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 fmind/dot --skill djangogit clone --depth 1 https://github.com/fmind/dotWrote 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/fmind/dot/django)<a href="https://agentmods.dev/skills/fmind/dot/django"><img src="https://agentmods.dev/badge/skills/fmind/dot/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/fmind/dot/django"><img src="https://agentmods.dev/badge/skills/fmind/dot/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 | $0.00036 | $0.00948 |
| Opus 5 | $0.00018 | $0.00474 |
| Sonnet 5 | $0.00007 | $0.00190 |
| Haiku 4.5 | $0.00004 | $0.00095 |
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 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Django
Use Django when its integrated ORM, migrations, forms, templates, authentication, and admin reduce the total system; python-stack owns non-Django Python packages, CLIs, and Litestar services.
Workflow
- Establish the framework contract: inspect the installed Django version, settings, URL configuration, apps, migrations, database, and deployment target before editing; for a new application, read bootstrap.
- Model the domain first: keep apps cohesive, encode invariants with fields, constraints, forms, and transactions, and decide whether a custom user model is needed before the first migration.
- Prefer Django's integrated path: start with server-rendered templates, forms, authentication, and admin; add an API framework, task backend, cache, or JavaScript layer only for a demonstrated requirement.
- Keep control flow visible: use thin views and explicit functions for multi-step use cases; avoid signals, custom middleware, managers, or repository/service layers when ordinary Django code is clearer.
- Choose sync deliberately: default to synchronous request and transaction code; use async only for measured concurrent I/O and verify the ASGI, middleware, ORM, connection-pooling, and transaction boundaries end to end.
- Treat schema changes as code: review generated migrations, preserve applied migration history, test data migrations in both directions when reversible, and never infer production schema state from models alone.
- Verify the behavior: run focused model, form, permission, view, and template tests, then the project gate; include Django system, deployment, and migration-drift checks.
uv run python manage.py check --fail-level WARNING
uv run python manage.py makemigrations --check --dry-run
uv run pytest
mise run check
mise run test
Gotchas
- Generated settings are development-only: move secrets and environment-specific values to validated inputs, default
DEBUGoff, and runcheck --deployagainst production-like settings. - User models are an early boundary: changing
AUTH_USER_MODELafter tables exist is complex; make the decision before the firstmigrateand reference users throughsettings.AUTH_USER_MODELorget_user_model(). - Async is not a blanket optimization: transactions still do not work in async mode, so keep transactional work in a synchronous function called through
sync_to_async(); disableCONN_MAX_AGEunder ASGI in favor of the database backend's own pooling, and never setDJANGO_ALLOW_ASYNC_UNSAFEto bypass the safety check. - Django needs stubs to type-check: add
django-stubsas a dev dependency ortyreportsunresolved-attributeonModel.objects; it reads PEP 561 stubs only, so declare reverse accessors underif TYPE_CHECKING:ascomments: RelatedManager[Comment]rather than suppressing the diagnostic. runserveris not production: choose and test a production WSGI or ASGI server only after the deployment target and concurrency model are known.
What ships with it
1 file 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.
- today Changed · +1 lines 86f595a21d14
- 3d ago First seen · 46 lines · 36 tokens per session scan A 5293130bb7d5
django is a skill published in the GitHub repository fmind/dot (4 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 948 once invoked, about $0.0002 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 2026-09-09.
Other skills, from other repositories
python-stack
Build typed Python projects with uv, Ruff, ty, pytest, Litestar, and Typer. Use for packages, CLIs, web apps, tests, typing, or API verification.
python-script
Write standalone single-file Python scripts using PEP 723 inline metadata and uv. Use when creating a quick CLI script that needs dependencies without a full project.
go-stack
Build Go projects, libraries, CLIs, TUIs, web apps, or ADK agents with the standard package layout and pinned tooling.
scaffold-python
Scaffold a complete Python project with CI/CD, release pipeline, justfile, sr.yaml, pyproject.toml, .envrc, and standard files. Uses uv, ruff, and justfile (Python lacks a native task runner like pnpm scripts, so just fills that gap). Loads on top of scaffold-project (run that first for cross-language standard files).…
k8s-local
Create and manage local Kubernetes clusters (k3d or kind) and deploy to them with kubectl, helm, helmfile, and skaffold. Use for local k8s cluster setup, dev loops, and debugging.
release
Cut or verify a versioned release — bump semver, generate the changelog with git-cliff, tag and publish on GitHub, or reconcile an already-published tag and assets.