What is cortex copilot-instructions.md?

Workspace instructions for CortexPrism’s Cortex project and its ContextStream memory system. They define required startup, context, search, and session tool calls for keeping work grounded.

Use them when starting or continuing Cortex work, loading project context, searching files, recording plans, and following ContextStream session rules.

They make the agent follow the project’s required context and memory workflow instead of relying only on the current chat. This helps preserve relevant project information across work sessions.

cortex copilot-instructions.md — Instructions file by CortexPrism

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/cortexprism/cortex/copilot-instructions

Clone the repo

git clone --depth 1 https://github.com/CortexPrism/cortex

Made for: GitHub Copilot.

Per session 10,877 This file is loaded in full into every session.

When invoked 10,877 The same file — it is already loaded in full.

Security scan C 2 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.

Model	Per session	Once invoked
Fable 5	$0.10877	$0.10877
Opus 5	$0.05438	$0.05438
Sonnet 5	$0.02175	$0.02175
Haiku 4.5	$0.01088	$0.01088

Measured 2d ago against content hash 31235c4d87bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

cortex copilot-instructions.md scanned grade C with 2 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 2d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL https://contextstream.io/scripts/setup.sh | bash

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsSL https://contextstream.io/scripts/setup.sh | bash

.github/copilot-instructions.md · 822 lines

How it starts

The opening of the file, as written. The whole thing — 822 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ContextStream Rules

MANDATORY STARTUP: On the first message of EVERY session call init(...). Then call context(user_message="...") when that tool is exposed; if context is unavailable in this MCP surface, call session(action="ground", user_message="...") instead. On subsequent messages, call context(...) first by default, or session(action="ground", user_message="...") when context is unavailable. A narrow bypass is allowed only for immediate read-only ContextStream calls when prior context is still fresh and no state-changing tool has run.

Required Tool Calls

First message in session: Call init(folder_path="<project_path>") then context(user_message="...", session_id="<id>"); if context is unavailable, call session(action="ground", user_message="...")
Subsequent messages (default): Call context(user_message="...", session_id="<id>") first, or session(action="ground", user_message="...") when context is unavailable. Narrow bypass: immediate read-only ContextStream calls with fresh context + no state changes.
Before file search: Call search(mode="auto", query="...") before local tools

Read the full file on GitHub · 822 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.

2d ago First seen · 822 lines · 10,877 tokens per session scan C 31235c4d87bd

Subscribe to this mod's changes

cortex copilot-instructions.md is an instructions file published in the GitHub repository CortexPrism/cortex (192 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 10,877 tokens to every session, about $0.0544 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Memory and context Research agentic-ai ai-agent-operating-system ai-agents ai-os ai-tools autonomous-agent-runtime

latchkey AGENTS.md

Instructions for imbue-ai/latchkey: For information about the high-level goal and motivations, see README.md.

imbue-ai/latchkey · 164 tokens

get-fable AGENTS.md

Instructions for imMamdouhaboammar/get-fable, covering get-fable repository instructions, purpose, working contract, canonical lifecycle packs and runtime semantics.

imMamdouhaboammar/get-fable · 733 tokens