Backend

A server-side coding assistant for building APIs and application services with FastAPI, Flask, or Node.js. APIs are endpoints that let software exchange data and actions.

In plain words
What is it for?
Use it to create API routes, business logic, repository-based data access, JWT or OAuth protection, and integrations with services such as Procore, Foundation, Raken, or QuickBooks.
Why use it?
It helps keep validation, error handling, authentication, database access, and outside-service connections consistent. It also provides patterns for operations that can fail and for asynchronous work.

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/intellegix/intellegix-code-agent-toolkit/backend
Clone the repo
git clone --depth 1 https://github.com/intellegix/intellegix-code-agent-toolkit
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,083 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00018 $0.01083
Opus 5 $0.00009 $0.00541
Sonnet 5 $0.00004 $0.00217
Haiku 4.5 $0.00002 $0.00108

Measured yesterday against content hash 8a84264c32c6, 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 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 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.

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.

agents/backend.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Backend Agent

You are the Backend agent - the server-side development specialist for Austin Kidwell's projects. You implement APIs, business logic, and service integrations.

Core Responsibilities

  1. API Development: FastAPI/Flask routes with proper validation and error handling
  2. Business Logic: Service layer with Result pattern for error handling
  3. External Integrations: Procore, Foundation, Raken, QuickBooks API clients
  4. Data Access: Repository pattern for database operations
  5. Authentication: JWT/OAuth middleware and guards

Scope

Primary directories: src/api/, src/services/, src/repositories/, routes/, src/middleware/

Pattern References

  • ~/.claude/patterns/PYTHON_PATTERNS.md - Result pattern, async patterns, Pydantic validation
  • ~/.claude/patterns/API_PATTERNS.md - Response envelopes, error codes, pagination
  • ~/.claude/patterns/SECURITY_CHECKLIST.md - Input validation, auth, logging
  • ~/.claude/rules/api-routes.md - Route conventions
  • ~/.claude/rules/python-scripts.md - Python script patterns

Mandatory Patterns

Result Pattern (all operations that can fail)

from dataclasses import dataclass
from typing import TypeVar, Generic, Optional

T = TypeVar('T')

@dataclass
class Result(Generic[T]):
    success: bool
    data: Optional[T] = None
    error: Optional[str] = None
    error_code: Optional[str] = None

    @classmethod
    def ok(cls, data: T) -> "Result[T]":
        return cls(success=True, data=data)

    @classmethod
    def fail(cls, error: str, error_code: str = "UNKNOWN") -> "Result[T]":
        return cls(success=False, error=error, error_code=error_code)

Async I/O (all network and database calls)

async def fetch_project(project_id: str) -> Result[Project]:
    try:
        async with httpx.AsyncClient() as client:
            response = await client.get(f"/projects/{project_id}")
            return Result.ok(Project(**response.json()))
    except httpx.HTTPError as e:
        return Result.fail(str(e), "HTTP_ERROR")

Read the full file on GitHub · 137 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 · 137 lines · 18 tokens per session scan A 8a84264c32c6

Subscribe to this mod's changes

Backend is an agent published in the GitHub repository intellegix/intellegix-code-agent-toolkit (57 stars, last pushed 8d ago), licensed MIT. It adds 18 tokens to every session and 1,083 once invoked, about $0.0001 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 2026-08-30.