Skip to content

sanmak/specops

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

76 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

SpecOps

Spec-driven development that adapts to your stack, your team, and your workflow.

CI CodeQL GitHub Release GitHub Stars License: MIT

SpecOps brings structured spec-driven development to your AI coding assistant — with domain-specific templates for infrastructure, data pipelines, and SDKs, and a built-in team review workflow for shared codebases. Works with Claude Code, Cursor, OpenAI Codex, and GitHub Copilot.

Why SpecOps

  • Domain-specific templates — Infrastructure specs include Rollback Steps and Resource Definitions. Data pipeline specs include Data Contracts and Backfill Strategy. Library specs flag Breaking Changes per task. Backend and fullstack use clean defaults — no unnecessary ceremony.
  • Built-in team review cycle — Draft a spec, get section-by-section feedback from teammates, revise, and only implement once minApprovals is met. Git identity detection, configurable approval thresholds, and an implementation gate that blocks unapproved specs from proceeding. Solo developers can enable allowSelfApproval for a self-review workflow with distinct audit trail.
  • Security-hardened spec processing — Convention strings and custom templates are sanitized against prompt injection. Secrets use placeholders, PII uses synthetic data, all config fields enforce strict schema validation, and path traversal is rejected at the boundary.

Quick Start

Install (Claude Code):

/plugin marketplace add sanmak/specops
/plugin install specops@specops-marketplace
/reload-plugins

Other platforms & manual install: QUICKSTART.md

Use:

Claude Code: /specops Add user authentication with OAuth | View the spec | List all specs Cursor / Codex / Copilot: Use specops to add user authentication with OAuth | View the spec | List all specs

Full command reference: docs/COMMANDS.md | Troubleshooting: QUICKSTART.md#troubleshooting

How It Works

SpecOps 4-phase workflow with optional interview mode: Understand, Spec, Implement, Complete

One command triggers a 4-phase workflow: understand your codebase, generate a structured spec, implement it, and verify the result. For vague or high-level ideas, an optional interview mode gathers structured requirements before spec generation.

Interview Mode (Optional)

For vague or exploratory ideas, SpecOps guides you through a structured interview before generating specs. Trigger explicitly with /specops interview I want to build X or say something vague and it auto-triggers. Once approved, SpecOps proceeds to spec generation with enriched context.

SpecOps interview mode: gathering questions → clarifying vague answers → confirming summary → proceeding to Phase 1

Team Review Workflow

SpecOps collaborative review workflow: draft, review, revise, approve, implement

For teams, SpecOps adds a structured review cycle between spec creation and implementation. Engineers review specs collaboratively, provide section-by-section feedback, and approve before coding begins. See TEAM_GUIDE.md for the full team workflow.

What Gets Created

SpecOps generates spec.json, requirements.md, design.md, tasks.md, and optional implementation.md and reviews.md

Platforms

Platform Status Trigger
Claude Code Supported /specops [description], /specops view, /specops list
Cursor Supported Use specops to [description], View the ... spec, List all specops specs
OpenAI Codex Supported Use specops to [description], View the ... spec, List all specops specs
GitHub Copilot Supported Use specops to [description], View the ... spec, List all specops specs
Windsurf Planned
Continue.dev Planned

How SpecOps Compares

SpecOps and Spec Kit share the same core philosophy: specs before code. We think Spec Kit is excellent — and we're building on the same principles with a different focus.

Choose Spec Kit if you want the broadest agent support (18+) and are exploring SDD as an individual or small team.

Choose SpecOps if you're a team shipping to production and need specs that match your project type, structured review before implementation, and security-hardened spec processing.

Capability SpecOps GitHub Spec Kit
Supported platforms Claude Code, Cursor, OpenAI Codex, GitHub Copilot 18+ agents
Installation Plugin marketplace or curl | bash, no dependencies Python 3.11+ and uv
Team review workflow Built-in (draft → review → revise → approve → gate) Not available
Vertical-aware templates 7 project types (infra, data, library, builder, etc.) Generic templates
Security hardening Prompt injection defense, schema validation, path containment Not documented
Platform breadth 4 platforms 18+ platforms

Plan Mode vs Spec Mode

Most AI coding assistants include a plan mode for session-scoped planning. SpecOps adds persistent, reviewable specifications that survive across sessions and team members. Plan mode is a whiteboard sketch; spec mode is the architectural blueprint. Use plan mode for tactical "how" decisions during implementation — use SpecOps when the work spans sessions, involves teammates, or touches code where regressions matter.

See the full comparison →

Configuration

Create .specops.json in your project root. Configuration is optional — SpecOps uses sensible defaults.

{
  "specsDir": ".specops",
  "team": {
    "conventions": ["Use TypeScript", "Write tests for business logic"],
    "reviewRequired": true,
    "specReview": { "enabled": true, "minApprovals": 2 }
  },
  "implementation": {
    "autoCommit": false,
    "createPR": true,
    "testing": "auto"
  }
}

See examples/ for minimal, standard, and full configurations. Full schema reference in REFERENCE.md.

Vertical Adaptation

SpecOps adapts spec templates to your project type. Set the vertical key in .specops.json or let SpecOps auto-detect from your codebase.

Vertical Adaptation
Backend Default templates (API endpoints, services, data models)
Frontend State management, components, UI patterns
Full Stack Handles both frontend and backend layers
Infrastructure Resource definitions, topology, IaC
Data Engineering Pipeline stages, data flow, contracts
Library/SDK Public API surface, developer use cases
Builder Product modules, ship plans, cross-domain tasks

Full per-vertical documentation and decision trees: REFERENCE.md

Architecture

SpecOps three-layer architecture: core, generator, platforms

Three layers, strict separation:

  • core/ — Platform-agnostic workflow, templates, and safety rules (single source of truth)
  • generator/ — Builds platform-specific outputs from core + platform adapters
  • platforms/ — Generated instruction files per platform (checked into git, no build step for users)

See STRUCTURE.md for the full repository layout.

Contributing

Contributions welcome. See CONTRIBUTING.md for guidelines.

License

MIT

About

SpecOps transforms how you work with AI coding assistants. Instead of jumping straight into code, it creates structured specifications — requirements, design, tasks — then implements them systematically. Works with Claude Code, Cursor, OpenAI Codex, and GitHub Copilot.

Topics

Resources

License

Contributing

Security policy

Stars

Watchers

Forks

Packages

 
 
 

Contributors