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/amanasmuei/amem/copilot-instructionsgit clone --depth 1 https://github.com/amanasmuei/amemWrote 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/amanasmuei/amem/copilot-instructions)<a href="https://agentmods.dev/instructions/amanasmuei/amem/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/amanasmuei/amem/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 | $0.02416 | $0.02416 |
| Opus 5 | $0.01208 | $0.01208 |
| Sonnet 5 | $0.00483 | $0.00483 |
| Haiku 4.5 | $0.00242 | $0.00242 |
Grade A, and why
amem 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Instructions for amem
Build, Test, Lint
npm run build # tsc — must produce zero errors
npm test # vitest run — full suite
npx vitest run tests/memory.test.ts # single test file
npx vitest run -t "should compute score" # single test by name
npm run dev # tsc --watch
No linter is configured. The TypeScript compiler (strict: true) is the primary safety net.
Architecture
amem is an MCP server that gives AI coding tools persistent, searchable memory backed by SQLite. It communicates over stdio and exposes 23 tools, 6 resources, and 2 prompts via the MCP protocol.
Module dependency chain
index.ts — entry point: MCP server init, project detection, resource/prompt registration, auto-backup
├── database.ts — SQLite layer: 7 tables, prepared statements, FTS5 triggers, migrations
│ └── transaction(), resolveId(), resolveReminderId(), getAllRelations() — centralized DB ops
├── tools/ — 23 MCP tool registrations, split by domain:
│ ├── index.ts — registerTools() orchestrator + re-exports (TYPE_ORDER, formatAge)
│ ├── helpers.ts — shared constants (SHORT_ID_LENGTH, CHARACTER_LIMIT) and utilities
│ ├── memory.ts — 12 core tools: store, recall, detail, context, forget, extract, stats, export, inject, consolidate, patch, import
│ ├── versions.ts — memory_versions tool
│ ├── log.ts — memory_log, memory_log_recall, memory_log_cleanup tools
│ ├── graph.ts — memory_relate, memory_since, memory_search tools
│ └── reminders.ts — reminder_set, reminder_list, reminder_check, reminder_complete tools
├── memory.ts — ranking engine (scoring, consolidation, recall, explain mode)
├── schemas.ts — Zod output schemas (discriminated unions)
├── embeddings.ts — HuggingFace all-MiniLM-L6-v2 (optional, graceful fallback)
└── cli.ts — standalone CLI entry point (read-only DB operations)
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 · 175 lines · 2,416 tokens per session scan A 6ac00a8d451d
amem copilot-instructions.md is an instructions file published in the GitHub repository amanasmuei/amem (2 stars, last pushed 4mo ago), licensed MIT. It adds 2,416 tokens to every session, about $0.0121 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
skills AGENTS.md
Instructions for qdrant/skills, covering qdrant skills, project overview, project structure, navigating skills locally and conventions.
Norn CLAUDE.md
Instructions for samad001z/Norn, covering norn — project context, what this is, stack (v1), v1 scope — build only this and not in v1 (resist).
mindkeg-mcp CLAUDE.md
Instructions for carloluisito/mindkeg-mcp, covering mind keg mcp — development guide for ai agents, project overview, repository layout, code conventions and typescript.
git-notes-memory CLAUDE.md
Instructions for zircote/git-notes-memory, covering claude.md, project overview, development commands, install with dev dependencies and run all tests.
repo-context-mcp AGENTS.md
Instructions for nduc99911/repo-context-mcp, covering agents.md — repo-context-mcp, project, layout, commands and conventions.
tages CLAUDE.md
Instructions for ryantlee25-droid/tages, covering tages — project configuration, architecture, key design decisions, security and commands.