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/huvaxstra/agnt/cursorrulesgit clone --depth 1 https://github.com/huvaxstra/AGNTWhat 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 | $0.00316 | $0.00316 |
| Opus 5 | $0.00158 | $0.00158 |
| Sonnet 5 | $0.00063 | $0.00063 |
| Haiku 4.5 | $0.00032 | $0.00032 |
Grade A, and why
cursorrules 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
SpecAgnt — Cursor Rules
Project Overview
SpecAgnt generates production-grade project specs + Agent Manifest from fill-in-the-blank templates. 31 templates in base/, orchestrated by kit.md + engine.md.
Critical Rules
- NEVER modify
base/templates in place — they are the source of truth - Template count must stay at 31 — discuss before adding/removing
- All cross-references must stay in sync: kit.md, README.md, CHANGELOG.md, scripts/, base/
- YAML frontmatter required on every
base/template - Placeholder format:
[...]or[AGENT: ...]— never empty[]
Deleted Files (do not recreate)
base/state-management.md→ merged intoarchitecture.md§7base/db-rollback.md→ merged intodeployment.md§5base/deploy-guide.md→ obsolete (cPanel hosting)
New Files
base/ai-integration.md— AI/LLM integration specbase/design-system-advanced.md— optional advanced design sections
Before Committing
bash scripts/validate-templates.sh
File Conventions
- Templates:
base/*.mdwith YAML frontmatter - Generated output:
docs/N-name.md(numeric prefix) - Config:
specagnt.json(auto-mode) - Scripts:
scripts/*.sh(setup + validation)
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 · 32 lines · 316 tokens per session scan A e6634748f095
cursorrules is a cursor rule published in the GitHub repository huvaxstra/AGNT (5 stars, last pushed 3mo ago), licensed MIT. It adds 316 tokens to every session, about $0.0016 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 cursor rules, from other repositories
css-styling
CSS architecture, tokens, and styling rules for this Docusaurus site. Apply when creating or modifying components, styles, layouts, or any UI-facing code.
code-patterns
Python code style and recurring patterns (config, logging, errors, paths).
creating-cursor-rules
Meta-rule for creating effective Cursor IDE rules with best practices, patterns, and examples.
controllers
Remember: Controllers are just the translation layer between HTTP and your application. Keep them simple and let other layers handle complexity.
performance
Remember: Premature optimization is the root of all evil. Profile first, optimize what matters, and keep solutions maintainable.
core
Rails 8 Core Principles Guide.