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 CATWILLgh/MAINFRAME --skill mainframe-python-backendgit clone --depth 1 https://github.com/CATWILLgh/MAINFRAMEWrote 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/catwillgh/mainframe/mainframe-python-backend)<a href="https://agentmods.dev/skills/catwillgh/mainframe/mainframe-python-backend"><img src="https://agentmods.dev/badge/skills/catwillgh/mainframe/mainframe-python-backend/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/catwillgh/mainframe/mainframe-python-backend"><img src="https://agentmods.dev/badge/skills/catwillgh/mainframe/mainframe-python-backend.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 | $0.00040 | $0.01071 |
| Opus 5.5 | $0.00016 | $0.00428 |
| Sonnet 5.5 | $0.00008 | $0.00214 |
| Haiku 4.5 | $0.00004 | $0.00107 |
Grade A, and why
mainframe-python-backend 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 15d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python backend engineering
Apply this method whenever the active work matches the description, whether you are the primary implementer, a delegated engineer, or a reviewer. Follow the scope and authority supplied through the current execution path; this skill does not expand either.
For behavior changes, load mainframe-testing for the shared TDD and local/CI boundary, then use this skill's testing reference for stack-specific evidence.
Establish the active server boundary
Identify the package that owns the affected behavior. If ownership or runtime wiring is unclear, use the bounded recon script or manual reconnaissance for that package. Reuse current inspected evidence; declared dependencies and filenames do not prove the active runtime path.
Trace the requested behavior through its real entrypoint, runtime validation, business rules, data or external boundary, side effects, callers, and observable output. Inspect the effective project instructions and use only infrastructure authorized by effective instructions or the immediate caller.
Several frameworks, validators, ORMs, workers, or test runners may legitimately coexist. Resolve ownership from imports, registration, configuration, entrypoints, runtime wiring, and affected files. Surface a decision only when evidence cannot resolve a product, business, data, infrastructure, permission, or authority choice with material consequences.
Preserve the established system
Preserve the active interpreter support, packaging tool, framework, WSGI or ASGI boundary, sync or async model, architecture, validation, authentication, persistence, contracts, observability, and testing conventions unless changing one is part of the assigned result. Do not introduce a competing library, broad typing migration, new service, or infrastructure dependency for convenience.
For a genuinely new isolated component, derive the stack from its requirements, supported runtime, operational environment, and project decisions. Do not impose a universal framework, ORM, database, queue, test runner, or deployment model.
What ships with it
13 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.
- references/background-and-realtime.md 1.4 KB
- references/concurrency-and-tenancy.md 1.5 KB
- references/contracts-and-security.md 1.6 KB
- references/data-and-migrations.md 1.7 KB
- references/django.md 1.5 KB
- references/fastapi.md 1.4 KB
- references/files-cache-and-integrations.md 1.3 KB
- references/flask.md 1.2 KB
- references/observability-and-lifecycle.md 1.4 KB
- references/recon.md 1.4 KB
- references/runtime-and-packaging.md 1.8 KB
- references/testing.md 1.9 KB
- scripts/recon.py 12 KB runs code
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.
- 15d ago Changed · +2 lines · +5 tokens per session a24d6806caa4
- 20d ago Changed · -41 tokens per session 7e7917b06478
- 1mo ago Changed · -35 lines · -19 tokens per session 48e3bf597f6f
- 1mo ago First seen · 86 lines · 95 tokens per session scan A 3835c4316a4c
mainframe-python-backend is a skill published in the GitHub repository CATWILLgh/MAINFRAME (2 stars, last pushed 9d ago), licensed MIT. It adds 40 tokens to every session and 1,071 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 2026-08-31.
Other skills, from other repositories
python-development
Professional Python development skill covering modern Python 3.10+, FastAPI, Django, Flask, async programming, data processing, and best practices. Use this skill when developing Python web applications, building FastAPI/Django projects, implementing async programming, or need guidance on Python architecture design…
fastapi
FastAPI application design and implementation conventions. Use this skill when building, updating, or reviewing FastAPI services, routers, dependencies, request/response schemas, streaming endpoints, or API tests. Trigger on FastAPI-specific work such as path operation design, dependency injection, response models…
cdrf-expert
Expert guidance for Django REST Framework class-based views using Classy DRF (https://www.cdrf.co). Use when selecting or debugging APIView, GenericAPIView, concrete generic views, mixin combinations, or ViewSet/GenericViewSet/ModelViewSet behavior; tracing method resolution order (MRO); understanding which method to…
fastapi
You are working on a FastAPI project. Apply these conventions.
django
You are working on a Django project. Apply these conventions.
fastapi-patterns
FastAPI patterns for async APIs, dependency injection, Pydantic request and response models, OpenAPI docs, tests, security, and production readiness.