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/thiagoguislotti/copilot-instructions/ormgit clone --depth 1 https://github.com/ThiagoGuislotti/copilot-instructionsWrote 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/thiagoguislotti/copilot-instructions/orm)<a href="https://agentmods.dev/instructions/thiagoguislotti/copilot-instructions/orm"><img src="https://agentmods.dev/badge/instructions/thiagoguislotti/copilot-instructions/orm.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 | $0.00460 | $0.00460 |
| Opus 5 | $0.00230 | $0.00230 |
| Sonnet 5 | $0.00092 | $0.00092 |
| Haiku 4.5 | $0.00046 | $0.00046 |
Grade A, and why
copilot-instructions orm.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 4d 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.
What it actually says
Domain
- Business rules in domain (not in repositories)
- POCO classes without infra deps
- Invariants in constructor/factories
- Restricted setters
- Singular descriptive names (e.g., Invoice)
- Guid or long IDs
- Consider value objects (e.g., Cnpj, Email) and owned types
// Value object Email with validation
// Aggregate Order exposes AddItem() enforcing invariants
// Entity IDs as Guid
// No EF attributes in Domain
Mapping
- Centralized mapping (per entity/aggregate)
- Avoid persistence annotations in domain
- No lazy loading
- Prefer projections and explicit loading
- Concurrency control
- Soft-delete only with clear requirement
- Explicit constraints/indexes
- Auditing outside domain
// Fluent mapping class OrderMapping configures keys/indexes and relationships
// Use HasIndex(o => new { o.CustomerId, o.CreatedAt }).IncludeProperties(...)
Repositories/use cases
- Repositories per aggregate
- No business rules in repositories
- UoW/transactions in use case
- For read-heavy paths use projections and optimized queries when sensible
// IOrderRepository.GetRecentAsync returns DTOs via projection
// Application UseCase wraps Save changes in a transaction with retry on deadlock
// Batch operations use bulk APIs
Queries/DTOs
- Never return entities to the API
- Map to DTOs
- Paginate large lists
- Safe sortable filters
// Query projects to OrderListItemDto { Id, Number, Total, CreatedAt }
// Keyset pagination using (CreatedAt,Id)
// Allow sort by CreatedAt only
Security/observability
- No secrets in connection strings
- Minimal DB roles
- Structured logs with correlationId
- Metrics for pool/timeout/retries
// Connection string from secure vault
// DbContext logs include correlationId
// Metrics: connection pool usage, command timeouts, retries count
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.
- 4d ago First seen · 66 lines · 460 tokens per session scan A 287dbf70459a
copilot-instructions orm.instructions.md is an instructions file published in the GitHub repository ThiagoGuislotti/copilot-instructions (2 stars, last pushed 2mo ago), licensed MIT. It adds 460 tokens to every session, about $0.0023 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
vespertide AGENTS.md
AGENTS.md instructions for dev-five-git/vespertide, covering vespertide knowledge base, structure, where to look, data flow and conventions.
lms-front CLAUDE.md
Claude Code instructions for guillermoscript/lms-front, covering claude.md, project overview, commands, architecture and multi-tenancy.
rails_ai_agents AGENTS.md
AGENTS.md instructions for ThibautBaissac/rails_ai_agents, covering project configuration, tech stack, architecture, key commands and tests.
seekstone CLAUDE.md
Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
llm-safe-sql AGENTS.md
AGENTS.md instructions for hyuga611/llm-safe-sql, covering notes for coding agents, what this project is, rules that are not style preferences, where things are and before you say you are done.
pg-dash CLAUDE.md
Claude Code instructions for indiekitai/pg-dash, covering pg-dash claude.md, 项目结构, 构建与测试, 发版纪律(强制) and 发版检查清单(每次 npm publish 前必须按序执行).