An open API service indexing awesome lists of open source software.

https://github.com/sighup/claude-workflow

Claude Code plugin for spec-driven development. Takes features from idea to validated implementation using structured specs, dependency-aware task graphs, and parallel agent execution.
https://github.com/sighup/claude-workflow

ai-agents claude claude-code developer-tools spec-driven-development task-automation

Last synced: about 1 month ago
JSON representation

Claude Code plugin for spec-driven development. Takes features from idea to validated implementation using structured specs, dependency-aware task graphs, and parallel agent execution.

Awesome Lists containing this project

README

          

# claude-workflow

A Claude Code plugin that unifies spec-driven development, autonomous task execution, and parallel agent dispatch into a single workflow. Takes a feature from idea to validated implementation using structured specifications, dependency-aware task graphs, and evidence-based verification.

## Install

### From Git (recommended)

```bash
# Add the marketplace
claude plugin marketplace add https://github.com/sighup/claude-workflow.git

# Install at project scope (shared with team via .claude/settings.json)
claude plugin install claude-workflow@claude-workflow --scope project

# Or install at user scope (personal, across all projects)
claude plugin install claude-workflow@claude-workflow --scope user
```

### Interactive installation

```bash
/plugin
# Navigate to Marketplaces tab → Add → paste the git URL
# Then go to Discover tab → select claude-workflow → choose scope
```

## Workflow

### Interactive (inside Claude)

```
/cw-spec → [/cw-gherkin] → /cw-plan → /cw-dispatch → /cw-validate
```

Each step can also be run independently. `/cw-execute` handles single-task execution for manual or shell-scripted loops. `/cw-review` adds a code review gate and `/cw-testing` generates and runs E2E tests.

### Worktrees (manual parallel development)

Use `/cw-worktree` to develop multiple features simultaneously. Each worktree gets its own feature branch and **isolated task list** (via `.claude/settings.local.json`). Tasks persist in `~/.claude/tasks/{worktree-name}/`, enabling seamless resume across sessions. See [examples/workflows.md](examples/workflows.md) for the full multi-terminal walkthrough.

## Skills

| Skill | Purpose |
|-------|---------|
| `/cw-spec` | Generate structured specification with demoable units and proof artifacts |
| `/cw-plan` | Transform spec into native task graph with dependencies and metadata |
| `/cw-execute` | Execute one task using the 11-phase protocol (orient → commit → clean exit) |
| `/cw-dispatch` | Spawn parallel subagent workers for independent tasks (no setup required) |
| `/cw-dispatch-team` | Persistent agent team with lead coordination for parallel task execution |
| `/cw-validate` | Run 6 validation gates and produce a coverage matrix report |
| `/cw-review` | Review implementation for bugs, security issues, and quality; creates fix tasks |
| `/cw-review-team` | Concern-partitioned team review — each reviewer sees all files through a specialized lens (security, correctness, spec compliance) |
| `/cw-testing` | E2E testing with auto-fix — generate tests from specs, execute, and fix failures |
| `/cw-gherkin` | Generate Gherkin BDD scenarios from spec acceptance criteria; optionally creates cw-testing task stubs |
| `/cw-worktree` | Manage git worktrees for multi-feature parallel development |

## Prerequisites

Shell scripts require `jq`. The `gh` CLI is needed for PR creation in `cw-pipeline`.

Most skills work out of the box. `/cw-dispatch-team` uses [Claude Code agent teams](https://code.claude.com/docs/en/agent-teams) which requires two env vars:

```json
// ~/.claude/settings.json (user-level) or .claude/settings.json (project-level)
{
"env": {
"CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1",
"CLAUDE_CODE_TASK_LIST_ID": "your-project-name"
}
}
```

`/cw-dispatch` (subagent workers) needs no setup and is the recommended default. `/cw-plan` will offer both options after task graph creation.

## Task Metadata

Every task on the board carries self-contained metadata enabling autonomous execution:

```json
{
"task_id": "T01",
"spec_path": "docs/specs/01-spec-auth/01-spec-auth.md",
"scope": {
"files_to_create": ["src/auth/login.ts"],
"files_to_modify": ["src/routes/index.ts"],
"patterns_to_follow": ["src/routes/health.ts"]
},
"requirements": [
{ "id": "R01.1", "text": "POST /auth/login accepts credentials", "testable": true }
],
"proof_artifacts": [
{ "type": "test", "command": "npm test -- src/auth/login.test.ts", "expected": "All pass" }
],
"commit": { "template": "feat(auth): add login endpoint" },
"verification": {
"pre": ["npm run lint"],
"post": ["npm test"]
},
"role": "implementer",
"complexity": "standard",
"model": null
}
```

## Shell Scripts

Shell scripts in `bin/` are optional and enable autonomous (unattended) execution without an interactive Claude session — useful for CI pipelines or scripted workflows. All core functionality is available through the skills above. See [examples/shell-scripts.md](examples/shell-scripts.md) for usage and environment variable reference.