copilot-self-improvement copilot-instructions.md

copilot-self-improvement copilot-instructions.md is an instructions file for GitHub Copilot from jfjordanfarr/copilot-self-improvement. It costs 1,628 tokens per session, scanned A, original, MIT.

Project instructions for GitHub Copilot Agent Mode in a VS Code project. They describe the project, require documentation-first work, and use a session-state file to retain decisions between conversations.

In plain words
What is it for?
Use them to guide Copilot's behavior, manage AI session state, and define how project instructions are matched to files.
Why use it?
They give Copilot consistent project context and a place to preserve progress when one conversation or context window ends.

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/jfjordanfarr/copilot-self-improvement/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/jfjordanfarr/copilot-self-improvement

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 copilot-self-improvement copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jfjordanfarr/copilot-self-improvement/copilot-instructions.svg)](https://agentmods.dev/instructions/jfjordanfarr/copilot-self-improvement/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/jfjordanfarr/copilot-self-improvement/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/jfjordanfarr/copilot-self-improvement/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,628 This file is loaded in full into every session.
When invoked 1,628 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 $0.01628 $0.01628
Opus 5 $0.00814 $0.00814
Sonnet 5 $0.00326 $0.00326
Haiku 4.5 $0.00163 $0.00163

Measured 5d ago against content hash c8bd77a307b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

copilot-self-improvement 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 · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Overview

This project defines the Copilot Self-Improvement plugin for VS Code, a radically simple read-only MCP tool which provides Github Copilot with the right instincts and context to durably self-manage the existing Copilot Instructions mechanism. .github/instructions/*.instructions.md files are prompts that are automatically added to the context window when matched to contain a glob pattern in their frontmatter. This simple technique can be used to introduce self-improvement capabilities to any project using GitHub Copilot Agent Mode.




AI Session State

[!IMPORTANT] When Agent Mode is enabled, it is mandatory to utilize the AI SESSION STATE FILE to track your progress and decisions. That file exists as a de-facto medium-term memory mechanism, carrying stateful/semi-ephemeral information across multiple context windows. On average, you (AI agent) are expected to one update to the session state doc per user response. Like our MDMD approach, this requires a commitment to keeping the AI Session State up-to-date with your current understanding and decisions. A highly durable indiciation for when to update the AI Session State file is this: If there is no evidence of a session state update within your active context window, the time to update the session state file is now.

[!IMPORTANT] If the circumstances or context change in such a way that would leave the AI Session State out of sync with your current understanding, you (AI agent) are expected to update the AI Session State file immediately. Failure to do so can cause cascading misunderstandings and errors in subsequent interactions.

[!NOTE] If not in Agent Mode (and conversing with a human user), please do not modify the AI Session State. This avoids issues with certain fully-autonomous agentic workflows.




Docs-First Approach

This project utilizes a Docs-First approach, patterned with an AI-Human collaboration model called Membrane Design Markdown (MDMD). Please refer to the MDMD Specification for comprehensive details on the syntax and structure used throughout this project. MDMD provides substantial grounding benefits but requires truly living documentation practices to be effective. AI assistants are expected to consult the docs/ and make updates often.

Read the full file on GitHub · 96 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. 5d ago First seen · 96 lines · 1,628 tokens per session scan A c8bd77a307b5

Subscribe to this mod's changes

copilot-self-improvement copilot-instructions.md is an instructions file published in the GitHub repository jfjordanfarr/copilot-self-improvement (2 stars, last pushed 1y ago), licensed MIT. It adds 1,628 tokens to every session, about $0.0081 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

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

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 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

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