Inject Spec-Driven Development into AI coding tools without building a new UI.
spec-driven-steroids is a CLI plus template bundle for running a strict workflow inside AI coding tools:
requirements → design → tasks → implementation
It injects:
- Platform-specific agents, commands, or workflows
- Universal writing/implementation skills
- CLI validation commands for spec structure and traceability
- A knowledge graph for architectural decisions and business rules
| Platform | Scope | Injection Type |
|---|---|---|
| Antigravity | project | /spec-driven workflow |
| Claude Code | project | Agents, commands, skills |
| Cline | user / project | Agents, commands, skills |
| Gemini CLI | global / project | Agents, commands, skills |
| GitHub Copilot CLI | user / project | Agents, commands, skills |
| GitHub Copilot for VS Code | global / project | Agents, prompts, skills |
| GitHub Copilot for JetBrains | project | Agents, prompts, skills |
| OpenCode | global / project | Agents, commands, skills |
| OpenAI Codex | project | Agents, command skills, skills |
| Qwen Code | user / project | Agents, commands, skills |
npm install -g spec-driven-steroidsRequirements:
- Node.js
>=20 pnpmfor local development
The CLI provides two command names:
sds(short alias - recommended)spec-driven-steroids(full name)
# Interactive injection (prompts for platform and scope)
sds inject# Validate spec folder structure
sds validate structure <slug>
# Validate EARS requirements
sds validate requirements <path>
# Validate design structure and Mermaid
sds validate design <path>
# Validate task structure and traceability
sds validate tasks <path>
# Full end-to-end validation
sds validate spec <slug># Clean globally injected steroids
sds clean --global
# Show version
sds --version
# Show help
sds --helpManage a knowledge graph of architectural decisions, business rules, and workflow conventions extracted from spec files:
# Report available stewardship capabilities
sds stewardship capabilities
# Search for rules in the knowledge graph
sds stewardship retrieve <query> --domain architecture [--scope <project-id>] [--global]
# Persist a project-scoped rule by default
sds stewardship store architecture --content "Use hexagonal architecture"
# Persist a truly universal rule
sds stewardship store workflow --content "Run typecheck before completion" --global
# Extract decision candidates from a design.md or requirements.md
sds stewardship extract .specs/changes/my-feature/design.md
# Show rule provenance and version history
sds stewardship trace <ruleId> [--scope <project-id>] [--global]
# Retrieve context for a spec phase
sds stewardship inject design [--scope <project-id>] [--global]
# List, deprecate, archive, or move rules
sds stewardship manage list
sds stewardship manage deprecate --ruleId <ruleId> [--scope <project-id>] [--global]
sds stewardship manage move --ruleId <ruleId> --scope <project-id>Rules are project-scoped by default and only fall back to global rules during retrieval. Use --global only for memories that are safe across unrelated repositories.
The CLI injects these universal skills that work across all platforms:
| Skill | Purpose | Phase |
|---|---|---|
spec-driven-requirements-writer |
Write EARS-format requirements | 1 |
spec-driven-technical-designer |
Create technical design with Mermaid | 2 |
spec-driven-task-decomposer |
Decompose into atomic tasks | 3 |
spec-driven-task-implementer |
Execute tasks from tasks.md | 4 |
| Skill | Purpose |
|---|---|
contextual-stewardship |
Knowledge graph for architectural decisions |
quality-grading |
Grade code/specs across 4 dimensions |
code-review-hardening |
Structured code review with self-repair |
universal-live-check |
Real-time validation framework |
long-running-work-planning |
Durable checkpointed execution for long tasks |
project-guidelines-writer |
Generate repository guidelines |
agent-work-auditor |
Audit agent-generated artifacts |
| Agent | Purpose |
|---|---|
spec-driven |
Main spec-driven workflow orchestrator |
Spec-Driven planning writes artifacts to:
.specs/changes/<slug>/
├── requirements.md
├── design.md
└── tasks.md
- Requirements - EARS-syntax requirements with stable IDs
- Design - Mermaid diagrams, architecture sections
- Tasks - Atomic implementation tasks with traceability
- Implementation - Task execution with verification
- Inject platform files into a repository:
sds inject- Generate project guidance:
/inject-guidelinesThis creates: AGENTS.md, CONTRIBUTING.md, STYLEGUIDE.md, TESTING.md, ARCHITECTURE.md, SECURITY.md
- Start the spec flow:
- GitHub Copilot:
@spec-driven Add a rate limiter - OpenCode: use the
Spec-Drivenagent - Cline: use the
Spec-Drivenagent or/spec-driven - Antigravity:
/spec-driven - Codex: select the
spec-drivenskill with/skillsor mention$spec-driven
- Approve each planning phase, then move to implementation.
For complex long-running tasks, SDS injects long-running-work-planning. It keeps agents working through durable artifacts, task status updates, checkpoints, and verification.
packages/
├── cli/ # Main CLI package
│ ├── src/
│ │ ├── cli/ # Injection commands
│ │ ├── core/validate/ # Validation modules
│ │ └── context-stewardship/ # Knowledge graph
│ └── templates/ # Platform templates & skills
├── test-utils/ # Test fixtures and mocks
└── landing-page/ # Documentation site
pnpm install
pnpm build
pnpm testUseful commands:
pnpm typecheck- Type check all packagespnpm lint- Lint all packagespnpm test:coverage- Run tests with coveragepnpm changeset- Create a changesetpnpm changeset:version- Version bump
- AGENTS.md - AI agent guidance
- CONTRIBUTING.md - PR process
- STYLEGUIDE.md - Code conventions
- TESTING.md - Testing strategy
- ARCHITECTURE.md - System architecture
- SECURITY.md - Security policy
MIT