Spec-Driven Development

Spec-Driven Development is a skill for Claude Code, Codex from winstonkoh87/Athena-Public. It costs 30 tokens per session (598 once invoked), scanned A, original, MIT.

A development process that requires a complete written design specification before code is written. It records the goal, requirements, exclusions, architecture, edge cases, and acceptance checks.

In plain words
What is it for?
Use it to question requirements, create a design document, get user approval, and then implement and verify code against the approved specification.
Why use it?
It reduces mistakes caused by starting implementation before the desired behavior, limits, integrations, and definition of success are clear.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: model in frontmatter.

Good fit Use it to question requirements, create a design document, get user approval…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/winstonkoh87/athena-public/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 winstonkoh87/Athena-Public --skill spec-driven-dev
Clone the repo
git clone --depth 1 https://github.com/winstonkoh87/Athena-Public

Made for: Claude Code, Codex.

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/winstonkoh87/athena-public/spec-driven-dev.svg)](https://agentmods.dev/skills/winstonkoh87/athena-public/spec-driven-dev)
Your own site
<a href="https://agentmods.dev/skills/winstonkoh87/athena-public/spec-driven-dev"><img src="https://agentmods.dev/badge/skills/winstonkoh87/athena-public/spec-driven-dev.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 598 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 $0.00030 $0.00598
Opus 5 $0.00015 $0.00299
Sonnet 5 $0.00006 $0.00120
Haiku 4.5 $0.00003 $0.00060

Measured 7d ago against content hash d61882510c85, 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 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 7d 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.

examples/skills/coding/spec-driven-dev/SKILL.md · 90 lines

What it actually says

📋 Spec-Driven Development

Philosophy: 55 minutes defining the problem, 5 minutes solving it.

1. The Problem

Most AI coding failures happen because the agent starts coding before understanding:

  • What the user actually wants (vs. what they said)
  • Edge cases and constraints
  • Integration points and dependencies
  • Success criteria

2. Execution Workflow

PHASE 1: INTERROGATION (No Code Allowed)
  ├─ "What is the ONE thing this must do?"
  ├─ "What does success look like? Be specific."
  ├─ "What are 3 things this must NOT do?"
  ├─ "Who/what does this interact with?"
  └─ "What's the simplest version that would be useful?"

PHASE 2: SPEC DOCUMENT
  └─ Write a design.md with:
     ├─ Goal (1 sentence)
     ├─ Requirements (numbered list)
     ├─ Non-Requirements (explicit exclusions)
     ├─ Architecture (how components connect)
     ├─ Edge Cases (what could go wrong)
     └─ Acceptance Criteria (how to verify)

PHASE 3: USER APPROVAL
  └─ Present spec for review
  └─ DO NOT proceed to code until approved

PHASE 4: IMPLEMENTATION
  └─ Code against the approved spec
  └─ Reference spec line items in commits

3. The Spec Template

# Design Spec: [Feature Name]

## Goal
[One sentence describing what this does]

## Requirements
1. [Must do X]
2. [Must handle Y]
3. [Must integrate with Z]

## Non-Requirements (Out of Scope)
- [Will NOT do A]
- [Will NOT support B]

## Architecture
[How the components connect — diagram or description]

## Edge Cases
- [What if input is empty?]
- [What if API is down?]
- [What if user does X instead of Y?]

## Acceptance Criteria
- [ ] [Testable condition 1]
- [ ] [Testable condition 2]

4. When to Use

  • Any feature that touches >3 files
  • Any task that takes >30 minutes
  • Any time you catch yourself thinking "I'll figure it out as I go"

skill #engineering #planning #spec

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. 7d ago First seen · 90 lines · 30 tokens per session scan A d61882510c85

Subscribe to this mod's changes

Spec-Driven Development is a skill published in the GitHub repository winstonkoh87/Athena-Public (582 stars, last pushed yesterday), licensed MIT. It adds 30 tokens to every session and 598 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.