django-modern-rest is a typed REST framework for Django, the Python web framework, for building APIs that exchange data with clients over HTTP. It is for Django developers who need asynchronous support, schema validation, multiple data formats, and generated OpenAPI descriptions. The catalogue add-ons provide plugins and skills for developing with the framework.
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 wemake-services/django-modern-rest --skill dmr-upgradegit clone --depth 1 https://github.com/wemake-services/django-modern-restWrote 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/wemake-services/django-modern-rest/dmr-upgrade)<a href="https://agentmods.dev/skills/wemake-services/django-modern-rest/dmr-upgrade"><img src="https://agentmods.dev/badge/skills/wemake-services/django-modern-rest/dmr-upgrade/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/wemake-services/django-modern-rest/dmr-upgrade"><img src="https://agentmods.dev/badge/skills/wemake-services/django-modern-rest/dmr-upgrade.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 | $0.00067 | $0.00853 |
| Opus 5.5 | $0.00027 | $0.00341 |
| Sonnet 5.5 | $0.00013 | $0.00171 |
| Haiku 4.5 | $0.00007 | $0.00085 |
Grade A, and why
dmr-upgrade 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 yesterday.
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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DMR upgrade
Overview
Every breaking django-modern-rest release ships an official migration prompt.
The prompts of the three latest breaking releases live in this skill,
one file per release in references/.
The CHANGELOG.md of the package lists the breaking changes themselves.
Do not guess how an API changed. Read the prompt for every release between the installed version and the target version and apply all of it.
Workflow
Find the current and the target versions
- Current:
uv pip show django-modern-rest,pip show django-modern-rest, or the pinned version inuv.lock,poetry.lock, orrequirements.txt. - Target: the version the user asked for, otherwise the latest release on https://pypi.org/project/django-modern-rest/.
- Tell the user which releases lie in between and that each one is applied in order. Never skip a release.
Bump the dependency
Update pyproject.toml (or the requirements file) to the target version
and install it, so the type checker sees the new API.
Apply each migration prompt
Read the prompt files for the selected releases, oldest first, and apply every numbered item to the whole project (source, tests, fixtures, settings, management commands):
| Upgrade across | Prompt |
|---|---|
| 0.13 to 0.14 | references/0.13-to-0.14.md |
| 0.14 to 0.15 | references/0.14-to-0.15.md |
| 0.15 to 0.16 | references/0.15-to-0.16.md |
Releases in between that are not listed had no breaking changes.
When the project is on a version older than 0.13, the prompts
of the older releases are not in this skill:
since 0.13.0 they are the descriptions of the releases on
https://github.com/wemake-services/django-modern-rest/releases,
before that they are in CHANGELOG.md. Apply them first, the same way.
Apply one release at a time and keep its edits together, so the user can review them release by release.
When the installed docs matter, load the version-specific index:
https://django-modern-rest.readthedocs.io/en/<version>/llms.txt
(every page is also served as Markdown, replace .html with .md).
What ships with it
5 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.
- yesterday First seen · 87 lines · 67 tokens per session scan A 0f84e1465001
dmr-upgrade is a skill published in the GitHub repository wemake-services/django-modern-rest (1,519 stars, last pushed yesterday), licensed MIT. It adds 67 tokens to every session and 853 once invoked, about $0.0003 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 2026-10-26.
Other skills, from other repositories
api-integration-architect
Design, implement, debug, and optimize API integrations with expert-level patterns for REST, GraphQL, webhooks, and authentication flows.
horse-database-pooling
Guide for setting up thread-safe database connection pooling (FireDAC / UniDAC) in multithreaded Horse applications.
horse-request-response
Guide to interacting with THorseRequest (body, query, params, headers) and THorseResponse (Send, Status, ContentType).
horse-dependency-injection
Guide for managing request-scoped contextual services and IoC (dependency injection) in Delphi and Lazarus.
horse-mvc-architecture
Guide for structuring corporate Horse applications using Clean MVC (Model-View-Controller) principles and decoupling HTTP layers from business logic.
horse-app-structure
Guide for setting up Horse applications, bootstrap program (.dpr), basic console initialization, and registering modules.