specops

Make your AI agent think before it codes.

---

You describe a feature to your AI coding assistant. It starts writing code immediately. No requirements. No design. No task breakdown. You spend the next hour correcting assumptions it made in the first minute.

The problem isn't the AI. It's that nobody told it to think first.

What SpecOps Does

SpecOps adds a structured thinking step to AI coding. One command triggers a 4-phase workflow:

1. Understand the codebase and context
2. Spec requirements, design, and ordered tasks
3. Implement from the spec, not from assumptions
4. Complete with verified acceptance criteria

Specs are git-tracked, survive across sessions, and work natively with Claude Code, Cursor, OpenAI Codex, GitHub Copilot, and Google Antigravity.

Quick Start

Claude Code (plugin marketplace):

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

One-line install (any platform):

bash <(curl -fsSL https://raw.githubusercontent.com/sanmak/specops/main/scripts/remote-install.sh)
# Inspect the script first: https://github.com/sanmak/specops/blob/main/scripts/remote-install.sh

Or clone and run:

git clone https://github.com/sanmak/specops.git && cd specops && bash setup.sh

Try it:

/specops Add user authentication with OAuth

Platform-specific install details: QUICKSTART.md | Full command reference: docs/COMMANDS.md

Before and After

Without SpecOps:

You: "Add OAuth authentication"
Agent: *writes auth.ts, picks JWT without asking, hardcodes Google,
       skips rate limiting, creates 6 files*
You: "No, I needed GitHub too, and..." (30 min of corrections)

With SpecOps:

You: "/specops Add OAuth authentication"
Agent:
  requirements.md  ->  4 user stories, 12 acceptance criteria (EARS notation)
  design.md        ->  JWT vs sessions trade-off, provider abstraction layer
  tasks.md         ->  8 ordered tasks with dependencies and effort estimates
  Then implements each task against verified criteria.

Problems SpecOps Solves

Problem	How SpecOps handles it
AI starts coding without understanding the domain	7 vertical templates: backend, frontend, infra, data pipelines, library/SDK, fullstack, builder
Specs lost when you close the session	Git-tracked spec files with cross-session context recovery
Agent forgets decisions from yesterday	Local memory layer, loaded automatically every session
No way to review specs before coding starts	Built-in team review workflow with configurable approval gates
Agent hallucinates vague acceptance criteria	EARS notation for precise requirements: WHEN [event] THE SYSTEM SHALL [behavior]
Specs drift from codebase after implementation	5 automated drift checks with audit and reconcile commands
AI adds packages without checking maintenance or license	Dependency introduction gate: 5-criteria evaluation (scope, maintenance, size, security, license) before any install
Agent marks its own work as "done" without scrutiny	Adversarial evaluation: separate evaluator scores specs and implementations against hard thresholds
Production reveals things specs missed	Production learnings layer: capture discoveries, link to specs, surface in future work
Locked into one AI coding tool	One source of truth, 5 platform outputs

Built With SpecOps

Every feature of SpecOps was specified, designed, and implemented using the SpecOps workflow. All specs are public in .specops/. The friction log captures 42 lessons learned that shaped the tool.

Multi-Spec Features

Large features that span multiple bounded contexts are automatically detected and split into coordinated specs.