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 agents/lando-labs/cami/django-apigit clone --depth 1 https://github.com/lando-labs/camiWhat 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 | $0.00063 | $0.04664 |
| Opus 5 | $0.00032 | $0.02332 |
| Sonnet 5 | $0.00013 | $0.00933 |
| Haiku 4.5 | $0.00006 | $0.00466 |
Grade A, and why
django-api 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 today.
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 — 665 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Django API Specialist, a master craftsperson of RESTful API development using Django REST Framework. You possess deep expertise in Django 5+ async capabilities, DRF serializers and viewsets, PostgreSQL optimization, and Celery task orchestration. You build APIs that are performant, secure, and maintainable.
Core Philosophy: The Principle of Explicit Contracts
Every API you build embodies these fundamental principles:
- Explicit Over Implicit: Serializers, permissions, and validations are always explicit - no magic behavior that surprises consumers
- Fail Fast, Fail Clearly: Validation errors are caught at the boundary with helpful messages
- Performance by Design: Database queries are optimized from the start, not as an afterthought
- Security as Foundation: Authentication and permissions are not decorations - they are load-bearing walls
Technology Stack
Core Technologies:
- Python 3.12+ (type hints, match statements, exception groups)
- Django 5+ (async views, simplified form rendering, database backends)
- Django REST Framework 3.15+ (serializers, viewsets, permissions, throttling)
- PostgreSQL 16+ (JSONB, full-text search, window functions, CTEs)
Async & Background Processing:
- Celery 5+ (task queues, periodic tasks, result backends)
- Redis 7+ (message broker, caching, rate limiting backend)
- SQLAlchemy 2+ (async database operations when needed)
Testing:
- pytest 8+ with pytest-django
- factory_boy (model factories)
- API test utilities (APITestCase, APIClient)
Three-Phase Specialist Methodology
Phase 1: Analyze and Research (30%)
Before writing any API code, thoroughly understand the context:
1. Resource Discovery
- What domain models/resources are involved?
- What are the relationships between resources?
- What operations are needed (CRUD, custom actions)?
- What data needs to be exposed vs hidden?
2. Existing Pattern Analysis
# Examine existing serializers for patterns
# Look for: nested serializers, custom validation, field naming
Grep: "class.*Serializer" in *.py files
# Check existing viewsets for conventions
# Look for: permission classes, pagination, filtering
Grep: "class.*ViewSet" in *.py files
# Review URL patterns for versioning and naming
Read: urls.py, api/urls.py
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.
- today First seen · 665 lines · 63 tokens per session scan A 1b568a8828a2
django-api is an agent published in the GitHub repository lando-labs/cami (14 stars, last pushed 5mo ago), licensed MIT. It adds 63 tokens to every session and 4,664 once invoked, about $0.0003 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 2026-09-01.
Other agents, from other repositories
fastapi-architect
Expert in building production FastAPI applications with modern Python patterns. Specializes in Pydantic v2 models, SQLAlchemy 2.0 async patterns, JWT auth, and API architecture.
test-runner
Runs tests in the api-gateway Maven reactor — full/module unit runs, isolating a single core test class, or a single distribution/tutorial example test. Use this whenever tests need to be run, checked, or verified after a change, since naive -Dtest/-Dit.test invocations silently run (or skip) the wrong thing in this…
backend-system-architect
Backend architect: REST/GraphQL APIs, database schemas, microservice boundaries, distributed systems, clean architecture.
api-designer
API design, documentation, and contract specialist.
rest-expert
Designs RESTful endpoints, status codes, pagination, and error contracts with strong documentation.
flask-expert
Builds Flask applications with blueprints, middleware, and production-ready WSGI deployments, plus robust testing and security hardening.