souschef copilot-instructions.md

souschef copilot-instructions.md is an instructions file for GitHub Copilot from kpeacocke/souschef. It costs 5,853 tokens per session, scanned A, original, MIT.

Project instructions for SousChef, an AI-powered server that converts Chef cookbooks into Ansible playbooks. They describe its architecture, specialised agents, testing practices, and code-quality rules.

In plain words
What is it for?
Use them when developing SousChef, invoking its specialised agents, maintaining its layered modules, writing tests, checking quality, or converting Chef configuration to Ansible.
Why use it?
They give coding agents the project context and working rules needed to make changes consistently.

Instructions file for GitHub Copilot

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/kpeacocke/souschef/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/kpeacocke/souschef

Made for: GitHub Copilot.

Wrote 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.

agentmods badge for souschef copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kpeacocke/souschef/copilot-instructions.svg)](https://agentmods.dev/instructions/kpeacocke/souschef/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/kpeacocke/souschef/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/kpeacocke/souschef/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 5,853 This file is loaded in full into every session.
When invoked 5,853 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 $0.05853 $0.05853
Opus 5 $0.02926 $0.02926
Sonnet 5 $0.01171 $0.01171
Haiku 4.5 $0.00585 $0.00585

Measured 5d ago against content hash 595694be693e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

souschef copilot-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 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.

.github/copilot-instructions.md · 558 lines

How it starts

The opening of the file, as written. The whole thing — 558 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SousChef Project - GitHub Copilot Instructions

Project Overview

SousChef is an AI-powered MCP (Model Context Protocol) server that assists with converting Chef cookbooks to Ansible playbooks.

Specialised Agents

For focused expertise on specific tasks, refer to AGENTS.md which defines specialised agents:

  • Test Coverage Guardian: Achieve 100% coverage with best-in-class testing
  • Quality Enforcer: Zero warnings from ruff, mypy, Pylance
  • Architecture Reviewer: Ensure code follows modular structure
  • TDD Coach: Guide test-driven development
  • Migration Specialist: Chef-to-Ansible conversion expertise
  • Documentation Maintainer: Keep docs accurate and current
  • Performance Optimiser: Profile and optimise bottlenecks

Invoke agents with: @AgentName [task description]

Project Architecture

Module Structure

The project follows a 7-layer modular architecture with strict dependency discipline:

souschef/
├── __init__.py          # Package initialization
├── server.py            # MCP server entry point (Layer 7)
├── cli.py               # Command-line interface (Layer 7)
├── ui/                  # Web interface (Layer 7)
├── orchestrators/       # Workflow coordination (Layer 6)
├── assessment.py        # Migration planning (Layer 6)
├── deployment.py        # AWX/Tower deployment (Layer 6)
├── api/                 # REST API endpoints (Layer 5)
├── integrations/        # External integrations (Layer 5)
│   └── github/          # GitHub integration
├── auth/                # Authentication & RBAC (Layer 4)
├── audit/               # Audit logging (Layer 4)
├── benchmarking/        # Performance profiling (Layer 4)
├── parsers/             # Input parsing (Layer 3)
│   ├── attributes.py    # Chef attribute parsing
│   ├── habitat.py       # Habitat plan parsing
│   ├── inspec.py        # InSpec profile parsing
│   ├── metadata.py      # Cookbook metadata parsing
│   ├── recipe.py        # Recipe parsing
│   ├── resource.py      # Custom resource parsing
│   └── template.py      # ERB template parsing
├── converters/          # Transformations (Layer 3)
│   ├── habitat.py       # Habitat to Docker
│   ├── playbook.py      # Recipe to playbook
│   └── resource.py      # Resource to task
├── generators/          # Output generation (Layer 3)
├── storage/             # Data persistence (Layer 2)
├── filesystem/          # File operations (Layer 2)
├── ir/                  # Intermediate representation (Layer 2)
└── core/                # Foundation utilities (Layer 1)
    ├── constants.py     # Shared constants
    ├── errors.py        # Custom exceptions
    ├── path_utils.py    # Path normalization
    ├── ruby_utils.py    # Ruby value parsing
    └── validation.py    # Validation helpers

Read the full file on GitHub · 558 lines

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. 5d ago First seen · 558 lines · 5,853 tokens per session scan A 595694be693e

Subscribe to this mod's changes

souschef copilot-instructions.md is an instructions file published in the GitHub repository kpeacocke/souschef (6 stars, last pushed 2d ago), licensed MIT. It adds 5,853 tokens to every session, about $0.0293 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.