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/heavyblotto/caelusWrote 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/heavyblotto/caelus/copy)<a href="https://agentmods.dev/rules/heavyblotto/caelus/copy"><img src="https://agentmods.dev/badge/rules/heavyblotto/caelus/copy/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/heavyblotto/caelus/copy"><img src="https://agentmods.dev/badge/rules/heavyblotto/caelus/copy.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 | $0.00365 |
| Opus 5.5 | $0.00000 | $0.00146 |
| Sonnet 5.5 | $0.00000 | $0.00073 |
| Haiku 4.5 | $0.00000 | $0.00036 |
Grade A, and why
copy 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 1mo 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
Copy and prose (Caelus)
Before editing user-facing text, read docs/editorial-voice.md and docs/ai-slop-style-sheet.md.
Voice
- Dry engineer, not pitch deck. Facts and measurements over adjectives.
- Short sentences. Name sources and numbers.
- No manifesto lines, mic-drops, or performed wit ("full stop", "mail to Zurich", "every layer needs its own referee").
Banned patterns
- AI filler: delve, unpack, landscape, tapestry, testament, resonates, pivotal, holistic, "it's important to note"
- Meta: "the lesson generalizes", "what this buys you", "cannot hide inside it", "the actual asset"
- Em-dash chains — prefer comma, colon, or a new sentence
Workflow
- Edit copy in
apps/web/ordocs/. - Run
npm run lint:proseand fix warnings. - Do not rewrite package API docs or golden test commentary unless asked.
Terminology
- Caelus (capitalized) for the project/engine in prose
caelus(lowercase) for the npm package name, imports (from "caelus"), andnpm install caelus- Title case for page headings and nav labels
- Emoji only in the home-page hero bullets and CTA labels; nowhere else
Swiss Ephemerisas oracle/referee, never as source codeclean-roomsparingly; prefer "written from published sources"
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.
- 1mo ago First seen · 37 lines · 0 tokens per session scan A c3ffad48e762
copy is a cursor rule published in the GitHub repository heavyblotto/caelus (1 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 365 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
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.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
config-validation-and-normalization
Config validation and normalization responsibilities (defineConfig normalizes, the orm section schema validates and resolves paths, the loader reports per-section diagnostics).