vscode-copilot-sync copilot-instructions.md

Repository instructions for PowerShell scripts that copy GitHub Copilot resources from the awesome-copilot repository into user and project locations. PowerShell is a Windows command-line scripting language.

In plain words
What is it for?
Use them when configuring the sync, installing resources for all VS Code sessions, or adding agents, instructions, hooks, workflows, and skills to a specific repository.
Why use it?
They clarify which scripts to run, where resources belong, and how errors and logs should be handled, reducing setup mistakes.

Instructions file for GitHub Copilot

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/ctout/vscode-copilot-sync/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/CTOUT/vscode-copilot-sync

Made for: GitHub Copilot.

Per session 1,008 This file is loaded in full into every session.
When invoked 1,008 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 $0.01008 $0.01008
Opus 5 $0.00504 $0.00504
Sonnet 5 $0.00202 $0.00202
Haiku 4.5 $0.00101 $0.00101

Measured 2d ago against content hash 2fb11b28a67f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vscode-copilot-sync 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 2d 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 · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot Instructions

This repository contains PowerShell scripts that sync Copilot resources from github/awesome-copilot to a local machine and distribute them to the right VS Code/Copilot locations.

Script Workflow

Scripts are designed to be run in this order:

configure.ps1                      # Main entry point (chains all steps)
scripts/sync-awesome-copilot.ps1   # 1. Clone/pull github/awesome-copilot → ~/.awesome-copilot/
scripts/init-user.ps1              # 2. User-level resources → prompts\ and ~/.copilot/skills/
scripts/init-repo.ps1              # 3. Interactive per-repo setup → .github/

Resource scopes:

  • User-level (all VS Code sessions, no .github/ needed): Agents + Instructions → %APPDATA%\Code\User\prompts\; Skills → ~/.copilot/skills/
  • Per-repo (committed to .github/): Agents, Instructions, Hooks, Workflows, Skills

Key Conventions

Error Handling

All scripts use $ErrorActionPreference = 'Stop' so errors terminate rather than prompt. Use try/catch blocks for recoverable errors — do not rely on error preference for expected failure paths.

Logging

Use the Log / Write-Log function (not Write-Host directly):

Log "Message here"           # INFO (Cyan)
Log "Something wrong" 'WARN' # Yellow
Log "Done!" 'SUCCESS'        # Green
Log "Failed" 'ERROR'         # Red

Dry-Run Pattern

Every destructive operation must be guarded by $DryRun:

if ($DryRun) { Log "[DryRun] Would do X"; return 'would-copy' }
# actual operation here

Change Detection

Always use SHA256 hash comparison before copying — never overwrite blindly:

$srcHash = (Get-FileHash $Src -Algorithm SHA256).Hash
$dstHash = if (Test-Path $dest) { (Get-FileHash $dest -Algorithm SHA256).Hash } else { $null }
if ($srcHash -eq $dstHash) { return 'unchanged' }

Portable Paths

Always use $HOME, $env:APPDATA, and Join-Path — never hardcode user paths:

Read the full file on GitHub · 105 lines

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. 2d ago First seen · 105 lines · 1,008 tokens per session scan A 2fb11b28a67f

Subscribe to this mod's changes

vscode-copilot-sync copilot-instructions.md is an instructions file published in the GitHub repository CTOUT/vscode-copilot-sync (4 stars, last pushed 1mo ago), licensed MIT. It adds 1,008 tokens to every session, about $0.0050 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.