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.
npx agentmods add instructions/jthiruveedula/agent-memory-mcp/copilot-instructionsgit clone --depth 1 https://github.com/jthiruveedula/agent-memory-mcpWrote 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/jthiruveedula/agent-memory-mcp/copilot-instructions)<a href="https://agentmods.dev/instructions/jthiruveedula/agent-memory-mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/jthiruveedula/agent-memory-mcp/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 | $0.00917 | $0.00917 |
| Opus 5 | $0.00458 | $0.00458 |
| Sonnet 5 | $0.00183 | $0.00183 |
| Haiku 4.5 | $0.00092 | $0.00092 |
Grade A, and why
agent-memory-mcp 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 3d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Memory MCP — Copilot Instructions
Project Overview
This is a TypeScript MCP server that provides persistent, cross-workspace agent memory with:
- Semantic + keyword memory recall (SQLite FTS5 + vector similarity)
- Personal knowledge graph (entity/relation extraction)
- Preference learning from explicit statements and corrections
- Tool outcome logging and recommendation
- Self-improvement via reflection (duplicate merge, insight surfacing)
SDK References
- MCP TypeScript SDK: https://github.com/modelcontextprotocol/typescript-sdk
- MCP Specification: https://modelcontextprotocol.io/specification/latest
- MCP Docs: https://modelcontextprotocol.io/
Architecture
src/index.ts— entry point (starts stdio transport)src/server.ts— MCP server wiring (tools, resources, prompts)src/config.ts— configuration from environment variablessrc/types.ts— Zod schemas and TypeScript typessrc/db/schema.ts— SQLite schema with versioned migrationssrc/db/memory-store.ts— CRUD, FTS5 search, embeddings, graph persistencesrc/db/embeddings.ts— hash-based local or OpenAI embedding generationsrc/graph/knowledge-graph.ts— entity/relation extraction and graph queriessrc/learning/preference-learner.ts— preference extraction from text and correctionssrc/learning/tool-recommender.ts— tool outcome learning and rankingsrc/learning/self-improver.ts— reflection, duplicate detection, confidence adjustmentsrc/tools/memory-tools.ts— MCP tool handlers (pure functions, context injected)
Conventions
- Use Zod schemas in
src/types.tsfor all tool arguments. - Keep tool handlers pure; context is passed via
ToolContext. - All storage goes through
MemoryStore. - Embeddings default to local hashing-based vectors; optionally use OpenAI when
OPENAI_API_KEYis set. - Data is stored in
~/.agent-memory-mcp/by default (configurable viaAGENT_MEMORY_DIR). - Schema versioning:
src/db/schema.tsmanages versioned migrations via_metatable.
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.
- 3d ago First seen · 107 lines · 917 tokens per session scan A d061f3b88dff
agent-memory-mcp copilot-instructions.md is an instructions file published in the GitHub repository jthiruveedula/agent-memory-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 917 tokens to every session, about $0.0046 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 2026-09-01.
Other instructions, from other repositories
vespertide AGENTS.md
AGENTS.md instructions for dev-five-git/vespertide, covering vespertide knowledge base, structure, where to look, data flow and conventions.
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
wayland-core copilot-instructions.md
Copilot instructions for FerroxLabs/wayland-core, covering ijfw rules, output discipline, memory routing, context discipline and cross-audit.
mcp-structured-memory CLAUDE.md
Claude Code instructions for nmeierpolys/mcp-structured-memory, a project described as: Structured Memory MCP Server.
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.
RNR-Enhanced-Cognee AGENTS.md
AGENTS.md instructions for vincentspereira/RNR-Enhanced-Cognee, covering rnr enhanced cognee implementation for codex, critical requirements, 1. ascii-only output (no unicode encoding), 2. dynamic categories (no hardcoded categories) and 3. standard memory mcp interface.