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/northgraindata/dbt-doctor/fp-guardrailsgit clone --depth 1 https://github.com/northgraindata/dbt-doctorWrote 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/rules/northgraindata/dbt-doctor/fp-guardrails)<a href="https://agentmods.dev/rules/northgraindata/dbt-doctor/fp-guardrails"><img src="https://agentmods.dev/badge/rules/northgraindata/dbt-doctor/fp-guardrails.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 5.1 | $0.00000 | $0.00266 |
| Opus 5 | $0.00000 | $0.00133 |
| Sonnet 5 | $0.00000 | $0.00053 |
| Haiku 4.5 | $0.00000 | $0.00027 |
Grade A, and why
fp-guardrails 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 6d 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
False-positive guardrails
When fixing a false positive in any rule:
- Add a minimal repro to
packages/dbt-doctor/tests/fixtures/dbt-fp-guardrails.ts- One
idper edge case; list every rule that must stay silent inrules.
- One
- Run
pnpm test—dbt-fp-guardrails.test.tsruns all cases viait.each. - Optionally validate on a real project:
pnpm fp-scan /path/to/dbt-project --preset enterprise.
Do not add large project snapshots to the repo; keep fixtures minimal and anonymized (no client model names, sources, or comments).
Coverage gap
~190 rules exist; guardrails currently cover common Jinja/dbt SQL patterns. Style-only rules use dedicated sql-*-style.test.ts files. When triaging new FPs, add anonymized cases to DBT_FP_GUARDRAILS or the relevant style test file.
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.
- 6d ago First seen · 21 lines · 0 tokens per session scan A 3592d4917c06
fp-guardrails is a cursor rule published in the GitHub repository northgraindata/dbt-doctor (58 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 266 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 2026-08-30.
Other cursor rules, from other repositories
cursorrules
Native SQL extensions for GoldenMatch (D:\showcase\goldenmatch).
dependencies
Dependency management guidelines.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.