django-react

An orchestrator command for building full-stack applications with Django, a Python web framework, and React with TypeScript, a language that adds type checking to JavaScript. It sends the work to specialist agents instead of editing code directly.

In plain words
What is it for?
Use it for Django APIs, React interfaces, or features that span both sides of the application. It supports quick, standard, and more involved task paths.
Why use it?
It routes a task through a defined development process suited to this backend and frontend combination.

Command

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 commands/adilkalam/orca/django-react
Clone the repo
git clone --depth 1 https://github.com/adilkalam/orca
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 7,224 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 $0.07224
Opus 5 $0.00009 $0.03612
Sonnet 5 $0.00004 $0.01445
Haiku 4.5 $0.00002 $0.00722

Measured yesterday against content hash 38f20eda1004, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

django-react 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.

commands/django-react.md · 809 lines

How it starts

The opening of the file, as written. The whole thing — 809 lines — stays where its author put it; the contents beside it link to each section on GitHub.

STOP - DELEGATION ONLY

Before you do ANYTHING else, read this.

This slash command EXISTS to delegate work to agents. Not to do work directly.

NEVER acceptable:

  • "This is simple, I'll just do it directly"
  • "Let me quickly fix this"
  • "I can handle this without agents"
  • Using Edit/Write tools to make changes yourself

ALWAYS required:

  1. Parse the arguments
  2. Determine routing (--tweak, default, --complex)
  3. Spawn specialists single-level via the Agent tool (you are the orchestrator, in the main thread — no orchestrator subagent; OS 7.1)

Even --tweak delegates to a builder. It skips gates, not agents.

If you are about to Edit/Write, STOP. Delegate instead.


/django-react - Django + React TypeScript Lane Orchestrator (OS 7.1)

Use this command for full-stack Django backend + React TypeScript frontend work.

Usage

/django-react "add user profile API"       # Default: light path + design gates
/django-react --tweak "fix form validation" # Fast: light path, no gates
/django-react --complex "multi-step checkout flow"  # Full: architect + builder + all gates
/django-react "implement requirement 2025-01-15-0930-auth-system"  # Full path with spec

CRITICAL ROLE BOUNDARY

YOU ARE AN ORCHESTRATOR. YOU NEVER WRITE CODE.

  • DO NOT use Edit/Write tools
  • DO NOT bypass the agent system
  • DELEGATE via the Agent tool only (single-level, from the main thread)
  • Update phase_state.json to track progress
  • Resume from interruptions without abandoning pipeline

Tool Requirements (CRITICAL)

Backend (Python/Django): Always use uv - NEVER use pip or python directly:

  • uv run pytest (not pytest or python -m pytest)
  • uv run manage.py runserver (not python manage.py)
  • uv run manage.py migrate (not python manage.py migrate)
  • uv run mypy . (not mypy)
  • uv pip install (not pip install)

Frontend (React/TypeScript): Always use bun - NEVER use npm or yarn:

  • bun test (not npm test or yarn test)
  • bun run build (not npm run build)
  • bun run typecheck (not npm run typecheck)
  • bun install (not npm install)
  • bunx for one-off commands (not npx)

Read the full file on GitHub · 809 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 · 809 lines · 18 tokens per session scan A 38f20eda1004

Subscribe to this mod's changes

django-react is a command published in the GitHub repository adilkalam/orca (2 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 7,224 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 2026-08-31.