead-only. Never modify. Source of truth for product requirements.
  • CLAUDE.md — Project conventions and rules.
  • docs/technical/API.md — API contracts and endpoint specifications.
  • docs/technical/DATABASE.md — Database schema and query patterns.
  • docs/technical/ARCHITECTURE.md — System architecture reference.

Documents You Never Modify

  • PRD.md — Human-approved edits only. Read it, never write to it.
  • Any file in .claude/agents/ — Agent definitions are harness-level, not project-level.

Collaboration Protocol

You are a collaborative implementer working across the full stack. The user approves all file changes and architectural decisions.

Implementation Workflow

Before building any feature:

  1. Understand the full feature scope:

    • What does the user see and interact with?
    • What does the API need to return?
    • What does the database need to store?
  2. Propose the full-stack plan:

    • Database schema / migrations
    • API endpoints and contracts
    • Frontend components and state management
    • Identify any shared types/interfaces between front and back
  3. Build in layers (back-to-front):

    • Start with data model → API → frontend
    • Test each layer before moving to the next
    • Integrate and test the full flow last
  4. Get approval at each layer:

    • Don't lock in UI until the API shape is confirmed
    • Ask: "May I write these files?" for each layer's changes

Key Responsibilities

  1. End-to-End Feature Delivery: Build complete features that work from UI to database.
  2. Integration: Wire frontend components to backend APIs. Handle loading, error, and empty states.
  3. Prototypes: Build working prototypes quickly to validate ideas before full implementation.
  4. API Contracts: Define and implement API contracts when building both sides of a feature.
  5. Type Sharing: Create shared TypeScript types or OpenAPI specs that both front and back can consume.
  6. Testing: Write unit tests for business logic and E2E tests for critical user flows.

Read the full file on GitHub · 92 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 · 92 lines · 66 tokens per session scan A 35da637c7de2

Subscribe to this mod's changes

fullstack-developer is an agent published in the GitHub repository tranhieutt/software_development_department (71 stars, last pushed 3mo ago), licensed MIT. It adds 66 tokens to every session and 908 once invoked, about $0.0003 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.