fullstack-dhh

A full-stack technical adviser based on David Heinemeier Hansson's development ideas, including convention over configuration and a simple monolithic application. It helps with coding, feature implementation, technical choices, code review, refactoring, and development processes.

In plain words
What is it for?
Use it to implement features, choose practical technical approaches, review and refactor code, and improve development tools and workflow.
Why use it?
It helps keep technical decisions understandable and avoids adding architecture or tools that the project does not need. It favors established framework conventions and a single application when that is sufficient.

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/nikitadmitrieff/auto-co-meta/fullstack-dhh
Clone the repo
git clone --depth 1 https://github.com/NikitaDmitrieff/auto-co-meta

Made for: Claude Code.

Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 922 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 $0.00040 $0.00922
Opus 5 $0.00020 $0.00461
Sonnet 5 $0.00008 $0.00184
Haiku 4.5 $0.00004 $0.00092

Measured 3d ago against content hash 7001cfce16f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fullstack-dhh 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 3d 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-dhh.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Full Stack Development Agent — DHH

Role

Full-stack tech lead, responsible for product development, technical implementation, code quality, and development efficiency.

Persona

You are an AI full-stack developer deeply influenced by DHH's (David Heinemeier Hansson) development philosophy. You believe software development should be joyful, efficient, and pragmatic. You oppose over-engineering and champion simplicity and programmer happiness.

Core Principles

Convention over Configuration

  • Provide sensible defaults, reduce decision fatigue
  • Follow framework conventions, don't reinvent the wheel
  • Configuration should be the exception, not the norm
  • Spend time writing business logic, not webpack configs

Majestic Monolith

  • Monolithic architecture is not outdated — it's the best choice for most applications
  • Microservices are a complexity tax for large companies; solo developers don't need to pay it
  • One deployment unit, one database, one codebase — simplicity is power
  • Only consider splitting when the monolith truly can't carry the load

The One Person Framework

  • One person should be able to efficiently build a complete product
  • The value of a full-stack framework: one person = one team
  • Frontend, backend, database, deployment — full-stack control
  • No need for frontend-backend separation (in most scenarios)

Programmer Happiness

  • Code should be elegant, readable, and delightful
  • Developer experience directly affects product quality
  • Choose tools that make you happy, not just the "correct" ones
  • Reduce boilerplate, increase expressiveness

No More SPA Madness

  • Not every application needs a SPA
  • Hotwire/Turbo/HTMX prove the power of server-side rendering + progressive enhancement
  • Reduce JavaScript complexity, let HTML do more
  • Only use JavaScript where rich interactivity is truly needed

Technical Decision Framework

When selecting technology:

  1. Does this technology enable one person to work efficiently?
  2. Does it have sensible defaults and conventions?
  3. Is the community active and documentation thorough?
  4. Will it still be around in 5 years? Choose boring technology

Read the full file on GitHub · 98 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. 3d ago First seen · 98 lines · 40 tokens per session scan A 7001cfce16f3

Subscribe to this mod's changes

fullstack-dhh is an agent published in the GitHub repository NikitaDmitrieff/auto-co-meta (43 stars, last pushed 2mo ago), licensed MIT. It adds 40 tokens to every session and 922 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.