Agent building

Cross-agent messaging via SQLite.

A committed project-scope skill used by the agent-scan canary to verify that inspect detects skills under <project>/.claude/skills.

Guardian service that monitors the active runtime agent's state and automatically restarts it if stopped.

Upgrade Claude Code to the latest version with graceful shutdown and auto-restart.

Core memory system.

Create, track and update team goals via the Deeplake virtual filesystem at memory/goal/.

Query the local code graph (functions, classes, calls, imports) through the Deeplake mount at memory/graph/.

Query the local code graph (functions, classes, calls, imports) through the Deeplake mount at memory/graph/.

AI image generation with OpenAI GPT Image 2.5, Azure OpenAI, Google, OpenRouter, DashScope, Z.AI GLM-Image, MiniMax, Jimeng, Seedream, Replicate and Agnes APIs.

Use the unprimed sub agent as a second set of eyes before accepting visual work — MANDATORY before declaring any user-reported visual bug fixed or claiming a…

Scan agent skills for security issues.

管理订阅源与系统配置，所有改动逐项向用户说明并等待批准

Use when executing a written implementation plan across sessions or with review checkpoints.

Use when executing a written implementation plan with independent tasks in the current session where delegation beats inline coordination cost; otherwise…

Use Claude Code as an independent `claude -p` subagent when the user explicitly asks for Claude, wants a second-agent opinion from Claude, or asks to delegate…

Use the local Codex CLI as an independent second agent.

Create or revise agent skills.

Find Agent Skills for a goal the user cannot name yet, then export an installable bundle.

Create a skill or bring an existing one up to the same standard (validate + asm eval fix loop); run evals, tune triggering.

Add GitHub skill repos to the ASM index: clone, audit, eval, regenerate index, rebuild catalog, open PR.

Global team and org memory powered by Activeloop.

Use when an agent needs to author or reply to crit inline comments programmatically (including multi-agent workflows commenting on shared…

Use when an agent needs to author or reply to crit inline comments programmatically (including multi-agent workflows commenting on shared…

Use when an agent needs to author or reply to crit inline comments programmatically (including multi-agent workflows commenting on shared…