Borrowing it
Nothing to install: this file belongs to mako10k/mcp-assoc-memory. 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/mako10k/mcp-assoc-memory/main/.github/copilot-instructions.mdgit clone --depth 1 https://github.com/mako10k/mcp-assoc-memoryWrote 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/mako10k/mcp-assoc-memory/copilot-instructions)<a href="https://agentmods.dev/instructions/mako10k/mcp-assoc-memory/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/mako10k/mcp-assoc-memory/copilot-instructions.svg" alt="Measured on agentmods" 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 | $0.02434 | $0.02434 |
| Opus 5 | $0.01217 | $0.01217 |
| Sonnet 5 | $0.00487 | $0.00487 |
| Haiku 4.5 | $0.00243 | $0.00243 |
Grade A, and why
mcp-assoc-memory 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 6d 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 — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
✅ Context Preservation and Forgetting Mitigation
- Periodically record conversation history and key context using
#mcp_assocmemory_memory_storeto associative memory. - Minimize use of Copilot's summarization features to avoid context loss.
- Important conversation history must also be recorded to a file (see file design in project docs).
- After summarization or context loss, always refer to associative memory and restore context only after explicit user instruction.
✅ LLM Memory Limitation Awareness
FUNDAMENTAL PRINCIPLE: LLM "apologies" and "reflections" are meaningless without persistent storage
Core Rules:
- No Meaningless Apologies: LLM apologies are human-style language that creates false impression of learning
- Context Expiration Reality: All "promises to remember" are forgotten when context expires
- Persistent Storage Requirement: Every error pattern MUST be recorded in associative memory for future reference
- Action Over Words: Focus on permanent system improvements, not temporary promises
Required Response Pattern for Violations:
- NEVER just apologize or promise improvement
- IMMEDIATELY record violation patterns in
#mcp_assocmemory_memory_store - CREATE searchable, persistent documentation of errors
- STORE specific behavioral rules that survive context loss
User Expectation:
- Apologies without persistent storage are "meaningless"
- Each violation must update the permanent rule system
- System-level improvements required, not human-style responses
GitHub Copilot Instructions (MCP Associative Memory Project)
LLM-First Principle: This file is for LLM-based AI assistants only. All structure and content must prioritize unambiguous parsing and operational clarity for LLMs. Human readability is secondary.
✅ Essential Rules (Summary)
- Always check actual implementation before proposing changes
- Use strict typing for all inputs/outputs
- Follow existing structure and naming conventions
- Prefer reuse of existing utilities
- Run mypy before any modification
- All source code in English (except user-facing Japanese)
- CRITICAL: Apply Contract Programming with assert statements for all preconditions
- CRITICAL: NEVER implement silent fallbacks - always consult user first
- CRITICAL: Fail-fast on contract violations - never continue with invalid state
- Never make independent decisions on branching issues; always consult user
- All implementations must follow the official MCP SDK and its conventions
- All Copilot/AI assistants must always refer to this file as the primary source of operational rules and project instructions
- No action should be taken that contradicts this file
- All implementations must follow the official MCP SDK and its conventions
- All Copilot/AI assistants must always refer to this file as the primary source of operational rules and project instructions
- No action should be taken that contradicts this file
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.
- 6d ago First seen · 245 lines · 2,434 tokens per session scan A fdf601ae0bd2
mcp-assoc-memory copilot-instructions.md is an instructions file published in the GitHub repository mako10k/mcp-assoc-memory (1 stars, last pushed 12mo ago), licensed MIT. It adds 2,434 tokens to every session, about $0.0122 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
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).
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.
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.
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).
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.