coding-mcp copilot-instructions.md

coding-mcp copilot-instructions.md is an instructions file for GitHub Copilot from kieutrongthien/coding-mcp. It costs 320 tokens per session, scanned A, original, MIT.

Repository instructions for building and maintaining an MCP server, including architecture, safety, response formats, and testing rules. MCP is a standard way for an AI agent to use tools and services.

In plain words
What is it for?
For implementing or changing an MCP server while preserving its project structure, preventing path traversal and unsafe commands, keeping schemas aligned, and running type checks and tests.
Why use it?
They give coding agents explicit rules for safe command execution, controlled file access, consistent interfaces, and required checks before completion.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot instructions file.

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/kieutrongthien/coding-mcp/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/kieutrongthien/coding-mcp

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 coding-mcp copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kieutrongthien/coding-mcp/copilot-instructions.svg)](https://agentmods.dev/instructions/kieutrongthien/coding-mcp/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/kieutrongthien/coding-mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/kieutrongthien/coding-mcp/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 320 This file is loaded in full into every session.
When invoked 320 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 5.1 $0.00320 $0.00320
Opus 5 $0.00160 $0.00160
Sonnet 5 $0.00064 $0.00064
Haiku 4.5 $0.00032 $0.00032

Measured 5d ago against content hash 048a0c2bd8c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

coding-mcp 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 · 48 lines

What it actually says

Copilot Instructions for coding-mcp

These instructions apply to all coding agents working in this repository.

Mission

Build and maintain a production-grade MCP server for multi-project coding workflows with strong safety controls.

Architecture Rules

  • Preserve modular boundaries: config, core, services, and mcp layers.
  • Reuse shared services via bootstrap container; do not bypass service abstractions in tool handlers.
  • Keep STDIO and HTTP transports behaviorally consistent.

Safety Rules (Mandatory)

  • Never allow path traversal outside project roots.
  • Keep destructive operations guarded by explicit confirmation flags.
  • Keep command execution allowlist-based; do not introduce shell concatenation.
  • Prefer spawn(command, args, { shell: false }) patterns.
  • Maintain output/file size limits and timeout controls.

MCP Contract Rules

  • Keep zod schemas in sync with tool/resource/prompt handlers.
  • Keep response envelopes consistent (ok, operation, data, warnings, errors).
  • Return structured failures with clear error codes and details.

Testing Rules

Before proposing completion for code changes:

  1. Run npm run typecheck
  2. Run npm test
  3. Add or update tests for changed behavior

Documentation Rules

  • Update README and env examples when changing CLI/config behavior.
  • Update GitHub templates/workflows when project process changes.

Preferred Workflow

  1. Read affected schemas and service interfaces first.
  2. Implement minimal changes preserving existing API contracts.
  3. Validate with typecheck/tests.
  4. Summarize changes with impacted files and behavior deltas.
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 · 48 lines · 320 tokens per session scan A 048a0c2bd8c1

Subscribe to this mod's changes

coding-mcp copilot-instructions.md is an instructions file published in the GitHub repository kieutrongthien/coding-mcp (2 stars, last pushed 5mo ago), licensed MIT. It adds 320 tokens to every session, about $0.0016 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.