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 lubusIN/frappe-skills --skill app-developmentgit clone --depth 1 https://github.com/lubusIN/frappe-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/lubusin/frappe-skills/app-development)<a href="https://agentmods.dev/skills/lubusin/frappe-skills/app-development"><img src="https://agentmods.dev/badge/skills/lubusin/frappe-skills/app-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/lubusin/frappe-skills/app-development"><img src="https://agentmods.dev/badge/skills/lubusin/frappe-skills/app-development.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 | $0.00055 | $0.02474 |
| Opus 5.5 | $0.00022 | $0.00990 |
| Sonnet 5.5 | $0.00011 | $0.00495 |
| Haiku 4.5 | $0.00006 | $0.00247 |
Grade A, and why
app-development 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.
How it starts
The opening of the file, as written. The whole thing — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frappe App Development
Scaffold, structure, and architect custom Frappe applications with production-grade patterns.
When to use
- Creating a new custom Frappe app from scratch
- Setting up app architecture (modules, services, utils)
- Configuring
hooks.pyfor events, scheduler, overrides - Implementing background jobs and async processing
- Building service layers and domain logic patterns
- Adding caching, logging, error handling utilities
- Preparing apps for production deployment
- Managing translations, versioning, and packaging
Inputs required
- App name and purpose
- Target Frappe version (v13+, v15+, v16+)
- Module structure (which DocTypes, APIs, services)
- Whether hooks/overrides of other apps are needed
- Background job requirements
- Production readiness needs
Procedure
0) Scaffold the app
# Create the app
bench new-app my_app
# Install on site
bench --site mysite.local install-app my_app
# Verify developer mode
bench --site mysite.local console
>>> frappe.conf.developer_mode # Must be True
1) Plan app structure
Follow the domain architecture pattern — keep DocType controllers thin and business logic in service modules:
my_app/
├── my_app/
│ ├── __init__.py
│ ├── hooks.py # App hooks and configuration
│ ├── api.py # Public API surface (RPC endpoints)
│ ├── services/ # Business logic modules
│ │ └── billing.py
│ ├── utils/ # Cross-cutting utilities
│ │ ├── cache.py
│ │ ├── errors.py
│ │ ├── logging.py
│ │ ├── permissions.py
│ │ └── validation.py
│ ├── background_jobs/ # Async job handlers
│ │ └── export_job.py
│ ├── integrations/ # External system connectors
│ │ └── payment_gateway.py
│ ├── my_module/
│ │ ├── doctype/
│ │ │ └── my_doc/
│ │ │ ├── my_doc.json
│ │ │ ├── my_doc.py
│ │ │ ├── my_doc.js
│ │ │ └── test_my_doc.py
│ │ ├── report/
│ │ └── dashboard/
│ └── translations/
│ ├── en.csv
│ └── fr.csv
├── setup.py
└── README.md
What ships with it
29 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.
- assets/mini-app-template/your_app/api.py 1.8 KB runs code
- assets/mini-app-template/your_app/background_jobs/sample_job.py 488 B runs code
- assets/mini-app-template/your_app/dashboard/sample_doc_dashboard.json 373 B
- assets/mini-app-template/your_app/doctype/sample_doc_item/sample_doc_item.json 664 B
- assets/mini-app-template/your_app/doctype/sample_doc/sample_doc_dynamic_link.json 353 B
- assets/mini-app-template/your_app/doctype/sample_doc/sample_doc_naming_series.json 252 B
- assets/mini-app-template/your_app/doctype/sample_doc/sample_doc.js 706 B runs code
- assets/mini-app-template/your_app/doctype/sample_doc/sample_doc.json 1.3 KB
- assets/mini-app-template/your_app/doctype/sample_doc/sample_doc.py 581 B runs code
- assets/mini-app-template/your_app/doctype/sample_single/sample_single.json 462 B
- assets/mini-app-template/your_app/doctype/sample_submittable/sample_submittable.json 466 B
- assets/mini-app-template/your_app/doctype/sample_tree/sample_tree.json 513 B
- assets/mini-app-template/your_app/hooks.py 474 B runs code
- assets/mini-app-template/your_app/integrations/sample_connector.py 962 B runs code
- assets/mini-app-template/your_app/list_view/sample_doc_list.js 725 B runs code
- assets/mini-app-template/your_app/README.md 1.8 KB
- assets/mini-app-template/your_app/report/sample_report/sample_report.js 2.2 KB runs code
- assets/mini-app-template/your_app/report/sample_report/sample_report.json 204 B
- assets/mini-app-template/your_app/report/sample_report/sample_report.py 1.6 KB runs code
- assets/mini-app-template/your_app/services/sample_service.py 585 B runs code
- assets/mini-app-template/your_app/utils/cache.py 215 B runs code
- assets/mini-app-template/your_app/utils/errors.py 854 B runs code
- assets/mini-app-template/your_app/utils/logging.py 978 B runs code
- assets/mini-app-template/your_app/utils/permissions.py 423 B runs code
- assets/mini-app-template/your_app/utils/validation.py 428 B runs code
- assets/mini-app-template/your_app/workflow/sample_doc_workflow.json 714 B
- references/app-development.md 3.7 KB
- references/translations.md 714 B
- references/version-compat.md 552 B
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 · 322 lines · 55 tokens per session scan A 41300e5c0450
app-development is a skill published in the GitHub repository lubusIN/frappe-skills (68 stars, last pushed 2d ago), licensed MIT. It adds 55 tokens to every session and 2,474 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.
app-development compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| app-developmentlubusIN/frappe-skills | Skill | 68 | 2d ago | MIT | A | 55 | Claude Code, Codex |
| build-mcp-serveranthropics/claude-plugins-official | Skill | 46k | yesterday | Apache-2.0 | A | 111 | Claude Code |
| data-manager-api-setupgoogle/skills | Skill | 22k | yesterday | Apache-2.0 | A | 86 | Claude Code, Codex |
| vss-manage-video-io-storageNVIDIA-AI-Blueprints/video-search-and-summarization | Skill | 2.0k | yesterday | Apache-2.0 | A | 143 | Claude Code, Codex |
| workers-best-practicescloudflare/skills | Skill | 3.3k | yesterday | Apache-2.0 | A | 25 | Claude Code |
| vss-search-archiveNVIDIA-AI-Blueprints/video-search-and-summarization | Skill | 2.0k | yesterday | Apache-2.0 | A | 67 | Claude Code, Codex |
| newclacky-ai/openclacky | Skill | 1.2k | yesterday | MIT | A | 10 | Claude Code |