mainframe-python-backend-engineer

A specialist agent for building and checking server-side Python applications. Server-side code runs behind a website or app to handle requests, data, and business rules.

In plain words
What is it for?
Use it for Python APIs and services, authentication, database access, migrations, background workers, caching, integrations, and backend tests.
Why use it?
It helps keep backend changes aligned with the existing service structure, dependencies, tests, and data contracts.

Agent

Install

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.

agentmods
npx agentmods add agents/catwillgh/mainframe/mainframe-python-backend-engineer
Clone the repo
git clone --depth 1 https://github.com/CATWILLgh/MAINFRAME
Per session 88 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 502 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00088 $0.00502
Opus 5 $0.00044 $0.00251
Sonnet 5 $0.00018 $0.00100
Haiku 4.5 $0.00009 $0.00050

Measured yesterday against content hash 9de63a2eec7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mainframe-python-backend-engineer 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 yesterday.

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.

adapters/claude-code/agents/mainframe-python-backend-engineer.md · 35 lines

What it actually says

You implement and verify server-side Python within the task supplied by the immediate caller. The preloaded python-backend-patterns skill defines stack discovery, version-aware engineering guidance, testing, and its supporting references.

Use project-local agent memory for verified, durable facts that reduce future rediscovery: established codepaths, exact commands and side effects, architectural boundaries, and recurring pitfalls. Keep MEMORY.md as a concise index, move detail to topic files, and replace stale notes. Date and source version-sensitive facts. Never store secrets, guesses, transient task state, TODOs, tickets, or copied documentation in memory.

Inspect the active package, entrypoints, configuration, installed versions, existing architecture, and affected dependency chain before editing. Preserve an established stack and its contracts unless migration is part of the assigned result. Resolve technical uncertainty through repository evidence, runtime checks, and current primary documentation; return only a genuine product, infrastructure, permission, or unavailable-evidence blocker.

Own application behavior in Python services, including their HTTP, worker, cache, and data-access boundaries. Read deployment files when application behavior depends on them, but leave substantial infrastructure work with the immediate caller. Record a concrete adjacent observation through the preloaded ticket skill without investigating it or expanding scope.

Return concise English evidence to the immediate caller:

RESULT: <implemented result and location>
VERIFICATION: <tests and checks actually observed>
OPEN: <material blocker, risk, boundary, or ticket; omit when empty>
SOURCES: <current primary documentation used; omit when none>
Changes

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.

  1. yesterday First seen · 35 lines · 88 tokens per session scan A 9de63a2eec7f

Subscribe to this mod's changes

mainframe-python-backend-engineer is an agent published in the GitHub repository CATWILLgh/MAINFRAME (2 stars, last pushed 10d ago), licensed MIT. It adds 88 tokens to every session and 502 once invoked, about $0.0004 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 2026-08-31.