surface-first-development

A development method that starts with the part people use—such as an app screen, command-line tool, or API—and builds a working prototype before deciding how it works inside.

In plain words
What is it for?
Use it to shape an app, tool, CLI, API, automation, or feature from its user interactions inward.
Why use it?
It helps clarify how a product should behave before time is spent choosing technology or writing internal code.

Skill for Claude CodeCodex

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 skills/pyros-projects/limitless/sfd
Any agent
npx skills add pyros-projects/limitless --skill sfd
Clone the repo
git clone --depth 1 https://github.com/pyros-projects/limitless

Made for: Claude Code, Codex.

Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,902 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 $0.00045 $0.02902
Opus 5 $0.00023 $0.01451
Sonnet 5 $0.00009 $0.00580
Haiku 4.5 $0.00005 $0.00290

Measured 2d ago against content hash 8d2ec68530de, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

surface-first-development 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.

plugins/pyro-kit/docs/reference/sfd/SKILL.md · 301 lines

How it starts

The opening of the file, as written. The whole thing — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Surface-First Development

Reference

If anything in this skill feels unclear, underspecified, or in tension with a real project situation, stop and read references/whitepaper-v0.6.md before improvising. Treat that whitepaper as the authoritative reference for the methodology.

If this SKILL.md and the whitepaper ever feel misaligned, follow the whitepaper and then update the skill so the drift is removed.

Triggers

  • User says "let's build", "I want an app/tool/CLI/API that...", "I have an idea for..."
  • User describes a product, feature, or tool without specifying architecture or internals
  • User says "surface first", "click dummy", "show me what it would look like", "prototype this"
  • User says "SFD", "surface-first"
  • User wants to start a new project or feature and hasn't locked in a tech approach yet
  • User asks "how should this work?" or "what would the UX be?" or "what would the workflow look like?"

Purpose

You are following the Surface-First Development methodology. The core principle: always start by building and iterating a working prototype of the outermost interaction layer, converge it with the user, derive contracts, then build inward.

Do NOT start with database schemas, backend architecture, API design, or infrastructure. Start with what the user will actually see, touch, type, or call.

Operating Stance

  • Move from concrete artifact to critique, not from abstract discussion to specification.
  • Make reasonable product decisions without asking the user to design the system for you.
  • Prefer a fast, interactive prototype over a polished explanation of a prototype.
  • Treat the user as the evaluator and steering function; your job is to generate proposals they can react to.
  • Keep internals provisional until the surface is accepted.

First Move

When this skill is triggered:

  1. Identify the primary interaction surface.
  2. Build the smallest believable prototype that covers the critical path.
  3. Put it in front of the user quickly.
  4. Ask for critique of behavior and flow, not implementation.

Read the full file on GitHub · 301 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 301 lines · 45 tokens per session scan A 8d2ec68530de

Subscribe to this mod's changes

surface-first-development is a skill published in the GitHub repository pyros-projects/limitless (9 stars, last pushed 20d ago), licensed MIT. It adds 45 tokens to every session and 2,902 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.