TokenSaver: Instructions file for GitHub Copilot

.github/copilot-instructions.md

TokenSaver copilot-instructions.md is an instructions file for GitHub Copilot from Byggarepop/TokenSaver. It costs 2,108 tokens per session, scanned A, original, MIT.

Instructions for using TokenSaver, a tool that reduces the amount of source code included as context for an AI coding assistant. It describes supported file types and when to use the tool instead of targeted search and reading.

In plain words
What is it for?
Use it when working in Visual Studio 2026 with supported C#, Razor, JavaScript, TypeScript, Python, HTML, CSS, SCSS, or LESS files, following the stated guidance for source inspection.
Why use it?
It helps the assistant inspect unfamiliar codebases with less unnecessary text while preserving useful structure. It also prevents attempts to use the tool on file types or situations it does not support.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot instructions file.

This is Byggarepop/TokenSaver's own configuration. It tells GitHub Copilot how to work on TokenSaver 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 TokenSaver configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Byggarepop/TokenSaver. 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/Byggarepop/TokenSaver/main/.github/copilot-instructions.md
Clone the repo
git clone --depth 1 https://github.com/Byggarepop/TokenSaver

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 TokenSaver copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/byggarepop/tokensaver/copilot-instructions.svg)](https://agentmods.dev/instructions/byggarepop/tokensaver/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/byggarepop/tokensaver/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/byggarepop/tokensaver/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,108 This file is loaded in full into every session.
When invoked 2,108 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 $0.02108 $0.02108
Opus 5 $0.01054 $0.01054
Sonnet 5 $0.00422 $0.00422
Haiku 4.5 $0.00211 $0.00211

Measured 8d ago against content hash 030ec6b3fbf0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

TokenSaver 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 8d 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 · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot Instructions

Token-efficient source context via the tokensaver MCP server

This workspace has the tokensaver MCP server registered. It gives the model a cheap structural warm start in an unfamiliar codebase and then gets out of the way. It exposes three tools. Prefer them for the cases below; for everything else, your own Grep plus a narrow Read (the relevant lines only) is the leanest path — don't reach for a tool when a targeted read will do.

Visual Studio 2026 — use Copilot Chat. MCP tools fire in both Ask and Agent mode. Open the Copilot Chat panel and ask your question there; inline completions do not invoke MCP tools.

Supported file types (via MinifyFile)

Format Extensions Method
C# .cs, .razor.cs Roslyn syntax-tree minify
Razor .razor Markup (HTML) + @code (Roslyn), combined
JavaScript .js, .mjs, .cjs, .jsx Lexical strip + collapse
TypeScript .ts, .tsx, .mts, .cts Lexical strip + collapse
Python .py, .pyi # strip, indent preserved
HTML .html, .htm <!-- --> strip, whitespace collapse
CSS / SCSS / LESS .css, .scss, .less /* */ strip, whitespace collapse
JSON / JSONC .json, .jsonc Whitespace collapse + comment strip
YAML .yaml, .yml # strip, indent preserved
XML / project files .xml, .csproj, .props, .targets, .config, .resx <!-- --> strip, blank-run collapse
C .c, .h // + /* */ strip, whitespace collapse, #directives preserved
C++ .cpp, .cc, .cxx, .hpp, .hh, .hxx, .inl same as C
X++ .xpp // + /* */ strip, whitespace collapse, #macro directives preserved
VB.NET .vb Roslyn comment strip (' and REM), blank-run collapse

Tool selection rules — follow these by default, no need to ask

  1. Orient in a C#/VB file — "what's in this file?", "where would I add X?", or before editing any file ≥50 lines → call OutlineCSharpFile. Returns every type and member as a signature, NO bodies (typical 70-95% reduction), each tagged with its source line range (// L31-44). To then read a body, Read that exact range (offset+limit) — do not re-read the whole file. C#/VB only.

Read the full file on GitHub · 150 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. 8d ago First seen · 150 lines · 2,108 tokens per session scan A 030ec6b3fbf0

Subscribe to this mod's changes

TokenSaver copilot-instructions.md is an instructions file published in the GitHub repository Byggarepop/TokenSaver (4 stars, last pushed 1mo ago), licensed MIT. It adds 2,108 tokens to every session, about $0.0105 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.

Related

Other instructions, from other repositories

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

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 · 5,153 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

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

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

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