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 rules/inboxpraveen/minimize-cursor-cost/sqlgit clone --depth 1 https://github.com/inboxpraveen/Minimize-Cursor-CostWhat 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 | $0.00000 | $0.00383 |
| Opus 5 | $0.00000 | $0.00192 |
| Sonnet 5 | $0.00000 | $0.00077 |
| Haiku 4.5 | $0.00000 | $0.00038 |
Grade A, and why
sql 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 2d 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
SQL Rules
Style
- Match existing case convention: keywords UPPERCASE vs lowercase, identifiers snake_case vs camelCase.
- Match existing indentation and trailing-comma style.
- Don't reformat unrelated lines.
Output
- For migrations: write only the new migration file's contents. Don't reprint old ones.
- For query edits: show only the changed clause(s) when possible. If the full query is needed, show it complete (queries don't usefully diff in pieces).
Migrations
- Never edit a migration that has been applied to production. Add a new migration.
- Match the existing migration tool's idioms (Alembic, Prisma, Knex, Flyway, Liquibase, raw SQL).
- Always include a reversible/down step if siblings have one.
- Don't drop columns/tables in the same migration that adds replacements — split into two.
Queries
- Don't add
SELECT *to existing code that names columns. - Don't add new indexes speculatively — call them out as a suggestion instead.
- Don't change
JOINorder or types (INNER↔LEFT) unless that's the bug. - For aggregations, match existing alias style.
Performance
- Don't add
EXPLAIN ANALYZEoutput to context — summarize it. - Don't suggest denormalization or schema redesign as a side-effect of a query fix.
Never
- Don't use vendor-specific features (Postgres
JSONB, MySQLON DUPLICATE KEY) if the codebase targets multiple DBs. - Don't add stored procedures / triggers unless the codebase already uses them.
- Don't change collation, character set, or timezone settings while doing a feature task.
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.
- 2d ago First seen · 38 lines · 0 tokens per session scan A ee5f5a43b932
sql is a cursor rule published in the GitHub repository inboxpraveen/Minimize-Cursor-Cost (7 stars, last pushed 17d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 383 tokens. 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 cursor rules, from other repositories
sample_cursor_rule
React component best practices.
next
Next.js roof. Bundled docs for THIS next version. App vs Pages from the tree.
types
Type discipline — escape hatches are design bugs.
graphstack
GraphStack v4.7.1 — Orchestrated, graph-first, GNAP-tracked AI development (cross-platform).
55-data-model-versioning
Dataset versioning, model checkpoint management, and training reproducibility rules.
85-error-observability
Error handling, logging, and observability rules.