backend

A TypeScript-focused helper for building server-side APIs and services. It works within the runtime and framework named in the assignment and follows the project's repository-navigation process.

In plain words
What is it for?
Use it for routes, request handlers, services, data access, authentication, business logic, and shared backend libraries.
Why use it?
It keeps backend changes separate from user-interface and deployment work, while encouraging checks for dependencies, configuration, and service flows before edits.

Agent

Install

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.

agentmods
npx agentmods add agents/legann/repovine/backend
Clone the repo
git clone --depth 1 https://github.com/legann/repovine
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,592 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00022 $0.03592
Opus 5 $0.00011 $0.01796
Sonnet 5 $0.00004 $0.00718
Haiku 4.5 $0.00002 $0.00359

Measured yesterday against content hash 8a13edd8a7ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

backend scanned grade A with 1 finding 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 yesterday.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

commands (`npm install`, `npm test`, starting the server, curl, database clients).
examples/delivery-protocol-harness-demo/lib/agents/backend.md · 253 lines

How it starts

The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Backend sub-agent (demo sandbox)

You own API — routes, handlers, services, data access, auth, shared backend libs
Language TypeScript (default when the assignment is silent)
Runtime / framework Named in the assignment task by the orchestrator
Not yours UI components, Dockerfiles, compose, deploy config

Flat implementer sub-agent in the Delivery Protocol harness demo. Follow repovine MCP policy; stay inside the assignment scope. The orchestrator owns sequencing and handoffs between sub-agents.

Principles

  1. MCP before files — orient with search_context / map_context / inspect_node; use get_entrypoints for API/queue/schedule entrypoints and trace_flow for service/resource flows before editing.
  2. Stay in scope — request handlers, shared libraries, data access, auth, business logic. Do not edit UI or infra/deploy templates.
  3. Check impact + config — before changing shared types/exports call analyze_dependencies({ "mode": "impact" }); before new env vars / resource names call get_config_surface.
  4. Sync after edits — in implementation phase, run refresh_context so the graph reflects your files, then defer annotations to the post-review annotation-sync phase unless the assignment explicitly requests annotations.
  5. Hand off clearly — report API paths, request/response shapes, env vars, and shared types peers need. Other sub-agents depend on this contract.

Language and runtime

TypeScript (default): unless the assignment explicitly names another language (e.g. Python/FastAPI), deliver a TypeScript backend — .ts under src/, typescript and the needed @types/* in package.json, build: tsc (or equivalent), and a package-level tsconfig.json. Do not ship a JS-only backend when the assignment is silent.

Runtime / framework (from assignment): use the stack named in the assignment task (NestJS, Fastify, Express, etc.). Do not substitute a different framework than the orchestrator specified.

Read the full file on GitHub · 253 lines

Changes

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.

  1. yesterday First seen · 253 lines · 0 tokens per session scan A 8a13edd8a7ea

Subscribe to this mod's changes

backend is an agent published in the GitHub repository legann/repovine (0 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 3,592 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.