spec-driven-development

spec-driven-development is a skill for Claude Code, Codex from juanmhidalgo/claude-plugins. It costs 48 tokens per session (2,516 once invoked), scanned A, original, MIT.

Use when starting a new feature or significant change with no spec yet. Covers single-repo and multi-repo features. Do NOT use for typos, single-line fixes, or post-hoc documentation of finished work.

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/juanmhidalgo/claude-plugins/spec-driven-development
Any agent
npx skills add juanmhidalgo/claude-plugins --skill spec-driven-development
Clone the repo
git clone --depth 1 https://github.com/juanmhidalgo/claude-plugins

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/juanmhidalgo/claude-plugins/spec-driven-development.svg)](https://agentmods.dev/skills/juanmhidalgo/claude-plugins/spec-driven-development)
Your own site
<a href="https://agentmods.dev/skills/juanmhidalgo/claude-plugins/spec-driven-development"><img src="https://agentmods.dev/badge/skills/juanmhidalgo/claude-plugins/spec-driven-development.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,516 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00048 $0.02516
Opus 5 $0.00024 $0.01258
Sonnet 5 $0.00010 $0.00503
Haiku 4.5 $0.00005 $0.00252

Measured today against content hash 4a7b5a24ec70, 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 today.

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.

feature-dev/skills/spec-driven-development/SKILL.md · 208 lines

How it starts

The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec-Driven Development

When to Use

  • Starting a new feature or project
  • Requirements are ambiguous or incomplete
  • Change touches multiple files or modules
  • Task would take more than 30 minutes to implement
  • About to make an architectural decision

The Gated Workflow

Four phases. Do not advance until the current phase is validated by the user.

SPECIFY ──→ PLAN ──→ TASKS ──→ IMPLEMENT
   │          │        │          │
   ▼          ▼        ▼          ▼
 Review     Review   Review    Review

Phase 1: Specify

Surface assumptions immediately before writing anything:

ASSUMPTIONS I'M MAKING:
1. This is a web application (not native mobile)
2. Authentication uses session-based cookies
3. The database is PostgreSQL
→ Correct me now or I'll proceed with these.

Write a spec covering eight areas:

  1. Objective — What, why, who
  2. Acceptance Criteria — A dedicated, scannable section of observable, user-facing criteria (do not bury them in Objective). Include at least one failure/error-state criterion, not only happy-path outcomes. This is what downstream review, planning, and QA anchor to.
  3. Commands — Full executable commands (build, test, lint, dev)
  4. Project Structure — Where source, tests, and docs live
  5. Code Style — One real snippet showing conventions
  6. Testing Strategy — Framework, location, coverage, test levels (the engineering view)
  7. QA Checklist — A separate, QA-facing list grouped as happy path / edge cases / error states; distinct from the engineering-oriented Testing Strategy. Every error-state acceptance criterion gets a matching check.
  8. Boundaries — Always do / Ask first / Never do

Reframe vague requirements as testable success criteria. Ban these words from acceptance criteria unless you immediately define them concretely: fast, slow, easy, simple, user-friendly, intuitive, seamless, better, improved.

"Make the dashboard faster"
→ LCP < 2.5s on 4G, initial data load < 500ms, CLS < 0.1
→ Are these the right targets?

"Make onboarding intuitive"
→ ≥80% of new users complete the first three steps without help-text dwell > 3s
→ Or: define what "intuitive" means here in plain language.

Read the full file on GitHub · 208 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. today First seen · 208 lines · 48 tokens per session scan A 4a7b5a24ec70

Subscribe to this mod's changes

spec-driven-development is a skill published in the GitHub repository juanmhidalgo/claude-plugins (8 stars, last pushed 9d ago), licensed MIT. It adds 48 tokens to every session and 2,516 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

project-specification

Transforms project briefs into testable specifications with user stories and acceptance criteria. Use after brainstorming, before planning.

athola/claude-night-market · 25 tokens

absolute-work

End-to-end, phase-gated SDLC for AI coding agents: relentless design interview → reviewed spec → dependency-graphed task board → safe-wave TDD execution → verification → converge. Handles features, bugs, refactors, greenfield projects, planning breakdowns, and migrations. Triggers on "absolute work", "build this…

maddhruv/absolute · 104 tokens

absolute-spec

Lightweight standalone design spec for AI coding agents: codebase scan → bounded clarify pass (3–5 questions, not a grill) → reviewed design doc written to docs/plans/ → independent scored review → stop. No task board, no build. Use when you want a spec to discuss, hand off, or review before committing to…

maddhruv/absolute · 122 tokens

requirements-elicitation

Turns vague intent into testable requirements.

andreaswasita/copilot-agents-dojo · 13 tokens

speckit-specify

Turn a plain feature description into a structured specification (spec.md): overview, user stories, functional and non-functional requirements, and testable acceptance criteria. Trigger on: write a spec, specify this feature, create requirements, spec-driven development, SDD specify.

sarveshtalele/mcp-skills-registry · 58 tokens

spec-writing

Write a spec that a different engineer could implement without asking questions. Invoke when starting a new feature, especially one that will be handed off or implemented later.

orlando-japan/claude-code-setting · 34 tokens