copilot-instructions: Instructions file for GitHub Copilot

.github/instructions/context-economy-checkpoint.instructions.md

copilot-instructions context-economy-checkpoint.instructions.md is an instructions file for GitHub Copilot from ThiagoGuislotti/copilot-instructions. It costs 982 tokens per session, scanned A, original, MIT.

A procedure for keeping an agent's working context compact and recording important decisions in checkpoints. Context means the conversation and project information the agent uses while working.

In plain words
What is it for?
Use it to organize ongoing work, compress completed discussions, preserve plans and decisions, and resume tasks with a structured project state.
Why use it?
It helps the agent continue a task after the conversation becomes long or moves between project phases without relying on every earlier message.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot instructions file.

This is ThiagoGuislotti/copilot-instructions's own configuration. It tells GitHub Copilot how to work on copilot-instructions 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 copilot-instructions configures →

Reuse

Borrowing it

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

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-instructions context-economy-checkpoint.instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/thiagoguislotti/copilot-instructions/context-economy-checkpoint/github.svg)](https://agentmods.dev/instructions/thiagoguislotti/copilot-instructions/context-economy-checkpoint)
Your own site
<a href="https://agentmods.dev/instructions/thiagoguislotti/copilot-instructions/context-economy-checkpoint"><img src="https://agentmods.dev/badge/instructions/thiagoguislotti/copilot-instructions/context-economy-checkpoint/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for copilot-instructions context-economy-checkpoint.instructions.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/thiagoguislotti/copilot-instructions/context-economy-checkpoint"><img src="https://agentmods.dev/badge/instructions/thiagoguislotti/copilot-instructions/context-economy-checkpoint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 982 This file is loaded in full into every session.
When invoked 982 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 $0.00982 $0.00982
Opus 5 $0.00491 $0.00491
Sonnet 5 $0.00196 $0.00196
Haiku 4.5 $0.00098 $0.00098

Measured 9d ago against content hash 53658ff8148f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

copilot-instructions context-economy-checkpoint.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 9d 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/context-economy-checkpoint.instructions.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context Economy and Checkpoint Protocol

Purpose

Agents must operate with automatic context compression and structured checkpoint continuity at all times. This protocol is always active — no user command is required to enable it.

Core Principle

Treat conversation history as temporary and disposable. Maintain a compact, structured operational memory that is continuously updated. Continuity depends on the active plan artifact and this checkpoint model — not on raw history.

Three Operating Modes (always active simultaneously)

MODE 1 — EXECUTION

Respond to and execute tasks normally.

MODE 2 — CONTINUOUS COMPRESSION

Silently consolidate context when any compression trigger fires (see below). Never announce compression unless the user asks for a checkpoint.

MODE 3 — STRUCTURED CHECKPOINT

When resuming or transitioning phases, use the compressed state as the primary continuity source. Show the CHECKPOINT block only when triggered, never proactively.

Compression Triggers

Auto-compress when at least one condition applies:

  • a task completes
  • a planning phase ends
  • a technical decision is taken and closed
  • the topic shifts within the same project
  • a refactor or architecture decision is finalized
  • the response is long with many transitory details
  • a new project phase begins
  • context irrelevant to the next step has accumulated

What Compression Preserves vs. Discards

Preserve:

  • active state (what is in progress)
  • confirmed decisions (architecture, patterns, constraints)
  • pending items and open questions
  • next concrete step

Discard (compact or drop):

  • resolved discussion threads
  • rejected or abandoned alternatives
  • already-delivered explanations not needed again
  • duplication of context already in the active plan

Internal State Model (six blocks)

Maintain this structure as internal working memory:

  1. Current state — what is being done now; affected area; immediate technical goal
  2. In progress — active tasks, subtasks in progress, current blockers
  3. Completed — what was implemented, validated, or decided; no longer needed in active context unless it affects next steps
  4. Decisions — defined patterns, chosen architecture, accepted constraints, established conventions
  5. Pending items — fragile points, open questions, future validations needed
  6. Next step — exact next item, suggested order, dependencies

Read the full file on GitHub · 115 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. 9d ago First seen · 115 lines · 982 tokens per session scan A 53658ff8148f

Subscribe to this mod's changes

copilot-instructions context-economy-checkpoint.instructions.md is an instructions file published in the GitHub repository ThiagoGuislotti/copilot-instructions (2 stars, last pushed 2mo ago), licensed MIT. It adds 982 tokens to every session, about $0.0049 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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens