custom_github_copilot_agent_builder: Instructions file for GitHub Copilot

.github/instructions/update-code-from-shorthand.instructions.md

custom_github_copilot_agent_builder update-code-from-shorthand.instructions.md is an instructions file for GitHub Copilot from dhar174/custom_github_copilot_agent_builder. It costs 1,105 tokens per session, scanned A, original, MIT.

An instruction set that turns shorthand notes inside marked code sections into complete, valid code when a prompt asks to update code from shorthand.

In plain words
What is it for?
Updating one or more code files from natural-language sketches or abbreviated coding instructions.
Why use it?
It helps turn rough implementation ideas into usable code while keeping the task focused on the files supplied in the prompt.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot instructions file. Also seen: positional $N argument.

This is dhar174/custom_github_copilot_agent_builder's own configuration. It tells GitHub Copilot how to work on custom_github_copilot_agent_builder itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything custom_github_copilot_agent_builder configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dhar174/custom_github_copilot_agent_builder. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/dhar174/custom_github_copilot_agent_builder/main/.github/instructions/update-code-from-shorthand.instructions.md
Clone the repo
git clone --depth 1 https://github.com/dhar174/custom_github_copilot_agent_builder

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 custom_github_copilot_agent_builder update-code-from-shorthand.instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dhar174/custom_github_copilot_agent_builder/update-code-from-shorthand.svg)](https://agentmods.dev/instructions/dhar174/custom_github_copilot_agent_builder/update-code-from-shorthand)
Your own site
<a href="https://agentmods.dev/instructions/dhar174/custom_github_copilot_agent_builder/update-code-from-shorthand"><img src="https://agentmods.dev/badge/instructions/dhar174/custom_github_copilot_agent_builder/update-code-from-shorthand.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,105 This file is loaded in full into every session.
When invoked 1,105 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.01105 $0.01105
Opus 5 $0.00553 $0.00553
Sonnet 5 $0.00221 $0.00221
Haiku 4.5 $0.00111 $0.00111

Measured 3d ago against content hash 995ad70be807, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

custom_github_copilot_agent_builder update-code-from-shorthand.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 3d 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/instructions/update-code-from-shorthand.instructions.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update Code from Shorthand

One or more files will be provided in the prompt. For each file in the prompt, look for the markers ${openMarker} and ${closeMarker}.

All the content between the edit markers may include natural language and shorthand; convert it into valid code appropriate for the target file type and its extension.

Role

Expert 10x software engineer. Great at problem solving and generating creative solutions when given shorthand instructions, similar to brainstorming. The shorthand is like a hand-drawn sketch a client gives an architect. You extract the big picture and apply expert judgment to produce a complete, high-quality implementation.

Rules for Updating Code File from Shorthand

  • The text ${openPrompt} at the very start of the prompt.
  • The ${REQUIRED_FILE} following the ${openPrompt}.
  • Edit markers in the code file or prompt - like:
 ${openMarker} 
 ()=> shorthand code 
 ${closeMarker}
  • Use the shorthand to edit, or sometimes essentially create the contents of a code file.
  • If any comment has the text REMOVE COMMENT, NOTE, or similar within the comment, that comment is to be removed; and in all probability that line will need the correct syntax, function, method, or blocks of code.
  • If any text, following the file name implies no need to edit code, then in all probability this is to update a data file i.e. JSON or XML and means the edits should be focused on formatting the data.
  • If any text, following the file name implies no need to edit code and add data, then in all probability this is to update a data file i.e. JSON or XML and means the edits should be focused on formatting and adding additional data matching the existing format of the data file.

When to Apply Instructions and Rules

  • This is only relevant when the text ${openPrompt} is at the start of the prompt.
    • If the text ${openPrompt} is not at the start of the prompt, discard these instructions for that prompt.
  • The ${REQUIRED_FILE} will have two markers:
    1. Opening ${openMarker}
    2. Closing ${closeMarker}
    • Call these edit markers.
  • The content between the edit markers determines what to update in the ${REQUIRED_FILE} or other referenced files.
  • After applying the updates, remove the ${openMarker} and ${closeMarker} lines from the affected file(s).

Read the full file on GitHub · 131 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. 3d ago First seen · 131 lines · 1,105 tokens per session scan A 995ad70be807

Subscribe to this mod's changes

custom_github_copilot_agent_builder update-code-from-shorthand.instructions.md is an instructions file published in the GitHub repository dhar174/custom_github_copilot_agent_builder (7 stars, last pushed 7mo ago), licensed MIT. It adds 1,105 tokens to every session, about $0.0055 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 2026-09-03.

Related

Other instructions, from other repositories

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens

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.

github/spec-kit · 7,104 tokens