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 adonai-labs/agent-runway --skill skill-python-coregit clone --depth 1 https://github.com/adonai-labs/agent-runwayWrote 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/adonai-labs/agent-runway/skill-python-core)<a href="https://agentmods.dev/skills/adonai-labs/agent-runway/skill-python-core"><img src="https://agentmods.dev/badge/skills/adonai-labs/agent-runway/skill-python-core/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/adonai-labs/agent-runway/skill-python-core"><img src="https://agentmods.dev/badge/skills/adonai-labs/agent-runway/skill-python-core.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 | $0.00076 | $0.00650 |
| Opus 5.5 | $0.00030 | $0.00260 |
| Sonnet 5.5 | $0.00015 | $0.00130 |
| Haiku 4.5 | $0.00008 | $0.00065 |
Grade A, and why
python-core 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 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.
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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python Core
How to invoke
After agent-runway add python, the skill is installed at .cursor/skills/python-core/. Use:
- Cursor:
@python-coreor ask a Python question while editing*.py(rules auto-attach) - Claude Code: reference
.agent-runway/skills/python-core/SKILL.mdor ask in context of Python files
Examples:
- How should I structure this FastAPI service?
- How do I test this use case without hitting the database?
- How do I add structured logging with correlation IDs?
- Is this error handling idiomatic Python?
Not sure which skill to use? Start with
/start— it classifies intent and routes to the right skill.
Guiding principles
Simplicity first. Python's culture favours readability and directness — respect it.
- Start flat; add structure only when complexity demands it
- One function, one responsibility — small, testable, named for what it does
- SOLID applies: DIP via dependency injection, ISP via focused ABCs, DRY for business logic
- Prefer explicit over magic; avoid metaclasses, deep decorators, and framework-specific tricks unless necessary
- Clean Architecture at the right scale — do not introduce it for a script or a small API
What this skill helps with
- Project structure scaled to complexity — scripts to full layered services
- FastAPI / Django REST / Flask patterns — routing, validation, error handling
- Testing: pytest, fixtures, mocking, integration with Testcontainers
- Security: input validation, SQL injection, secrets, dependency audit
- Observability:
structlog/ standardlogging, OpenTelemetry, health endpoints - Toolchain:
pyproject.toml,uv, type checking withmypy/pyright
Skill files
| File | Contents |
|---|---|
| architecture.md | Project structure, layers, dependency rules, config |
| patterns.md | Service layer, repository, dependency injection, error handling |
| testing.md | pytest setup, fixtures, mocking, Testcontainers, API testing |
| security.md | Input validation, SQL injection, secrets, subprocess safety |
| observability.md | Structured logging, OpenTelemetry, health checks |
| reference.md | Toolchain, pyproject.toml, common commands |
What ships with it
6 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.
- 1mo ago First seen · 66 lines · 76 tokens per session scan A 6fc717125cff
python-core is a skill published in the GitHub repository adonai-labs/agent-runway (2 stars, last pushed 22d ago), licensed MIT. It adds 76 tokens to every session and 650 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 2026-09-03.
Other skills, from other repositories
fastapi-templates
Create production-ready FastAPI projects with async patterns, dependency injection, and comprehensive error handling. Use when building new FastAPI applications or setting up backend API projects.
python-services
Python patterns for CLI tools, async parallelism, and backend services. Use when building CLI apps, async/parallel Python, FastAPI services, background jobs, or configuring Python project tooling (uv, ruff, ty).
plugin-system
Generic plugin system for Python applications. Auto-discovery, validation, fault tolerance. Zero dependencies (Python stdlib only).
fastapi-async-microservices
Design and develop production-grade asynchronous microservices using FastAPI, Python 3.12+, Pydantic v2 Settings and Schemas, SQLAlchemy 2.0 async sessions, dependency injection, lifespan state management, structured JSON logging, and connection pooling. Trigger when building async Python APIs, microservices, or…
django
Expert Django assistance covering ORM, models, class-based views, admin interface, migrations, and Django REST Framework. Use when developing robust, scalable Python web applications and REST APIs.
fastapi
Expert FastAPI assistance covering Pydantic models, async endpoints, dependency injection, and OpenAPI generation. Use when developing high-performance Python REST APIs and microservices.