Plugins · kamioj/spec-workflow

spec

Spec-driven development plugin: research → ask → propose → HARD GATE → apply → verify → archive, plus a goal-driven autonomous loop (/spec:loop) — enforced by 5 hooks (TBD scan / approval gate / archive audit / verify reminder / loop driver), with scope-dispatched dev agents and a fresh-context verifier agent

CLEARED_STATICagent-agnosticv0.5.5

Pipeline results

Coverage

CLEARED_STATIC

Tests run

7 / 8

Portability

Agent-agnostic (works beyond Claude)

Type

Plugins

Tests & results

What the pipeline checked

TestStateResult or reason

eligibilityranall eligibility checks passed

dedupranunique -- no near-duplicate found

clocran18508 code lines / 141 files

secretsranno secret patterns matched

egressran20 lexical match(es) — FLAG-INFO (C-01: semantic analysis deferred to v2)

injectionranno patterns matched (confidence: STANDARD)

required-fieldsranrequired fields present: name, version, description

behaviouraln/anot reached — prior gate did not pass

What's inside

Components found

agents/spec-dev.md

componentmedium

agents/spec-verifier.md

componentmedium

commands/apply.md

componentmedium

commands/archive.md

componentmedium

commands/ask.md

componentmedium

commands/chat.md

componentmedium

commands/design.md

componentmedium

commands/loop.md

componentmedium

commands/propose.md

componentmedium

commands/research.md

componentmedium

commands/revise.md

componentmedium

commands/status.md

componentmedium

commands/verify.md

componentmedium

commands/workflow.md

componentmedium

core/skill.md

componentmedium

core/agents/spec-dev.md

componentmedium

core/agents/spec-verifier.md

componentmedium

core/commands/apply.md

componentmedium

core/commands/archive.md

componentmedium

core/commands/ask.md

componentmedium

Coverage

Not assessed

behavioural execution not run
egress patterns logged (FLAG-INFO): 20 lexical match(es)

README

From the repository


# spec-workflow

**Spec-driven development plugin for Claude Code**

Large changes, kept controllable and reversible. The pipeline — research → clarify → propose → **HARD GATE** → implement → verify → archive — is re-entrant at every step, enforced by hooks, and runs its agents in parallel.

[![Version](https://img.shields.io/badge/version-0.4.2-blue.svg)](https://github.com/kamioj/spec-workflow)
[![Platform](https://img.shields.io/badge/platform-Windows%20%7C%20macOS%20%7C%20Linux-lightgrey.svg)](https://github.com/kamioj/spec-workflow)
[![Claude Code](https://img.shields.io/badge/Claude%20Code-v2.1+-purple.svg)](https://docs.claude.com/en/docs/claude-code)
[![License](https://img.shields.io/badge/license-MIT-green.svg)](LICENSE)

**English** | [中文](README_cn.md)



---

## Why

Two paradigms already dominate AI-assisted spec-driven development:

- **Fast lane** — start coding right away and let hooks catch the mistakes (hookify, or a stripped-down superpowers brainstorm).
- **Heavy lane** — spec everything up front, but down a rigid track (OpenSpec's 4 commands, superpowers brainstorm's 9 steps).

**spec-workflow takes a third path.** It keeps the discipline of thinking before …

← Back to Plugins