Architecture on Gokin

Multi-Agent System

Mon, 01 Jan 0001 00:00:00 +0000

Gokin uses a multi-agent architecture with 5 built-in agent types, task delegation, and inter-agent communication.

Agent Types#

Type	Purpose	Tools
explore	Codebase exploration	read, glob, grep, tree, list_dir, tools_list, request_tool, ask_agent
bash	Command execution	bash, read, glob, tools_list, request_tool, ask_agent
general	Full access	All tools (unrestricted)
plan	Task planning	read, glob, grep, tree, list_dir, diff, todo, web_fetch, web_search, ask_user, env, tools_list, request_tool, ask_agent, enter_plan_mode, exit_plan_mode, update_plan_progress, get_plan_status
claude-code-guide	Documentation & guides	glob, grep, read, web_fetch, web_search, tools_list, request_tool, ask_agent

Agent Lifecycle#

pending → running → completed | failed | cancelled

Custom Agent Types#

Create a new type via slash command:

Memory & Context

Mon, 01 Jan 0001 00:00:00 +0000

Gokin implements a three-level memory system and intelligent context management.

Memory Types#

Type	Scope	Lifetime	Description
Session	Current session	Until session ends	Temporary notes
Project	Current project	Persistent	Project knowledge
Global	All projects	Persistent	General preferences

Entry Structure#

Entry {
 ID string // SHA256: "mem_" + hash[:8]
 Key string // Optional key for lookup
 Content string // Memory content
 Type MemoryType // session, project, global
 Tags []string // Auto-extracted tags
 Timestamp time.Time
 Project string // Project identifier (path hash)
}

Auto-Tagging#

Tags are automatically extracted from content:

Security

Mon, 01 Jan 0001 00:00:00 +0000

Gokin implements a multi-layered security system: permissions, sandbox, command validation, audit, and file protection.

Permission System (3 Levels)#

Level	Behavior	Tools
RiskLow	Auto-approved	read, glob, grep, tree, diff, env, list_dir, git_status, git_log, git_diff, git_blame, web_search, web_fetch, ask_user, memory, code_graph, semantic_search, history_search, task_output, task_stop, todo
RiskMedium	Ask once, then auto-approve	write, edit, git_add, copy, move, mkdir, task, batch
RiskHigh	Ask every time	bash, delete, git_commit, ssh

User Decisions#

Decision	Description
Allow	Allow once
AllowSession	Allow for the entire session
Deny	Deny once
DenySession	Deny for the entire session

RiskMedium tools are automatically approved after the first Allow until session end (stored in autoApprovedTools).