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 agentmods add instructions/decade-qiu/cookhero/copilot-instructionsgit clone --depth 1 https://github.com/Decade-qiu/CookHeroWrote 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/decade-qiu/cookhero/copilot-instructions)<a href="https://agentmods.dev/instructions/decade-qiu/cookhero/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/decade-qiu/cookhero/copilot-instructions.svg" alt="Measured on agentmods" 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 | $0.00364 | $0.00364 |
| Opus 5 | $0.00182 | $0.00182 |
| Sonnet 5 | $0.00073 | $0.00073 |
| Haiku 4.5 | $0.00036 | $0.00036 |
Grade A, and why
CookHero 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 4d 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.
What it actually says
Global Instructions
0. General Code Quality Requirements
- Clarity and Simplicity: Write clean, self-documenting code with meaningful names and consistent formatting. Prefer straightforward solutions; avoid unnecessary abstraction or complexity.
- Reliability and Correctness: Ensure code is robust and predictable. Handle errors gracefully, validate inputs, and include tests where appropriate.
- Maintainability and Modularity: Structure code to be easy to understand, modify, and extend. Minimize coupling between modules and keep related functionality cohesive.
- Consistency and Standards: Follow established project conventions and language best practices consistently. Avoid introducing special cases without strong justification.
1. Task Decomposition & Planning
- For complex or multi-step tasks, carefully analyze and plan before proceeding.
- Break down tasks into a prioritized to-do list of executable steps.
- Process each subtask sequentially by priority, ensuring logical progression and clarity.
2. Version Compatibility Policy
- No backward compatibility guarantee — Feel free to break old formats to prioritize new features and improvements.
- Allow destructive updates, prioritize code quality and architectural soundness over maintaining legacy support.
3. Git Operations
- Never automatically execute git commit after making code changes.
- Perform git operations (e.g., commit, push) only when explicitly instructed by the user.
Python Project Instructions
1. Python Environment Management
- Always activate the virtual environment in the project root before running or testing code.
- Activation command:
source .venv/bin/activate
Frontend Project Instructions
1. Frontend Build Process
- After modifying frontend code, always run the following command to compile and check for errors:
npm run build. - Ensure the build succeeds before proceeding with other operations to maintain code consistency and stability.
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.
- 4d ago First seen · 32 lines · 364 tokens per session scan A 651587cac364
CookHero copilot-instructions.md is an instructions file published in the GitHub repository Decade-qiu/CookHero (609 stars, last pushed 14d ago), licensed Apache-2.0. It adds 364 tokens to every session, about $0.0018 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 2026-08-30.
Other instructions, from other repositories
sage AGENTS.md
AGENTS.md instructions for MythicAgents/sage, covering sage codex session guide, start here, product contracts and runtime authority, durable artifact retention and sealed evaluation review discipline.
sage CLAUDE.md
Claude Code instructions for MythicAgents/sage, covering sage assistant compatibility guide, current system, required workflows, hard boundaries and testing.
deepagents AGENTS.md
AGENTS.md instructions for langchain-ai/deepagents, covering global development guidelines for the deep agents monorepo, corridor security analysis, development workflow, suppressing ruff rules and pr conventions.
opik copilot-instructions.md
Copilot instructions for comet-ml/opik, covering copilot code review instructions, project overview, 1. git workflow & branch management, branch naming convention and commit message standards.
openagent CLAUDE.md
Claude Code instructions for the-open-agent/openagent, covering claude.md, commands, architecture, backend (go / beego) and frontend (react).
langchain-aws AGENTS.md
AGENTS.md instructions for langchain-ai/langchain-aws, covering global development guidelines for the langchain monorepo, project architecture and context, langchain-aws structure, key components and langgraph-checkpoint-aws structure.