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.
curl -O https://raw.githubusercontent.com/ThiagoGuislotti/copilot-instructions/main/.github/instructions/context-economy-checkpoint.instructions.mdgit clone --depth 1 https://github.com/ThiagoGuislotti/copilot-instructionsWrote 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.
[](https://agentmods.dev/instructions/thiagoguislotti/copilot-instructions/context-economy-checkpoint)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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:
- Current state — what is being done now; affected area; immediate technical goal
- In progress — active tasks, subtasks in progress, current blockers
- Completed — what was implemented, validated, or decided; no longer needed in active context unless it affects next steps
- Decisions — defined patterns, chosen architecture, accepted constraints, established conventions
- Pending items — fragile points, open questions, future validations needed
- Next step — exact next item, suggested order, dependencies
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.
- 9d ago First seen · 115 lines · 982 tokens per session scan A 53658ff8148f
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.
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.
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.
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).
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).
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.
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.