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/duthaho/copilot-instructions/meta-instructionsgit clone --depth 1 https://github.com/duthaho/copilot-instructionsWrote 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/duthaho/copilot-instructions/meta-instructions)<a href="https://agentmods.dev/instructions/duthaho/copilot-instructions/meta-instructions"><img src="https://agentmods.dev/badge/instructions/duthaho/copilot-instructions/meta-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 | $0.00674 | $0.00674 |
| Opus 5 | $0.00337 | $0.00337 |
| Sonnet 5 | $0.00135 | $0.00135 |
| Haiku 4.5 | $0.00067 | $0.00067 |
Grade A, and why
copilot-instructions meta-instructions.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.
How it starts
The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meta-Instructions for Writing Instruction Files
Overview
This meta-instruction file defines the standard format, structure, and best practices for creating instruction files in .github/instructions/.
File Naming Convention
All instruction files must follow this pattern:
<topic-name>.instructions.md
Examples:
domain-driven-design.instructions.mdcoding-style-python.instructions.mdunit-and-integration-tests.instructions.md
Required Structure
Every instruction file must include:
1. Frontmatter
YAML frontmatter with metadata:
---
description: "Brief description of what this instruction covers"
applyTo: "**/*.py" # Optional: file pattern
---
2. Title and Overview
# [Topic] Instructions
## Overview
A clear, concise description of what this instruction file enforces.
3. Main Content Sections
Organize content logically with clear headings:
- Principles/Rules
- Examples (Good vs Bad)
- Implementation details
- Best practices
4. Validation Checklist
End with a checklist for easy reference:
## Validation Checklist
- [ ] Item 1
- [ ] Item 2
- [ ] Item 3
Content Guidelines
Language
- Write in English only
- Use imperative mood for rules ("Use X" not "You should use X")
- Be specific and actionable
Code Examples
- Include both ✅ Good and ❌ Bad examples
- Add comments explaining why
- Use realistic examples from the domain
Structure
- Use hierarchical headings (##, ###, ####)
- Keep sections focused and cohesive
- Use bullet points for lists
- Use code blocks with language tags
Example Template
---
description: "Brief description"
applyTo: "**/*.py"
---
# Topic Instructions
## Overview
Clear explanation of what this instruction enforces.
## Section 1: Core Principles
### Rule 1
Explanation of the rule.
✅ **Good:**
```python
# Good example with explanation
def good_example():
pass
```
❌ Bad:
# Bad example with explanation
def bad_example():
pass
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 · 169 lines · 674 tokens per session scan A 5e869d2d9ab9
copilot-instructions meta-instructions.instructions.md is an instructions file published in the GitHub repository duthaho/copilot-instructions (7 stars, last pushed 10mo ago), licensed MIT. It adds 674 tokens to every session, about $0.0034 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.
Other instructions, from other repositories
copilot-instructions copilot-instructions.md
Instructions for SebastienDegodez/copilot-instructions, covering copilot instructions, language policy, development code generation and workflow implementation.
fastify-boilerplate AGENTS.md
AGENTS.md instructions for marcoturi/fastify-boilerplate, covering agents.md, project overview, quick reference, architecture and layer boundaries (critical).
squad copilot-instructions.md
Copilot instructions for bradygaster/squad, covering copilot coding agent — squad instructions, ⚠️ identity lock — read this first, 🚦 route before you act — generic copilot sessions, adversarial input handling and team context.
vscode-unify-chat-provider AGENTS.md
Instructions for smallmain/vscode-unify-chat-provider, a project described as: Integrate multiple LLM API providers into VS Code's GitHub Copilot Chat using the Language Model API. One-click use of your Claude Code, Gemini CLI, Antigravity, Github Copilot, OpenAI Codex (ChatGPT Plus/Pro), xAI Grok (SuperGrok / X…
apex-accelerator agent-skills.instructions.md
Guidelines for creating high-quality Agent Skills for GitHub Copilot.
apex-accelerator vendor-prompting.instructions.md
Vendor prompting best-practice rules for Anthropic Claude and OpenAI GPT-5.6-Terra agents and prompts. Each rule cites a rule ID in the vendor-prompting skill rules.json registry. Validator: npm run lint:vendor-prompting.