agentmods.dev

mcpkernel python-conventions.instructions.md

A set of coding rules for Python changes in MCPKernel, covering asynchronous code, type annotations, logging, errors and import order. Asynchronous code lets programs handle waiting for files or network operations without blocking other work.

In plain words
What is it for?
Use it when adding or changing Python functions to choose async patterns, add required type hints, use structlog, define and catch specific exceptions, add retries and organize imports.
Why use it?
It keeps new code consistent with the project and helps avoid blocked I/O, unclear types, inconsistent logs and overly broad error handling.

Instructions file for GitHub Copilot

2 +1 2mo ago A scan 267 tokens original Apache-2.0
View the source file piyushptiwari1/mcpkernel
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 instructions/piyushptiwari1/mcpkernel/python-conventions
Clone the repo
git clone --depth 1 https://github.com/piyushptiwari1/mcpkernel

Made for: GitHub Copilot.

Per session 267 This file is loaded in full into every session.
When invoked 267 The same file — it is already loaded in full.
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 $0.00267 $0.00267
Opus 5 $0.00133 $0.00133
Sonnet 5 $0.00053 $0.00053
Haiku 4.5 $0.00027 $0.00027

Measured 2d ago against content hash 4c8a49418b4f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcpkernel python-conventions.instructions.md 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 2d 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.

.github/instructions/python-conventions.instructions.md · 31 lines

What it actually says

MCPKernel Python Conventions

Async-First

  • All I/O-bound functions must be async def
  • Use asyncio.gather() for concurrent operations
  • Never use blocking I/O in async functions (use aiofiles, aiohttp, etc.)

Type Hints

  • All public functions and methods must have type annotations
  • Use from __future__ import annotations for forward references
  • Use Optional[X] not X | None (Python 3.10 compatibility)

Logging

  • Use structlog — NOT stdlib logging
  • Get logger: logger = structlog.get_logger(__name__)
  • Include context: logger.info("action_description", key=value)

Error Handling

  • Define custom exceptions per package in exceptions.py
  • Catch specific exceptions, not broad Exception
  • For async retry: use exponential backoff with jitter

Imports

  • stdlib → third-party → local (separated by blank lines)
  • Use absolute imports: from mcpkernel.policy.engine import PolicyEngine
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. 2d ago First seen · 31 lines · 267 tokens per session scan A 4c8a49418b4f

Subscribe to this mod's changes

mcpkernel python-conventions.instructions.md is an instructions file published in the GitHub repository piyushptiwari1/mcpkernel (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 267 tokens to every session, about $0.0013 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.

Data and AISecurityWriting and docsa2aagent-securityai-agentai-securityaudit-loggingdeterministic-execution
Related

Other instructions, from other repositories

AgentHound CLAUDE.md

Instructions for adithyan-ak/AgentHound, covering agenthound maintainer contract, required checks, hard boundaries, core invariants and module registration.

adithyan-ak/AgentHound · 1,136 tokens

arcjet-js AGENTS.md

Instructions for arcjet/arcjet-js, covering agent guidance, examples live in arcjet/examples and integration work: review before a pr.

arcjet/arcjet-js · 351 tokens

prismor CLAUDE.md

Instructions for PrismorSec/prismor, covering prismor security — claude.md, prismor runtime protection, cloaking (secret prevention) and working in this repo.

PrismorSec/prismor · 359 tokens

AgentHound copilot-instructions.md

Instructions for adithyan-ak/AgentHound: Keep generated examples local to the fixture project.

adithyan-ak/AgentHound · 15 tokens

ave CLAUDE.md

Instructions for aveproject/ave, covering claude.md — aveproject/ave, project, the critical distinction — read this twice, record schema v1.1.0 and adding a record.

aveproject/ave · 1,671 tokens

Agent-Security-Regression-Harness AGENTS.md

Instructions for OWASP/Agent-Security-Regression-Harness, covering ai agent guide: owasp agent security regression harness, project overview, architecture, contribution workflow and what needs doing.

OWASP/Agent-Security-Regression-Harness · 927 tokens