Now Available

Secure Claude Code

Real-time threat detection and policy enforcement for your entire development team. One command. Zero friction.

$ /plugin marketplace add agentkeeper/security && /plugin install agentkeeper

Install directly from the Claude Code plugin marketplace, then restart Claude Code to activate hooks

No credit card required · Free tier forever · Works instantly with no account

The problem with AI coding agents

Claude Code is powerful. But power without visibility is risk.

6 CVEs in 12 months

Claude Code has had critical vulnerabilities including RCE and API key exfiltration. Keeping up manually doesn’t scale.

Zero visibility

Your developers run Claude Code on their laptops. You have no idea what commands it runs, what files it reads, or where it sends data.

No policy enforcement

Anthropic gives you managed settings. But there’s no centralized policy engine, no audit trail, and no fleet-wide compliance view.

How it works

Four layers of protection. One command to activate.

1

Connect in one command

Install Agent Keeper from the Claude Code plugin marketplace. Hooks, threat detection, and 9 security skills activate instantly — no account, no config.

/plugin install agentkeeper

Then restart Claude Code so hooks load at startup.

Or for team-wide push-hooks: agentkeeper claude-code init

2

Every action monitored

Four hook types give you full visibility into every Claude Code session across your org.

UserPromptSubmit

Scans every prompt before Claude processes it

PreToolUse

Evaluates tool calls before execution

PostToolUse

Monitors tool output for hidden instructions

SessionStart

Validates environment and policy on launch

3

Threats blocked in real-time

Behavioral detection patterns tuned for zero false positives on normal development. Dangerous tool calls are stopped before execution.

Credential exfiltrationReverse shellsCI/CD tamperingPrompt injectionSecurity control bypassSupply chain attacksSensitive file accessNetwork data exfiltration
4

Fleet-wide visibility

One dashboard for your entire Claude Code fleet. Compliance percentage, active developers, blocked threats, version tracking.

94%

Compliance

23

Developers

147

Threats Blocked

312

Sessions / 24h

Built for security teams

Every feature designed to give you control without slowing your developers down.

Prompt Injection Detection

UserPromptSubmit hook scans every prompt before Claude processes it. Catches social engineering, jailbreaks, and embedded instructions in file content. All prompts logged to the threat feed.

Tool-level Policy Control

Allow, warn, or block specific tools per org. Enforce which Bash commands, file operations, and web fetches your team can use.

Git Remote Validation

Restrict Claude Code to approved repositories only. Prevent code from being pushed to unauthorized remotes or cloned from untrusted sources.

Sandbox Enforcement

Require sandbox mode across your entire fleet. Verify every developer session runs in a restricted environment with no exceptions.

Complete Audit Trail

Every prompt and tool call logged to the threat feed with timestamps, session context, and user identity. Full forensic trail for incident response and compliance.

Compliance Dashboard

Claude Code version, sandbox status, hooks active per developer. One view for your entire fleet’s security posture.

What Anthropic gives you vs. what you need

Anthropic Enterprise is a great start. Agent Keeper fills the gaps.

CapabilityAnthropic Enterprise+ Agent Keeper
Managed settings
Permission rules
Usage analytics
Real-time threat blocking
Behavioral detection patterns
Prompt injection monitoring
Fleet compliance dashboard
Tool-level policy per org
Git remote validation
Complete audit trail

Simple, transparent pricing

Start free — no credit card required. Scale when you need to.

Free

For individual developers

$0forever
  • 1 workstation
  • Full monitoring
  • All detection patterns
  • 7-day history
Most Popular

Pro

For small teams

$19/mo
  • 3 workstations
  • Custom policies
  • 90-day audit log
  • Tool-level controls
  • Email alerts

Team

For security teams

$29/seat/mo
  • Unlimited workstations
  • Fleet dashboard
  • Compliance reporting
  • Git remote validation
  • RBAC & webhook alerts
  • Priority support

Need enterprise features? Contact us for enterprise pricing

One command. Instant protection.

$ /plugin marketplace add agentkeeper/security && /plugin install agentkeeper

Restart Claude Code to activate hooks. Connect a free dashboard later with /agentkeeper:connect

or for team push-hooks
$ agentkeeper claude-code init

Push-hooks commit to git — every developer who pulls gets covered automatically.

No credit card required · Setup in 30 seconds