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 dvf/opinionated-django --skill dj-lintgit clone --depth 1 https://github.com/dvf/opinionated-djangoWrote 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/dvf/opinionated-django/dj-lint)<a href="https://agentmods.dev/skills/dvf/opinionated-django/dj-lint"><img src="https://agentmods.dev/badge/skills/dvf/opinionated-django/dj-lint/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/dvf/opinionated-django/dj-lint"><img src="https://agentmods.dev/badge/skills/dvf/opinionated-django/dj-lint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00058 | $0.00459 |
| Opus 5.5 | $0.00023 | $0.00184 |
| Sonnet 5.5 | $0.00012 | $0.00092 |
| Haiku 4.5 | $0.00006 | $0.00046 |
Grade A, and why
dj-lint 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 2mo 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
Lint and Type-Check
Run the full static-analysis suite on the project and fix any issues found.
uv run ruff check src— lint the codeuv run ruff format --check src— verify formattinguv run pyrefly check src— static type analysis
Fix every issue reported (re-run until clean) and report a short summary of what changed when done. If a failure is not auto-fixable, explain what needs human judgement rather than silencing it.
Pyrefly + Django gotchas
Pyrefly has built-in Django support (via django-stubs), but a few things aren't covered yet. Recognize these before reaching for # type: ignore:
- Reverse relations (
user.order_set,author.article_set) are not supported. This is a known pyrefly limitation, not a real bug. The right fix is to query the child model directly from its repository (OrderRepository().list_for_user(user_id)) — push the access down into the repo layer rather than suppressing it. Only if that's impossible, narrow it with# type: ignore[attr-defined]at a single call site. ManyRelatedManageris generic over[Parent, Model], not the concrete child. Don't rely on pyrefly to catch a mistyped M2M target — cover it with a test instead.- Chained QuerySet methods beyond
.all()are thinly typed. Keep chains inside the repository where the return type is an annotatedlist[SomeDTO]; don't let querysets leak out into services.
See pyrefly.org/en/docs/django for the current support matrix. Pyrefly's Django support is actively evolving — re-check when upgrading.
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.
- 2mo ago First seen · 26 lines · 58 tokens per session scan A 53dac938acb7
dj-lint is a skill published in the GitHub repository dvf/opinionated-django (111 stars, last pushed 2mo ago), licensed MIT. It adds 58 tokens to every session and 459 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 2026-08-30.
dj-lint compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dj-lintdvf/opinionated-django | Skill | 111 | 2mo ago | MIT | A | 58 | Claude Code |
| python-code-qualitymicrosoft/agent-framework | Skill | 15k | today | MIT | A | 40 | Claude Code, Codex |
| plugin-architecture-patternsxberg-io/xberg | Skill | 9.6k | today | MIT | A | 15 | Claude Code |
| test-corpusxberg-io/xberg | Skill | 9.6k | today | MIT | A | 15 | Claude Code, Codex |
| python-debug-execution-911f17HKUDS/OpenSpace | Skill | 7.9k | 2d ago | MIT | A | 23 | Claude Code, Codex |
| stack-trace-python-probeopensquilla/opensquilla | Skill | 7.1k | 2d ago | Apache-2.0 | A | 40 | Claude Code |
| idapythonmrexodia/ida-pro-mcp | Skill | 13k | 1mo ago | MIT | A | 77 | Claude Code |