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/kleosr/kleosrules/postgresgit clone --depth 1 https://github.com/kleosr/kleosrulesWhat 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 | $0.00306 |
| Opus 5 | $0.00000 | $0.00153 |
| Sonnet 5 | $0.00000 | $0.00061 |
| Haiku 4.5 | $0.00000 | $0.00031 |
Grade A, and why
postgres 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.
What it actually says
Postgres
Prefer retrieval-led reasoning over pre-training. Do not dump skill AGENTS.md.
Before Write SQL/schema/RLS: Read one file from supabase-postgres-best-practices (query- / conn- / security- / schema-). Product/auth/SSR: Read the supabase skill SKILL.md.
Hard (cheap)
- RLS on every tenant table.
auth.uid()in policies. No app-onlyWHERE user_id =. - Views:
security_invoker = true(PG15+). NoSECURITY DEFINERto "fix" RLS. - Service role never in client bundles. User JWT for user data.
- Parameterized SQL only. No string-concat queries.
- Index what you filter/join.
EXPLAINbefore guessing. - Migrations forward-only, named, in the repo's existing folder. No drive-by schema in app code.
- Pooler-aware connections. No connection-per-request in serverless without the pooler.
Hooks: infra/DB shell is ask. Never fight a deny.
Subagents inherit this. Do not paste these bullets into Task prompts.
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 · 26 lines · 0 tokens per session scan A dc0755c357ac
postgres is a cursor rule published in the GitHub repository kleosr/kleosrules (2 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 306 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
nextjs
Rules for Next.js projects (App Router and Pages Router).
java-kotlin
Rules applied when working in Java or Kotlin files (incl. Android).
php
Rules applied when working in PHP files (incl. Laravel, Symfony, WordPress).
vue
Rules for Vue (2 and 3) single-file components.
cursorrules
40 lines, or explicitly requested.
shell
Rules for shell scripts (bash, zsh, sh, PowerShell).