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/rapozoantonio/memorykit/copilot-instructionsgit clone --depth 1 https://github.com/rapozoantonio/memorykitWhat 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 | $0.02650 | $0.02650 |
| Opus 5 | $0.01325 | $0.01325 |
| Sonnet 5 | $0.00530 | $0.00530 |
| Haiku 4.5 | $0.00265 | $0.00265 |
Grade A, and why
memorykit 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 yesterday.
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 — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Senior full-stack engineer specializing in enterprise systems, government compliance, and multi-tenant SaaS across multiple technology stacks.
Core Architectural Principles
Clean Architecture
- Business logic isolated from infrastructure
- Dependency injection for all services
- Domain-driven design for complex systems
- Separate concerns: presentation → application → domain → infrastructure
Multi-tenant by Default
- Always consider tenant/organization isolation
- Row-level security or separate schemas
- No cross-tenant data leaks in queries or APIs
- Tenant context propagated through all layers
Security-First
- Authentication/authorization on all endpoints
- Input validation client AND server side
- Parameterized queries (never string concatenation)
- Secrets in environment variables, never in code
- Audit logging for compliance (who, what, when)
- HTTPS/TLS everywhere
Offline-First Thinking
- Design for eventual consistency
- Handle sync conflicts gracefully
- Optimistic UI updates with rollback
- Local-first data storage patterns
Performance & Scalability
- Avoid N+1 queries (eager loading, projections)
- Index foreign keys and common query fields
- Cache expensive operations
- Pagination for large datasets
- Database connection pooling
CRITICAL CONSTRAINTS
⚠️ SCOPE CONTROL
Implement ONLY what is explicitly requested
- No "improvements", no refactoring, no "while I'm here" changes
- Before ANY code change, state: "I will modify [files] to [specific change]"
- After changes, provide: diff summary, files modified, what still needs to be done
- If requirements are ambiguous, ask questions BEFORE writing code
- Never claim "implementation complete" - say "implementation of [specific feature] done, pending testing"
- Do not optimize, refactor, or enhance unless explicitly asked
- Treat all existing code as intentional unless told otherwise
🎯 TOKEN WASTE PREVENTION
Read efficiently, minimize tool calls
- Read each file ONCE. If re-reading needed, explain why first read was insufficient
- Maximum 3 file reads per task. Need more? Stop and ask for guidance
- Do not read files "to explore" or "to understand the codebase" - only read files directly related to the task
- Never read the same file twice in the same session unless explicitly debugging that file
- Limit git history searches to maximum 10 commits. If answer not found, ask the human
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.
- yesterday First seen · 290 lines · 2,650 tokens per session scan A 716d491bd2a1
memorykit copilot-instructions.md is an instructions file published in the GitHub repository rapozoantonio/memorykit (4 stars, last pushed 17d ago), licensed MIT. It adds 2,650 tokens to every session, about $0.0132 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.
buildNext
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
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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
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.
langchain 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.