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 Mariatta/claude-skills --skill djangogit clone --depth 1 https://github.com/Mariatta/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/mariatta/claude-skills/django)<a href="https://agentmods.dev/skills/mariatta/claude-skills/django"><img src="https://agentmods.dev/badge/skills/mariatta/claude-skills/django/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/mariatta/claude-skills/django"><img src="https://agentmods.dev/badge/skills/mariatta/claude-skills/django.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 | $0.00210 | $0.04757 |
| Opus 5 | $0.00105 | $0.02379 |
| Sonnet 5 | $0.00042 | $0.00951 |
| Haiku 4.5 | $0.00021 | $0.00476 |
Grade A, and why
django 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 10d 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 — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Django conventions
These are one developer's house rules for their own Django projects. They are not Django community consensus, and they are not binding on anyone else's codebase.
When contributing to a project you do not own, that project wins. Its CLAUDE.md
or AGENTS.md, its existing code, its reviewers, and any explicit instruction all
take precedence over anything here, and where they are silent the surrounding code is
the better guide. Follow these by default on the owner's own projects; treat them as
a starting point everywhere else.
Each convention below states a principle that holds for any Django project,
then the concrete values for this one. Every concrete value (which formatters,
which threshold, which paths) comes from profile.json. Read it first; do not assume
the stack named here is the stack this project runs.
Adapting the skill to a different project is profile.json plus ADAPTING.md.
This skill is meant to grow. Each convention is self-contained. Add new ones under
## Conventions, and when a convention has real implementation detail, give it a
file under references/ and link it from here.
Conventions
Code style: match the project's formatters, and emit code that already passes
Principle. Whatever formatters and linters a project runs, match them and emit
code that passes them on the first try. CI runs them in check mode and fails on any
diff, so unformatted code never merges. Hand-formatting around a formatter wastes a
review cycle and produces a diff the next make reformat will undo.
The one trap worth knowing regardless of project: if both isort and black run, isort
must use profile = black. Otherwise the two rewrite imports each other's way
and CI never converges.
This project (profile.json → formatting). The stack is black, isort,
djlint, flake8, checked by make lint and autofixed by make reformat, each running
inside docker compose run --rm web.
- black formats Python on its defaults. There is no
[tool.black]block anywhere in the repo; do not add one. Write black-shaped code: no manual alignment, no fighting its line breaks. - isort sorts imports with
profile = black: stdlib, third-party, first-party, alphabetized, parenthesized multi-line imports with trailing commas. - djlint formats and lints Django templates with
profile = "django". Formatting and linting run as two separate commands, not combined. - flake8 lints Python with
max-line-length = 100butE501extended-ignored, so flake8 never fights black over length. Black's 88 governs in practice. makemigrations --checkalso runs inmake lint, so a model change without a migration fails the build.
What ships with it
6 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.
- 10d ago First seen · 380 lines · 0 tokens per session scan A dfe84a9d11ad
django is a skill published in the GitHub repository Mariatta/claude-skills (2 stars, last pushed 27d ago), licensed MIT. It adds 210 tokens to every session and 4,757 once invoked, about $0.0011 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.
Other skills, from other repositories
stripe-projects
Use after E2B sandbox/API access has been provisioned through Stripe Projects and the user needs to use the resulting E2B API key with the E2B CLI, JavaScript SDK, Python SDK, or Code Interpreter SDK.
azure-messaging-webpubsubservice-py
Azure Web PubSub Service SDK for Python. Use for real-time messaging, WebSocket connections, and pub/sub patterns. Triggers: "azure-messaging-webpubsubservice", "WebPubSubServiceClient", "real-time", "WebSocket", "pub/sub".
azure-mgmt-botservice-py
Azure Bot Service Management SDK for Python. Use for creating, managing, and configuring Azure Bot Service resources. Triggers: "azure-mgmt-botservice", "AzureBotService", "bot management", "conversational AI", "bot channels".
backend
Python server code, APIs, async, strict typing.
fastapi-app
Bootstrap a new FastAPI backend with async SQLAlchemy 2.0, asyncpg, Alembic, Pydantic v2, and no deprecated APIs. Use when the user wants to start, scaffold, or set up a new FastAPI service, a Python REST API, an async backend, or asks to "create a new fastapi app" or "new python backend". Handles JWT auth, layered…
azure-appconfiguration-py
Centralized configuration management with feature flags and dynamic settings.