Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/ninemindai/agentback-demo/agentbacknpx skills add ninemindai/agentback-demo --skill agentbackgit clone --depth 1 https://github.com/ninemindai/agentback-demoWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ninemindai/agentback-demo/agentback)<a href="https://agentmods.dev/skills/ninemindai/agentback-demo/agentback"><img src="https://agentmods.dev/badge/skills/ninemindai/agentback-demo/agentback.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00220 | $0.03156 |
| Opus 5 | $0.00110 | $0.01578 |
| Sonnet 5 | $0.00044 | $0.00631 |
| Haiku 4.5 | $0.00022 | $0.00316 |
Grade A, and why
agentback scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build REST + MCP Services with AgentBack
AgentBack is an ESM/Zod/MCP fork of LoopBack 4 — a TypeScript DI
framework (@agentback/core + @agentback/context) with HTTP and MCP
servers that discover your code by tag in one Context. Its bet: a single Zod
schema is the validator, the z.infer type, the OpenAPI contract, the MCP
input/output, and the rendered docs — simultaneously. Change the schema and
every contract changes in one edit; disagreements surface as a TypeScript error
at the decorator, a startup throw, or a failing test.
ESM-only, Node 22.13+, TypeScript 6, pnpm workspaces. Relative imports use
.js extensions. This is a slim modern subset — no LB4 sequences/actions, no
@loopback/repository, no per-parameter @param/@requestBody.
Architecture Decision Tree
- DI container, bindings, components, lifecycle? → Dependency injection &
components (dependency-injection.md).
(Same model as
@loopback/core; this layer is a faithful port.) - HTTP/REST API with validation + OpenAPI? → Zod-first REST (rest-and-openapi.md)
- Tools / resources / prompts for MCP clients (Claude, Cursor, agents), over stdio or HTTP? → MCP tools (mcp-tools.md)
- Share schemas/types between server and a typed client (no codegen)? → Schema sharing & client (schema-sharing-and-client.md)
- Authentication, authorization, scopes, rate limiting (REST or MCP/HTTP)? → Auth & rate limiting (auth-and-rate-limiting.md)
- Health/metrics, middleware, subclassing the dispatcher, packaging? → Composition & operations (composition-and-operations.md)
Getting Started: scaffold a new app
Don't hand-write package.json/tsconfig.json. Scaffold with the
create-agentback CLI — npm create agentback resolves to it:
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 217 lines · 220 tokens per session scan A 847a165aa4f6
agentback is a skill published in the GitHub repository ninemindai/agentback-demo (0 stars, last pushed 1mo ago), licensed MIT. It adds 220 tokens to every session and 3,156 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
webmcp-nexus
当接入 webmcp-nexus-sdk 的项目中需要新增 WebMCP 工具函数、将现有业务方法改造为 WebMCP 工具函数，或配置 vite-plugin-webmcp-nexus / webpack-plugin-webmcp-nexus 时使用本技能。本技能约束工具函数的签名、JSDoc、TS 类型写法，并提供零风险的改造流程（仅改签名与注释，不动原方法业务逻辑）。触发示例："新增一个 WebMCP 工具"、"把这个函数改造成能被 AI Agent 调用的工具"、"让 xxx 函数接入 WebMCP"、"配置 webmcp 构建插件"。.
generated-assets
Keep the README GIF and social preview card truthful by re-rendering them whenever a code change alters what they show.
live-api-verification
Verify response models and MCP transports against the real YNAB API before claiming a tool works.
dark-memory
Use for governance, memory, drift detection, and audit trail via dark-memory-mcp. Covers 52 canonical + 3 red-team tools across 16 namespaces: session lifecycle, agentmemory CRUD+search, vibe-flow spec/artifact publish + drift, LLM-as-judge, delegation+mindset, research, observability, error observatory, governance…
ynab-platform-compliance
Keep this project compliant with YNAB's API terms, OAuth requirements, naming rules, and branding restrictions.
driving-unreal
Use when driving an Unreal Engine 5.x editor through the unreal-ai-connection MCP tools — building or populating a level, spawning/transforming actors, authoring materials and material instances, setting up lighting and atmosphere, reconstructing a scene from a reference photo, setting up a sequencer/cinematic shot…