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.
git clone --depth 1 https://github.com/blockmatic/basilicWrote 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/blockmatic/basilic/docs)<a href="https://agentmods.dev/rules/blockmatic/basilic/docs"><img src="https://agentmods.dev/badge/rules/blockmatic/basilic/docs/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/blockmatic/basilic/docs"><img src="https://agentmods.dev/badge/rules/blockmatic/basilic/docs.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00298 |
| Opus 5.5 | $0.00000 | $0.00119 |
| Sonnet 5.5 | $0.00000 | $0.00060 |
| Haiku 4.5 | $0.00000 | $0.00030 |
Grade A, and why
docs 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 22d 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
Writing Principles
- Simple, succinct, technical, factual; lead with the answer
- Active voice, present tense, concrete nouns;
evelowercase - Consistent capability names with architecture overview
- Follow
.agents/skills/technical-writing/(verify against this repo) - 300-500 words/section, remove redundancy; no promotional adjectives
Content Structure
- Title/description → short intro → H2/H3 → examples → related links
- One concept per section; happy path before alternatives
- Personas: intro = evaluate; architecture = mental model; development = task; reference-dense pages = scan
Navigation
- Max 5-7 top categories, max 2 levels deep; inbound body links, no orphans
Organization
- DRY: one canonical home; README/homepage summarize and link
- Progressive disclosure; do not invent pages to fill Diátaxis slots
- Semantic feature parity with root README (same capabilities, different copy)
Layers
- This MDX is canonical technical docs. Visual language is root
DESIGN.md. Rules do not@-attach MDX - READMEs are how to run the app/package; they link here, no duplication
- Update this page when behavior, architecture, commands, or conventions change
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.
- 22d ago Changed · +1 lines 39902237566b
- 25d ago Changed 4f1a2a1c3e43
- 29d ago Changed e6572116e6a3
- 1mo ago Changed 5ee5b11f1605
- 1mo ago Changed · +5 lines · -172 tokens per session 86815da4788b
- 1mo ago First seen · 25 lines · 172 tokens per session scan A c3102050e290
docs is a cursor rule published in the GitHub repository blockmatic/basilic (90 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 298 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
hatch3r-typescript-patterns
TypeScript and JavaScript typing mechanics — satisfies over as, discriminated unions, branded types, strict utility types, barrel exports, and import ordering.
typescript-coding-standards
Production TypeScript coding standards.
testing-standards-typescript
When writing tests for typescript.
typescript-error-handling
Error handling patterns for TypeScript with Sentry.
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.