A development workflow that organizes software work into written requirements, design decisions, implementation tasks, testing, review, and acceptance.

Brainstorm and refine requirements, create designs and task lists, execute and verify work, run reviews and tests, accept completed features, and prepare project documentation or release steps.

It gives a project a shared written plan, so developers can track what should be built and whether each requirement was covered.

spec-driven — Plugin for Claude Code by Habib0x0/spec-driven-plugin

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.

Clone the repo

git clone --depth 1 https://github.com/Habib0x0/spec-driven-plugin

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/habib0x0/spec-driven-plugin/spec-driven-plugin/github.svg)](https://agentmods.dev/plugins/habib0x0/spec-driven-plugin/spec-driven-plugin)

Your own site

<a href="https://agentmods.dev/plugins/habib0x0/spec-driven-plugin/spec-driven-plugin"><img src="https://agentmods.dev/badge/plugins/habib0x0/spec-driven-plugin/spec-driven-plugin/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/habib0x0/spec-driven-plugin/spec-driven-plugin"><img src="https://agentmods.dev/badge/plugins/habib0x0/spec-driven-plugin/spec-driven-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 1 skill, 18 commands, 11 agents cost 1,959 tokens a session between them.

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.

Security

Grade A, and why

spec-driven 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 1mo 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.

.claude-plugin/plugin.json · 42 lines

What it actually says

{
  "name": "spec-driven",
  "version": "5.3.3",
  "description": "Spec-driven development workflow with structured requirements, design, and task phases",
  "author": {
    "name": "habib0x"
  },
  "keywords": ["specs", "requirements", "design", "planning", "workflow", "EARS"],
  "agents": [
    "./agents/spec-planner.md",
    "./agents/spec-tasker.md",
    "./agents/spec-validator.md",
    "./agents/spec-implementer.md",
    "./agents/spec-tester.md",
    "./agents/spec-reviewer.md",
    "./agents/spec-consultant.md",
    "./agents/spec-acceptor.md",
    "./agents/spec-documenter.md",
    "./agents/spec-scanner.md",
    "./agents/spec-debugger.md"
  ],
  "commands": [
    "./commands/spec.md",
    "./commands/spec-brainstorm.md",
    "./commands/spec-refine.md",
    "./commands/spec-tasks.md",
    "./commands/spec-status.md",
    "./commands/spec-validate.md",
    "./commands/spec-exec.md",
    "./commands/spec-loop.md",
    "./commands/spec-accept.md",
    "./commands/spec-docs.md",
    "./commands/spec-release.md",
    "./commands/spec-verify.md",
    "./commands/spec-retro.md",
    "./commands/spec-complete.md",
    "./commands/research.md",
    "./commands/zoom-out.md",
    "./commands/ubiquitous-language.md"
  ]
}

Contents

What it installs

The manifest is a name and a version. 1 skill, 18 commands, 11 agents travel with it, and installing the plugin installs all of them — 1,959 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Files

What ships with it

1 file beside plugin.json 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.

marketplace.json 525 B

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.

1mo ago First seen · 42 lines scan A e83b644c3e6e

Subscribe to this mod's changes

spec-driven is a plugin published in the GitHub repository Habib0x0/spec-driven-plugin (10 stars, last pushed 5mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.

Claude Code Planning architecture claude claude-code-plugin codex codex-skill

wyx

Architecture guardrails for Claude Code — automatically injects declared module boundaries into Claude's context when it edits files near a spec.

jlifyio/wyx · not measured

capstone

Architecture reference generator: a lean docs/capstone/ index plus topic files stamped to the commit they were derived at, built and kept current by one command, map. Companion commands: doctor, an opt-in two-sided review, a greenfield pipeline from mockup to running code with a frontend-design stage, and a…

GentBajko/capstone · not measured

deep-plan

AI-assisted deep planning with research, interview, external LLM review, and TDD approach.

piercelamb/deep-plan · not measured

capstone

Architecture reference docs: a docs/capstone/ index plus topic files stamped to commits, built and kept current by one command, map, plus doctor/review, a greenfield pipeline from product mockup to running code with a frontend-design stage, and a doc-grounded feature chain.

GentBajko/capstone · not measured

punchcard

Architecture-level code review from a fifty-year veteran: design, boundaries, data and error paths — never naming or formatting. One verdict, every finding that earns its place, every claim demonstrated in code. Reviews a diff in the conversation or posts one review into a GitHub PR / GitLab MR. Briefs a change before.

Maksim-Burtsev/punchcard · not measured

dokmatiq-docgen

Document generation with stationery/letterhead overlay, e-invoicing (ZUGFeRD/XRechnung/Factur-X), Excel, PDF signing, and AI receipt recognition for Codex and Claude Code. Bundles the Dokmatiq DocGen MCP server (40 tools) with a triggering skill.

dokmatiq/docgen-sdks · not measured

spec-driven

Getting it into your agent

Wrote this? Show the measurements

Grade A, and why

Nothing flagged

What it actually says

What it installs

What ships with it

What this file has done since we first saw it

Other plugins, from other repositories

wyx

capstone

deep-plan

capstone

punchcard

dokmatiq-docgen