Claude Code Plugin

The Opsera DevSecOps plugin brings four AI security and compliance agents directly into Claude Code. Currently available in the private marketplace only.

Installation

There are two ways to install. The Marketplace method is the fastest and handles future updates automatically.

Method A — Claude Code Marketplace Recommended

Install directly from inside Claude Code with a single command:

/install opsera-devsecops

If this command works, skip directly to the Authentication step. You don't need Method B.

Method B — Install from GitHub Manual

Use this if your Claude Code version doesn't support /install, or to pin a specific versionOpen Claude Code

---

Step 1: Open Claude Code

Launch Claude Code in your terminal:

claude

Then open the plugin manager:

/plugin

Step 2: Add the Plugin Repository

Navigate to Marketplace → Add Marketplace.

If claude isn't found, visit code.claude.com/docs to install Claude Code and add it to your PATH.2🐙Add the Plugin Repository

When prompted for the marketplace source, enter:

opsera-agents/opsera-devsecops

Press Enter to confirm. You'll see: + Adding marketplace to configuration…

Step 3: Install the Plugins

Select the Opsera DevSecOps plugin from the catalog and confirm. This installs all 4 agents in one step:

Architecture Analyze   # Risk-focused architecture analysis
Security Scan          # SAST, secrets, CVEs, containers
Compliance Audit       # SOC2, HIPAA, PCI-DSS, ISO 27001
SQL Security           # Injection detection + AI auto-fix

Step 4: Restart Claude Code

Fully exit and reopen Claude Code for the plugin to load:

exit   

Step 5: Verify Installation

Run /plugin and go to Installed Plugins. You should see an Opsera MCP entry that requires authentication.

Move your cursor to it and press Enter to begin the authentication flow.

Step 6: Authenticate in Browser

A browser window opens automatically for secure OAuth login. Sign in with your Opsera account at agent.opsera.ai — or a free trial account is created automatically if you don't have one.

Once authenticated in the browser, return to your terminal. You're ready to go.

Using the Agents

Just describe what you need. Claude routes the request to the right agent automatically:

What you say	Agent	What you get
"Scan this repo for security vulnerabilities"	Security Scan	SAST report + CVE list + secret detection results
"Are we SOC2 compliant?"	Compliance Audit	Gap analysis against SOC 2 controls with evidence map
"Check my SQL files for injection risks"	SQL Security	Flagged queries with safe alternatives and auto-fix
"What are the architectural risks in this codebase?"	Architecture	Risk-annotated architecture diagram + failure modes
"Do we have any secrets committed to this repo?"	Security Scan	Per-file secret detection report with severity ratings
"Generate a HIPAA compliance report"	Compliance Audit	HIPAA control checklist with pass/fail + remediation steps
"Show PII exposure in our query layer"	SQL Security	PII/PHI field inventory with exposure risk ratings