Borrowing it
Nothing to install: this file belongs to kpeacocke/souschef. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kpeacocke/souschef/main/.github/copilot-instructions.mdgit clone --depth 1 https://github.com/kpeacocke/souschefWrote 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/instructions/kpeacocke/souschef/copilot-instructions)<a href="https://agentmods.dev/instructions/kpeacocke/souschef/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/kpeacocke/souschef/copilot-instructions/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/instructions/kpeacocke/souschef/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/kpeacocke/souschef/copilot-instructions.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 | $0.05853 | $0.05853 |
| Opus 5.5 | $0.02341 | $0.02341 |
| Sonnet 5.5 | $0.01171 | $0.01171 |
| Haiku 4.5 | $0.00585 | $0.00585 |
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 1mo 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 — 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
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.
- 1mo ago First seen · 558 lines · 5,853 tokens per session scan A 595694be693e
souschef copilot-instructions.md is an instructions file published in the GitHub repository kpeacocke/souschef (6 stars, last pushed 3d ago), licensed MIT. It adds 5,853 tokens to every session, about $0.0234 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.