agentback

agentback is a Backend frameworks skill for AI agents, published by ninemindai in the agentback repository on GitHub. Skillspace rates agentback D (58/100) and it passed the safety scan; the rating is based on static analysis only.

Build HTTP (REST) and MCP services from one Zod schema set and one DI container with AgentBack — an ESM/Zod/MCP fork of LoopBack 4. Use when building TypeScript/Node.js apps with @agentback/* packages: Zod-first REST controllers (@api, @get/@post/... with path/query/body/response schemas), MCP tool servers (@mcpServer, @tool with input/output schemas), OpenAPI 3.1 emission, a schema-typed HTTP client, authentication strategies / @authorize voters, rate limiting, MCP-over-HTTP auth, the agent runtime, or actors (stateful entities behind a stable address). Triggers on @agentback/core, RestApplication, MCPApplication, @api, @get, @tool, @mcpServer, installMcpHttp, @authenticate, @authorize, @actor, @actorCommand, @actorQuery, ActorRegistry, @injectActor, z.infer, toHostTools, installAgent, running a Vercel AI SDK ToolLoopAgent/HarnessAgent with the app's own @tool classes as host tools (@agentback/agents), rendering an MCP Apps (SEP-1865) ui:// widget for a tool result (@tool({ui})), or…

Grade
D
Quality
58 / 100
Safety
Passed
GitHub stars
29

Unproven: rated by static analysis only, not yet compared head-to-head.

Our two independent classifiers differ on this skill's category, so treat the placement as provisional.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

View source on GitHubninemindai/agentback

Our review

Architecture
78 / 100
Maturity
Structured: ships references or scripts
Security scan
Low-risk patterns
License
Not declared. Check the repository before reusing it.
Adoption
Adopted by 0 other repositories, in 0 collections

What the scanner flagged

  • mentions secrets in text

Not checked yet

  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Better-rated skills in Backend frameworks

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.