ReferenceCLI

Claude Code Plugin

Install the Agentuity Coder plugin for Claude Code to get specialized agents with persistent memory.

The Agentuity Coder plugin adds a team of specialized AI agents, persistent memory, and cloud service access to Claude Code. It runs as a native Claude Code plugin with event hooks, slash commands, and auto-activated skills.

Installation

# Via Agentuity CLI (recommended)
agentuity ai claude-code install
 
# Via Claude Code marketplace
/plugin marketplace add agentuity/sdk
/plugin install agentuity-coder@agentuity

Prerequisites

Requires Claude Code, Agentuity CLI (agentuity auth login), and Bun. The plugin works without the CLI, but memory and cloud features will be unavailable.

Slash Commands

CommandDescription
/agentuity-coderRun a task with the full agent team
/agentuity-cadenceStart autonomous long-running task execution
/agentuity-cadence-cancelCancel an active Cadence session
/agentuity-memory-saveSave session context to cloud memory
/agentuity-memory-shareShare content via Agentuity Cloud Streams
/agentuity-sandboxRun code in an isolated sandbox
/agentuity-coder implement dark mode for the settings page

Agents also activate automatically based on context. You don't always need a slash command.

Agents

Seven agents with distinct roles, each running on a model tier suited to their task:

AgentRoleModel
LeadOrchestrator: plans, delegates, synthesizesopus
ScoutExplorer: codebase research, read-onlyhaiku
BuilderImplementer: code changes, tests, buildssonnet
ArchitectAutonomous implementer: complex multi-file workopus
ReviewerCode reviewer: catches issues, verifies qualitysonnet
MemoryContext manager: stores/recalls across sessionshaiku
ProductRequirements owner: PRDs, feature planningsonnet

Lead handles delegation automatically. For most tasks, describe what you want and the right agents are chosen for you.

Skills

The plugin includes auto-activated skills that inject Agentuity SDK expertise when relevant:

SkillCovers
agentuity-backend@agentuity/runtime, @agentuity/schema, @agentuity/drizzle, @agentuity/postgres, @agentuity/evals
agentuity-frontend@agentuity/react, @agentuity/auth, @agentuity/frontend, @agentuity/workbench
agentuity-opsCLI commands, cloud services, deployments
agentuity-cloudPackage routing, ecosystem overview
agentuity-command-runnerRuntime detection, build/test/lint execution

Memory

Persistent context across sessions via Agentuity Cloud:

  • KV Storage for structured data (patterns, decisions, corrections)
  • Vector Storage for semantic search over session history
  • Entity-centric: tracks users, orgs, projects, repos
  • Branch-aware: scopes memories to git branch context

Use /agentuity-memory-save after completing work to persist decisions and lessons learned.

Cadence Mode

Cadence runs the agent team autonomously across multiple iterations until a task is complete:

/agentuity-cadence build the auth system with OAuth, session management, and tests

How it works:

  1. A Stop hook intercepts session end and re-injects the task prompt
  2. Memory checkpoints at each iteration for recovery
  3. The loop continues until the agent signals completion or max iterations is reached (default: 50)

Use --max-iterations N to cap iterations (e.g., /agentuity-cadence --max-iterations 10 build the auth system).

Cancel with /agentuity-cadence-cancel or Ctrl+C.

Hooks

The plugin registers event hooks that run automatically:

ScriptEventWhat It Does
session-start.shSessionStartDetects Agentuity project, org, user, and git context
session-end.shSessionEndSaves session memory (immediate KV + async processing)
block-sensitive-commands.shPreToolUseBlocks access to secrets, API keys, auth tokens
pre-compact.shPreCompactSaves memory before context window compaction
cadence-stop.shStopKeeps the Cadence loop running until task is done
stop-memory-save.shStopPrompts memory save before session ends

Permissions

The install script configures Claude Code permissions in ~/.claude/settings.local.json:

  • Allowed: agentuity cloud * and agentuity auth whoami *
  • Blocked: agentuity cloud secrets *, agentuity cloud secret *, agentuity cloud apikey *, agentuity auth token *

Deny rules take precedence. The PreToolUse hook adds a second layer blocking sensitive commands before they reach the permission system.

Cloud Services

Agents can use any agentuity cloud subcommand:

ServiceDescription
KVKey-value storage for structured data
VectorSemantic search over stored content
StorageFile upload/download
SandboxIsolated code execution environments
DatabasePostgres via agentuity cloud db
SSHConnect to deployments

Next Steps

Need Help?

Join our DiscordCommunity for assistance or just to hang with other humans building agents.

Send us an email at hi@agentuity.com if you'd like to get in touch.

Please Follow us on

If you haven't already, please Signup for your free account now and start building your first agent!