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 instructions/7tg/django-admin-mcp/agents-mdgit clone --depth 1 https://github.com/7tg/django-admin-mcpWrote 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/instructions/7tg/django-admin-mcp/agents-md)<a href="https://agentmods.dev/instructions/7tg/django-admin-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/7tg/django-admin-mcp/agents-md.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 | $0.02370 | $0.02370 |
| Opus 5 | $0.01185 | $0.01185 |
| Sonnet 5 | $0.00474 | $0.00474 |
| Haiku 4.5 | $0.00237 | $0.00237 |
Grade A, and why
django-admin-mcp AGENTS.md 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 3d 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 — 336 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - AI Agent Instructions for django-admin-mcp
This document provides context and guidelines for AI agents (GitHub Copilot, etc.) working on this codebase.
Project Overview
django-admin-mcp is a Django package that exposes Django admin models to MCP (Model Context Protocol) clients via HTTP. It enables AI assistants to interact with Django admin interfaces through standardized tools, providing CRUD operations, admin actions, model history, and more.
Key Features
- Zero dependencies beyond Django and Pydantic
- Token-based HTTP authentication with configurable expiry
- Respects Django admin permissions (view/add/change/delete)
- Full CRUD, bulk operations, admin actions, model introspection
- Related object traversal and change history access
Architecture
MCP Client (IDE, Agent, etc.)
↓ HTTP + Bearer Token
MCPHTTPView (django_admin_mcp/views.py)
↓ JSON-RPC
Tools Registry (django_admin_mcp/tools/registry.py)
↓
Handlers (django_admin_mcp/handlers/)
↓
Django Admin + ModelAdmin
↓
Database
Directory Structure
django-admin-mcp/
├── django_admin_mcp/ # Main package
│ ├── __init__.py # Public exports (MCPAdminMixin)
│ ├── mixin.py # Core MCPAdminMixin class
│ ├── models.py # MCPToken model (authentication)
│ ├── views.py # HTTP view (MCPHTTPView)
│ ├── admin.py # Django admin registration
│ ├── apps.py # Django app config
│ ├── urls.py # URL routing
│ ├── handlers/ # Operation handlers
│ │ ├── base.py # Base utilities, permissions
│ │ ├── crud.py # Create, Read, Update, Delete
│ │ ├── actions.py # Admin actions
│ │ ├── relations.py # Foreign key relations
│ │ └── meta.py # Model introspection
│ ├── protocol/ # MCP protocol implementation
│ │ ├── types.py # Pydantic type definitions
│ │ ├── jsonrpc.py # JSON-RPC implementation
│ │ └── errors.py # Error definitions
│ ├── tools/ # Tool registry and management
│ │ ├── registry.py # Tool registration and routing
│ │ └── __init__.py # Tool exports
│ └── migrations/ # Database migrations
├── example/ # Example Django application
├── tests/ # Test suite (pytest)
├── docs/ # Documentation (OpenAPI specs)
└── plans/ # Future improvement plans
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.
- 3d ago First seen · 336 lines · 2,370 tokens per session scan A 41a7902cee0d
django-admin-mcp AGENTS.md is an instructions file published in the GitHub repository 7tg/django-admin-mcp (16 stars, last pushed 1mo ago), licensed MIT. It adds 2,370 tokens to every session, about $0.0119 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.
Other instructions, from other repositories
django-ninja-aio-crud CLAUDE.md
Instructions for caspel26/django-ninja-aio-crud, covering claude.md, project overview, project structure, running tests and test-driven development protocol.
django-admin-mcp-api CLAUDE.md
Instructions for MartinCastroAlvarez/django-admin-mcp-api, covering claude.md, 0. required reading, 1. mission summary, 2. the five rules and 3. working agreements.
gmgn-skills CLAUDE.md
Instructions for GMGNAI/gmgn-skills, covering claude.md, critical rule — read this first, project overview, available skills and quick decision guide.
go-proxmox AGENTS.md
Instructions for luthermonson/go-proxmox, covering agents.md, build, test, lint, integration test env vars, architecture and client and request layer (proxmox.go).
ultracontext CLAUDE.md
Instructions for ultracontext/ultracontext, covering claude.md, architecture, context api (apps/api), sync (apps/sync) and mcp server (apps/mcp-server).
pruna-skills AGENTS.md
AGENTS.md instructions for PrunaAI/pruna-skills, covering pruna skills (agent notes), how it works, clarification (library-wide), install and layout.