spec-driven-development

spec-driven-development is a skill for Claude Code, Codex from GuillemRoca/agent-skills-android. It costs 41 tokens per session (937 once invoked), scanned A, original, MIT.

A workflow for writing a structured specification before building an Android project or feature. Android is Google's platform for mobile and related devices; the specification records the agreed goals, scope, technical choices, and checks.

In plain words
What is it for?
Use it for new Android projects or features that span several files or layers, especially when requirements are ambiguous or come from multiple people.
Why use it?
Unclear requirements can lead to rework, scope growth, and different interpretations of the feature. A shared specification gives implementation decisions a common reference.

Skill for Claude CodeCodex

Part of the agent-skills-android plugin — 29 skills, 7 commands, 3 agents, 1 hook shipped together

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/guillemroca/agent-skills-android/spec-driven-development
Any agent
npx skills add GuillemRoca/agent-skills-android --skill spec-driven-development
Clone the repo
git clone --depth 1 https://github.com/GuillemRoca/agent-skills-android

Made for: Claude Code, Codex.

Or install agent-skills-android, the plugin that ships this one along with the rest of its 29 skills, 7 commands, 3 agents, 1 hook.

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 spec-driven-development

README.md
[![agentmods](https://agentmods.dev/badge/skills/guillemroca/agent-skills-android/spec-driven-development.svg)](https://agentmods.dev/skills/guillemroca/agent-skills-android/spec-driven-development)
Your own site
<a href="https://agentmods.dev/skills/guillemroca/agent-skills-android/spec-driven-development"><img src="https://agentmods.dev/badge/skills/guillemroca/agent-skills-android/spec-driven-development.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 937 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 $0.00041 $0.00937
Opus 5 $0.00020 $0.00468
Sonnet 5 $0.00008 $0.00187
Haiku 4.5 $0.00004 $0.00094

Measured 4d ago against content hash 766345d5729a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-driven-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 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.

skills/spec-driven-development/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec-Driven Development

Overview

Write a structured specification before writing code. The spec becomes the shared source of truth — a development contract that prevents misalignment, scope creep, and wasted effort. Every implementation decision traces back to the spec.

When to Use

  • Starting a new Android project or module
  • Adding a feature that spans multiple files or layers
  • Requirements are ambiguous or come from multiple stakeholders
  • Before writing a tasks/plan.md

Skip when: Single-line fixes or changes that are unambiguous and self-contained.

Core Process

Phase 1: Specify

  1. Ask clarifying questions before writing anything:

    • What problem does this solve? Who is the user?
    • Which features are in scope? Which are explicitly out?
    • What is the tech stack? (minSdk, target SDK, Compose vs XML, DI framework)
    • What are the boundaries? (offline support? accessibility? tablet?)
  2. Write SPEC.md with these sections:

# Feature Name — Specification

## Objective
What we're building and why. One paragraph.

## Commands
Key Gradle tasks and how to use them:
- `./gradlew assembleDebug` — build debug APK
- `./gradlew test` — run unit tests
- `./gradlew connectedAndroidTest` — run instrumented tests
- `./gradlew lint` — run Android Lint

## Project Structure
Where new code lives in the module hierarchy:
- `:app` — main application module
- `:feature:feature-name` — new feature module
- `:core:data` — data layer (repositories, data sources)
- `:core:domain` — domain layer (use cases, models)

## Code Style
- Kotlin with Jetpack Compose for UI
- MVVM/MVI architecture with ViewModel + StateFlow
- Hilt for dependency injection
- Coroutines + Flow for async operations
- Material 3 design system

## Testing Strategy
- Unit tests: JUnit5 + MockK for ViewModels, use cases, repositories
- UI tests: Compose test rules for screen-level testing
- Integration tests: Room in-memory database, MockWebServer
- Target: critical paths covered, not arbitrary coverage %

## Boundaries
What is explicitly NOT in scope:
- [ ] List exclusions here

Read the full file on GitHub · 116 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 · 116 lines · 41 tokens per session scan A 766345d5729a

Subscribe to this mod's changes

spec-driven-development is a skill published in the GitHub repository GuillemRoca/agent-skills-android (2 stars, last pushed 2mo ago), licensed MIT. It adds 41 tokens to every session and 937 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.