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 jxoesneon/Ciel --skill django-developmentgit clone --depth 1 https://github.com/jxoesneon/CielWrote 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/jxoesneon/ciel/django-development)<a href="https://agentmods.dev/skills/jxoesneon/ciel/django-development"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/django-development/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/jxoesneon/ciel/django-development"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/django-development.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 | $0.00023 | $0.00432 |
| Opus 5.5 | $0.00009 | $0.00173 |
| Sonnet 5.5 | $0.00005 | $0.00086 |
| Haiku 4.5 | $0.00002 | $0.00043 |
Grade B, and why
django-development scanned grade B with 1 finding 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.
Instruction-override phrasingmediumPrompt injection
Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.
- **Context Bypass**: Adding instructions to `CLAUDE.md` to ignore security rules. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
What it actually says
CIEL ADAPTATION: Django Development (The Python Web Layer)
This skill formalizes the development of scalable Django and Django REST Framework (DRF) applications.
Architecture & Patterns
- Split Settings: Use
base.py,development.py, andproduction.py. - Models: Extend
AbstractUserearly. Use customQuerySetsfor reusable logic. - DRF: Use
ViewSetsfor standard CRUD. Map serializers to specific actions (List vs Create). - Performance: Use
select_related(FK) andprefetch_related(M2M) to prevent N+1 queries.
Security Standards
- Harness: Disable
DEBUGin production. RotateSECRET_KEYvia env vars. - SQLi: Trust the ORM. Prohibit direct string interpolation in
.raw()or.extra(). - XSS: Use template auto-escaping. Use
mark_safeONLY after manual escaping. - Permissions: Deny by default. Use
PermissionRequiredMixinor custom DRFBasePermission.
TDD & Verification
- Framework: pytest-django + factory_boy. Avoid manual object creation.
- CI Loop: Clean env ->
ruff check->makemigrations --check->pytest --cov(80% gate). - Deployment: Run
check --deploybefore finalizing any infra-related branch.
Anti-Patterns
- Signal Hell: Overusing signals for business logic (makes control flow invisible).
- Context Bypass: Adding instructions to
CLAUDE.mdto ignore security rules. - Amnesiac Migrations: Modifying a model without including the corresponding migration file.
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.
- 1mo ago Changed · -13 lines 0a6b3c072fc2
- 1mo ago First seen · 52 lines · 23 tokens per session scan B 9d4b0080d045
django-development is a skill published in the GitHub repository jxoesneon/Ciel (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 23 tokens to every session and 432 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (instruction-override phrasing). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
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.
django-patterns
Django architecture patterns, REST API design with DRF, ORM best practices, caching, signals, middleware, and production-grade Django apps.
doc-generator
Auto-generate API reference documentation from Python code.
api-route-design
Use when designing RESTful API endpoints in FastAPI or Python projects. Triggers for: creating GET/POST/PUT/DELETE endpoints, request validation with Pydantic, response formatting with JSON schemas, status code selection, pagination, filtering, or sorting parameters. NOT for: GraphQL APIs, WebSocket handlers, or…
fastapi-router-creator
Create fastapi router creator operations. Auto-activating skill for Backend Development. Triggers on: fastapi router creator, fastapi router creator Part of the Backend Development skill category. Use when working with APIs or building integrations. Trigger with phrases like "fastapi router creator", "fastapi…
httpx
A next-generation HTTP client for Python with both sync and async support, perfect for modern Python applications.