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 agentmods add skills/rakaarwaky/qwen-web-arwaky/create-surface-pythonnpx skills add rakaarwaky/qwen-web-arwaky --skill create-surface-pythongit clone --depth 1 https://github.com/rakaarwaky/qwen-web-arwakyWhat 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 | $0.00050 | $0.00711 |
| Opus 5 | $0.00025 | $0.00356 |
| Sonnet 5 | $0.00010 | $0.00142 |
| Haiku 4.5 | $0.00005 | $0.00071 |
Grade A, and why
create-surface-python 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 3d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
create-surface-python
Surface = entry points and UI adapters. No business logic. Delegate to aggregates. File: surface_<domain>_<role>.py.
Three Types (AES406)
| Type | Suffixes | Imports | Forbidden |
|---|---|---|---|
| Smart | _command, _controller, _page, _entry |
taxonomy +contract_*_aggregate |
capabilities, concrete agents |
| Utility | _hook, _store, _action, _screen |
taxonomy + passive surfaces | smart surfaces, capabilities, agents |
| Passive | _component, _view, _layout |
taxonomy only | all other layers |
Rules
- Smart: inject
I<Name>Aggregatevia DI, delegate, return Result VO. - Utility: map events → VOs, hold minimal UI state, compose passive.
- Passive: render from VOs only — no computation, no orchestration.
- Never silently discard errors: forbidden
result = self.runner.run(r) or None. UseResult.ok/error update error state VO. - All state fields use shared VOs.
Helper vs Utility
Keep in surface file if ANY: uses self, surface-specific mapping, factory.
Extract to taxonomy utility only if ALL: no self, pure, domain-agnostic, reusable.
Templates
from shared.<domain>.taxonomy_<name>_vo import <VO>
from shared.<domain>.contract_<name>_aggregate import I<Name>Aggregate
class Surface<Name>:
def __init__(self, aggregate: I<Name>Aggregate):
self._aggregate = aggregate
def handle(self, event: TuiEvent) -> Result[UiState, SurfaceError]:
# orchestration only
return Ok(UiState.idle())
Workflow
- Determine type (Smart/Utility/Passive), choose suffix.
- Enforce import rules for that type.
- No silent error discard.
python -c "import <module>".
Checklist
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.
- 3d ago First seen · 80 lines · 50 tokens per session scan A c4664f0c0700
create-surface-python is a skill published in the GitHub repository rakaarwaky/qwen-web-arwaky (11 stars, last pushed 6d ago), licensed MIT. It adds 50 tokens to every session and 711 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
bump-dependency
Bumps a Python package dependency across Home Assistant Core integrations, regenerates core requirement files, runs verification tests and prek lint, and prepares a pull request with proper release/compare links.
biopython
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use…
marimo-pair
Work inside the user's live marimo notebook from the code editor: run Python in the same kernel the user does, inspect live notebook state, and commit durable notebook changes through code mode. Use whenever you create, analyze, or improve the user's marimo notebook.
adk-style
Python style and codebase conventions for ADK (Agent Development Kit): private-by-default file visibility, imports, type hints, Pydantic v2 models, formatting, docstrings, logging, async I/O, file and test layout, and unit test structure. Use when writing or editing ADK source or tests, deciding whether a new file or…
coding
编写并运行 Python 代码，验证脚本逻辑和输出。.
ax-python-agent
Use when writing Python code with axllm for agents, child delegation, tools, MCP, citations, persistent playbook learning, stage instructions, runtime state, final typed responses, and direct-respond executor skipping.