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/deeprave/mcp-guide/copilot-instructionsgit clone --depth 1 https://github.com/deeprave/mcp-guideWhat 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 | $0.01048 | $0.01048 |
| Opus 5 | $0.00524 | $0.00524 |
| Sonnet 5 | $0.00210 | $0.00210 |
| Haiku 4.5 | $0.00105 | $0.00105 |
Grade A, and why
mcp-guide 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 yesterday.
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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Copilot Instructions for Code Reviews
Code Review Formatting for AI Agents
When providing code reviews or feedback in this repository, format your responses to be AI-agent friendly rather than human-web-browser friendly.
Principles
- Plain Text First: Use plain text and markdown instead of HTML, CSS, or heavily formatted web content
- Copy-Paste Ready: Format entire reviews so they can be copied and pasted directly into AI agents without reformatting
- Clear Structure: Use markdown headings, lists, and code blocks for organization
- Minimal Formatting: Avoid complex tables, purely decorative elements, or special characters that break when copied as plain text
Format Guidelines
DO: Use Simple Markdown Code Blocks
# Issue: Variable name is unclear
# Fix:
def process_user_data(user_id: str) -> dict:
return fetch_user(user_id)
DO: Provide File Paths and Line References
File: src/handlers.py
Lines: 45-52
Issue: Missing error handling
# Current code:
result = api.call()
# Suggested fix:
try:
result = api.call()
except APIError as e:
logger.error(f"API call failed: {e}")
raise
DO: Use Plain Lists for Multiple Issues
Issues Found:
- src/utils.py:23 - Missing type hint for
process_datafunction - src/models.py:67 - Potential null pointer in
get_user_name() - tests/test_api.py:12 - Test should verify error message content
DON'T: Use HTML/CSS Formatting
<!-- Avoid this -->
<div style="color: red; font-weight: bold;">
<p>Issue found in line 45</p>
</div>
DON'T: Use Complex Tables or Formatting
Avoid:
- Decorative symbols that may not copy correctly (assume utf-8)
- Complex nested tables
- Inline HTML styling
- Rich text formatting that doesn't translate to plain text
- Special Unicode characters that break in plain text contexts
- Bold/italic markdown in excess (use sparingly only for headers)
Review Comment Structure
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.
- yesterday First seen · 177 lines · 1,048 tokens per session scan A ab4e2a3e8fa0
mcp-guide copilot-instructions.md is an instructions file published in the GitHub repository deeprave/mcp-guide (0 stars, last pushed 4d ago), licensed MIT. It adds 1,048 tokens to every session, about $0.0052 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
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.