spec-driven-dev

spec-driven-dev is a skill for Claude Code from medy-gribkov/arcana. It costs 35 tokens per session (1,895 once invoked), scanned A, original, Apache-2.0.

A development workflow that turns vague ideas into written requirements, technical specifications, implementation plans, and quality checks before coding begins.

In plain words
What is it for?
Use it to write product briefs, define testable acceptance criteria, break work into tasks, and plan implementations.
Why use it?
It reduces misunderstandings and prevents unclear requirements from becoming rework or bugs.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Good fit Use it to write product briefs, define testable acceptance criteria, break work…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/medy-gribkov/arcana/spec-driven-dev
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.

Any agent
npx skills add medy-gribkov/arcana --skill spec-driven-dev
Clone the repo
git clone --depth 1 https://github.com/medy-gribkov/arcana

Made for: Claude Code.

Its marketplace also offers this one on its own, as the plugin spec-driven-dev/plugin install spec-driven-dev after adding the marketplace above.

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-dev

README.md
[![agentmods](https://agentmods.dev/badge/skills/medy-gribkov/arcana/spec-driven-dev.svg)](https://agentmods.dev/skills/medy-gribkov/arcana/spec-driven-dev)
Your own site
<a href="https://agentmods.dev/skills/medy-gribkov/arcana/spec-driven-dev"><img src="https://agentmods.dev/badge/skills/medy-gribkov/arcana/spec-driven-dev.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,895 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00035 $0.01895
Opus 5 $0.00017 $0.00948
Sonnet 5 $0.00007 $0.00379
Haiku 4.5 $0.00003 $0.00189

Measured 3d ago against content hash 726eff6da696, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

spec-driven-dev 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.

skills/spec-driven-dev/SKILL.md · 228 lines

How it starts

The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Specification-Driven Development

You are a specification architect. Convert vague ideas into precise, testable requirements. Plan before coding. Break work into parallelizable tasks with clear dependencies.

Core Principles

  1. Specifications drive code, not the reverse. Write the spec first. Code implements the spec.
  2. Ambiguity is a bug. Every unclear requirement gets a [NEEDS CLARIFICATION] marker.
  3. Research before design. Investigate unknowns before committing to architecture.
  4. Test-first ordering. Contracts, then tests, then implementation.
  5. Parallel by default. Mark independent tasks with [P] for concurrent execution.

Requirements Specification

BAD - Vague requirements:

## Feature: User Authentication
- Users should be able to log in
- Add social login
- Make it secure

GOOD - Structured spec with acceptance criteria:

## Feature: User Authentication

### User Stories
- As a new user, I can register with email/password so I have an account
- As a returning user, I can log in with email/password so I access my data
- As a user, I can log in with Google OAuth so I skip manual registration

### Acceptance Criteria
1. Registration validates: email format, password >= 12 chars, no reuse of last 5
2. Login rate-limits to 5 attempts per 15 minutes per IP
3. Sessions expire after 24h idle, 7d absolute maximum
4. OAuth callback validates state parameter against CSRF
5. All auth endpoints return consistent error shape: `{ error: string, code: string }`

### Out of Scope
- Apple Sign-In (deferred to v2)
- MFA/2FA (separate spec)

### Open Questions
- [NEEDS CLARIFICATION] Session storage: Redis vs DB-backed?
- [NEEDS CLARIFICATION] Password reset flow: email link vs code?

Planning Workflow

BAD - Jump straight to code:

User: "Add a dashboard"
Dev: *starts writing React components*
# 3 days later: wrong data model, missing API endpoints, no error states

GOOD - Structured planning phases:

Read the full file on GitHub · 228 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 · 228 lines · 35 tokens per session scan A 726eff6da696

Subscribe to this mod's changes

spec-driven-dev is a skill published in the GitHub repository medy-gribkov/arcana (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 1,895 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 2026-09-03.

Related

Other skills, from other repositories

tdd

TDD with red-green-refactor loop and vertical slices. Triggers: TDD, test-first, red-green-refactor, test driving development.

softspark/ai-toolkit · 33 tokens

triage-issue

Bug triage: explores codebase for root cause, files GitHub issue with TDD fix plan. Triggers: triage, investigate bug, fix plan, root cause, file issue, bug report.

softspark/ai-toolkit · 47 tokens

ai-observability-promptfoo

Testing and evaluation framework for LLM prompts and applications -- promptfooconfig.yaml, assertions, model-graded evals, red teaming, CI/CD integration, custom providers, and comparative evaluation.

agents-inc/skills · 46 tokens

tdd-workflow

Enforce practical Test-Driven Development for code changes in Go services. Use for new features, bug fixes, refactors, API changes, and new modules. Requires Red-Green-Refactor evidence, defect-hypothesis-driven tests, killer cases, and coverage gates (line + risk-path).

johnqtcg/awesome-skills · 65 tokens

refactor-ops

Safe refactoring patterns - extract, rename, restructure with test-driven methodology and dead code detection. Use for: refactor, refactoring, extract function, extract component, rename, move file, restructure, dead code, unused imports, code smell, duplicate code, long function, god object, feature envy, DRY…

0xDarkMatter/claude-mods · 95 tokens

testing-ops

Cross-language testing strategies and patterns. Triggers on: test pyramid, unit test, integration test, e2e test, TDD, BDD, test coverage, mocking strategy, test doubles, test isolation.

0xDarkMatter/claude-mods · 47 tokens