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 skills add FutureJJ/claude-skills --skill django-mastergit clone --depth 1 https://github.com/FutureJJ/claude-skillsWrote 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/skills/futurejj/claude-skills/django-master)<a href="https://agentmods.dev/skills/futurejj/claude-skills/django-master"><img src="https://agentmods.dev/badge/skills/futurejj/claude-skills/django-master/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/futurejj/claude-skills/django-master"><img src="https://agentmods.dev/badge/skills/futurejj/claude-skills/django-master.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00054 | $0.00337 |
| Opus 5.5 | $0.00022 | $0.00135 |
| Sonnet 5.5 | $0.00011 | $0.00067 |
| Haiku 4.5 | $0.00005 | $0.00034 |
Grade A, and why
django-master 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 1mo 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.
What it actually says
Django Master
You are a Django expert focused on ORM optimization, DRF best practices, and scalable project architecture.
Core Principles
- Fat models, thin views. Business logic belongs in models/managers, not views.
- QuerySet chaining. Custom managers return querysets, enabling composable queries.
- N+1 awareness. Always use
select_related(FK) andprefetch_related(M2M) before iterating. - DRF serializers validate. Never trust incoming data — validate in serializers, not views.
Anti-Patterns
- Calling
.all()then filtering in Python — filter in the database - N+1 queries in serializers — use
select_related/prefetch_relatedin the viewset's queryset - Raw SQL when the ORM can handle it — ORM is safer and more maintainable
- Fat views with business logic — move to model methods or services
Reference Guide
| Topic | Reference | Load When |
|---|---|---|
| ORM patterns | references/orm-patterns.md |
Complex queries, managers, optimization |
| DRF patterns | references/drf-patterns.md |
Serializers, viewsets, permissions |
| Project structure | references/project-structure.md |
App organization, settings, deployment |
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 31 lines · 54 tokens per session scan A 3fb02a754a16
django-master is a skill published in the GitHub repository FutureJJ/claude-skills (3 stars, last pushed 7mo ago), licensed MIT. It adds 54 tokens to every session and 337 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
insforge
Use this skill when writing app code with InsForge or @insforge/sdk: database CRUD, auth, storage uploads/storage RLS, functions, OpenRouter AI, realtime, emails, Stripe or Razorpay payments, or pointing S3-compatible tooling (aws CLI, AWS SDKs, rclone, Terraform, boto3) at InsForge Storage. Trigger on requests like…
firebase-development
This skill should be used when working with Firebase projects, including initializing projects, adding Cloud Functions or Firestore collections, debugging emulator issues, or reviewing Firebase code. Triggers on "firebase", "firestore", "cloud functions", "emulator", "firebase auth", "deploy to firebase", "firestore…
python-database-patterns
SQLAlchemy and database patterns for Python. Triggers on: sqlalchemy, database, orm, migration, alembic, async database, connection pool, repository pattern, unit of work.
convex-expert
Convex backend specialist. Use this agent for any code inside a convex/ directory — function definitions, schemas, indexes, queries, mutations, actions, HTTP endpoints, cron jobs, file storage, auth wiring, and component installation. Knows the object-form function syntax, validator patterns, resource limits, and…
convex-design
Design and build reactive, type-safe, production-grade backends on Convex. Covers schema, queries/mutations/actions, indexes, auth, file storage, scheduling, real-time multiplayer, mobile backends, and LLM/agent workflows on Convex's one-platform stack.
convex-suggest
Suggest the matching Convex component when the user hand-rolls a pattern it already solves (crons, sharded-counter, rate-limiter, storage, search, presence, workflow, RAG, prosemirror-sync). Passive — suggest after the task, never interrupt. Never install without consent.