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 WrongStack/WrongStack --skill python-backendgit clone --depth 1 https://github.com/WrongStack/WrongStackWrote 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/wrongstack/wrongstack/python-backend)<a href="https://agentmods.dev/skills/wrongstack/wrongstack/python-backend"><img src="https://agentmods.dev/badge/skills/wrongstack/wrongstack/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/wrongstack/wrongstack/python-backend"><img src="https://agentmods.dev/badge/skills/wrongstack/wrongstack/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 | $0.00042 | $0.00610 |
| Opus 5.5 | $0.00017 | $0.00244 |
| Sonnet 5.5 | $0.00008 | $0.00122 |
| Haiku 4.5 | $0.00004 | $0.00061 |
Grade A, and why
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 5d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python Backend
Selection card
- Task: Implement Python APIs and typed validation.
- Start: Locate the endpoint, schema, authentication boundary and caller.
- Finish: apply the acceptance checks below; report observed results and unresolved constraints.
Overview
Build and upgrade Python services with explicit environments, validation, async boundaries and resource cleanup.
Checked 2026-10-09: Python 3.15.0, FastAPI 0.143.0, Django 6.1.2 and uv 0.12.24. Verify framework/native-wheel/Python support before combining them; latest Python can lead package support.
Rules
- Inspect pyproject/lockfile, interpreter, environment and deployment entrypoint.
- Validate incoming data and model output contracts; static annotations do not validate JSON.
- Keep blocking I/O and CPU work off async request loops; cancellation must propagate to owned work.
- Scope database sessions/clients and transactions to the operation; cleanup must run on failure.
- Keep secrets/config and public serialization explicit; object authorization remains at the data operation.
- Do not replace the project package manager or migrate frameworks as an incidental feature change.
Workflow
- Trace the request/job path and current framework/environment conventions.
- Verify latest stable targets and support requirements; read migration notes.
- Implement the feature with typed/validated boundaries and explicit resource ownership.
- Test input/errors, database rollback, cancellation and application startup.
- Run configured formatting/lint/type/tests and the real service entrypoint.
Before returning
Interpreter/environment and compatibility clear; validation/async/resource semantics tested; framework/service checks reported.
Sources
Versioned facts checked 2026-10-09; refresh authoritative sources before new installs/upgrades. Python releases, FastAPI, Django.
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.
- 5d ago Changed ac48532ed0ac
- 6d ago First seen · 59 lines · 42 tokens per session scan A bd13c6f167ae
python-backend is a skill published in the GitHub repository WrongStack/WrongStack (376 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 610 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 2026-10-10.
Other skills, from other repositories
pydantic-models-py
Create Pydantic models following the multi-model pattern for clean API contracts.
performant-python
Strategies for high-performance Python systems (FastAPI, Asyncio, UVloop, Memory Optimization).
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.
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.
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.
build-fullstack-backend
ONLY for writing backend or fullstack code BY HAND. NOT needed on the normal path — createartifact(fullstack-stateless-app or fullstack-stateful-app) followed by generateartifact writes the backend, verifies it by importing it and launches it. Recall this when editing an existing fullstack artifact, or when…