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/zexion7873/copilot-setting/sqlgit clone --depth 1 https://github.com/zexion7873/copilot-settingWhat 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 | $0.00732 | $0.00732 |
| Opus 5 | $0.00366 | $0.00366 |
| Sonnet 5 | $0.00146 | $0.00146 |
| Haiku 4.5 | $0.00073 | $0.00073 |
Grade A, and why
copilot-setting sql.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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SQL Conventions
Non-negotiable rules for all SQL — raw JDBC, HQL, native queries. Hibernate query patterns: instructions/spring-hibernate.instructions.md. DDL / migration rules: instructions/sql-ddl.instructions.md.
Security
- JDBC: all user input via
PreparedStatementwith?— zero tolerance for string concatenation - HQL / Criteria: use named parameters (
:paramName) only — never concatenate into query strings - Escape
%,_, and the escape char itself in any user input bound toLIKE, and declare it —... LIKE ? ESCAPE '\\'; never silently strip user-supplied wildcards (that changes query semantics) - No
SELECT *on tables with sensitive columns - Never log SQL containing credentials or PII
Performance
- No
SELECT *— list columns explicitly - No functions on indexed columns in
WHERE— use range conditions - No
OFFSETpagination on large tables — cursor:WHERE id > ? ORDER BY id LIMIT N - N+1 = SQL inside a loop — batch with
INor JOIN INvsEXISTSsubqueries: MySQL 8.0 optimizes both with the same semijoin transforms (EXISTSsince 8.0.16) — pick the clearer form and checkEXPLAIN; bewareNOT INmatching nothing when the subquery returns aNULL- Batch INSERT/UPDATE/DELETE — never row-by-row; chunk and commit per chunk to bound lock time, transaction size, and redo/binlog volume (low thousands of rows is a typical starting point, not a fixed limit — tune to row width, index count, and lock/replication pressure)
JDBC Resources
try-with-resourcesforConnection,PreparedStatement,ResultSetWHEREclause mandatory on everyUPDATEandDELETE- Transactions (raw JDBC only — Spring-managed
<tx:advice>handles this automatically): commit or rollback on every code path
Anti-Patterns
| Pattern | Problem | Fix |
|---|---|---|
"WHERE name = '" + name + "'" |
SQL injection | PreparedStatement with ? + setString() |
SELECT * FROM orders |
Unnecessary columns; schema-fragile | List columns explicitly |
WHERE YEAR(created_at) = 2024 |
Function kills index | Range: >= '2024-01-01' AND < '2025-01-01' |
LIMIT 10 OFFSET 10000 |
Scans 10K rows to discard | Cursor: WHERE id > ? ORDER BY id LIMIT 10 |
SQL inside a for loop |
N+1 queries | WHERE id IN (?, ...) or JOIN |
Connection without try-with-resources |
Leak on exception; pool exhaustion | try (Connection c = ...) { } |
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 · 43 lines · 732 tokens per session scan A aeee0da4269a
copilot-setting sql.instructions.md is an instructions file published in the GitHub repository zexion7873/copilot-setting (1 stars, last pushed 28d ago), licensed MIT. It adds 732 tokens to every session, about $0.0037 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
ai-agent-rules-generator copilot.instructions.md
Glitch WooCommerce Payment Gateway plugin coding guidelines — auto-doc sync for plugin, features, and infrastructure.
ai-agent-rules-generator agent-observations.instructions.md
Mandatory agent observation logging — anomalies, recommendations, and critical findings must be disclosed before commit.
ai-agent-rules-generator task.instructions.md
Task execution rules for Glitch WooCommerce Payment Gateway engineering work.
ai-agent-rules-generator doc-sync.instructions.md
Documentation sync rules — which docs to update when code changes.
ai-agent-rules-generator browsetools.instructions.md
Browser verification rules for Glitch WooCommerce Payment Gateway using Chrome DevTools MCP.
ai-agent-rules-generator devtools.instructions.md
Browser DevTools and local development access credentials.