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:
- Understand the codebase and context
- Spec requirements, design, and ordered tasks
- Implement from the spec, not from assumptions
- 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.