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/databasegit clone --depth 1 https://github.com/ThiagoGuislotti/copilot-instructionsWhat 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 | $0.01366 | $0.01366 |
| Opus 5 | $0.00683 | $0.00683 |
| Sonnet 5 | $0.00273 | $0.00273 |
| Haiku 4.5 | $0.00137 | $0.00137 |
Grade A, and why
copilot-instructions database.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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Schema design
- Tables/columns/indexes/constraints in EN
- PascalCase for tables
- camelCase for columns
- pk_ for primary keys
- fk_ for foreign keys
- ix_ for indexes
- ck_ for checks
- uq_ for unique
- Triggers with tr_ prefix
CREATE TABLE Orders (
orderId BIGINT PRIMARY KEY,
createdAt DATETIME
);
ALTER TABLE Orders ADD CONSTRAINT pk_Orders PRIMARY KEY (orderId);
CREATE INDEX ix_Orders_CreatedAt ON Orders(createdAt);
Normalization
- 1NF atomic columns
- 2NF full functional dependency
- 3NF no transitive dependency
- BCNF when applicable
- Controlled denormalization only for critical performance with justification
-- 3NF - Separate Addresses from Users to avoid transitive dependency
Cartesian explosion
- Avoid JOINs without proper predicates
- Prefer EXISTS over IN with subqueries
- Filter before JOIN using CTEs/subqueries
- Verify cardinality estimates
- Test with large datasets
- Inspect execution plans
WITH Filtered AS (SELECT * FROM Orders WHERE status = 'Active')
SELECT * FROM Filtered JOIN Customers ON Filtered.customerId = Customers.id;
Parameter sniffing
- OPTION(OPTIMIZE FOR UNKNOWN) when applicable
- Properly typed parameters
- Avoid dynamic SQL when possible
- Stored procedures with RECOMPILE when needed
- Plan guides for specific cases
- Forced parameterization in controlled scenarios
SELECT * FROM Orders WHERE status = @status OPTION (OPTIMIZE FOR UNKNOWN);
Query performance
- Avoid SELECT *
- Appropriate indexes
- SARGABLE predicates (avoid functions in WHERE)
- LIMIT/TOP for large datasets
- Up-to-date statistics
- Plan analysis
- Avoid N+1
- Keyset (seek) pagination for large lists
SELECT TOP (@size) * FROM Orders
WHERE (createdAt, id) > (@lastCreatedAt, @lastId)
ORDER BY createdAt, id; -- Keyset pagination
Indexes
- Clustered on most queried keys
- Non-clustered for FKs and filter columns
- Composite with most selective first
- Include columns for covering indexes
- Proper fill factor
- Maintenance plans
- Avoid over-indexing
- Drop unused
CREATE INDEX ix_Orders_CustomerId_CreatedAt ON Orders(CustomerId, CreatedAt) INCLUDE (Status, TotalAmount);
-- Drop ix_Orders_Temp if unused per stats
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 · 213 lines · 1,366 tokens per session scan A ad26fccf80d4
copilot-instructions database.instructions.md is an instructions file published in the GitHub repository ThiagoGuislotti/copilot-instructions (2 stars, last pushed 2mo ago), licensed MIT. It adds 1,366 tokens to every session, about $0.0068 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
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.
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).
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).
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.