rishi-ai-mcp / rules
Cursor rule2 starsChanged 6 days agoMITView on GitHub
RishiAI - ground-truth Vedic astrologer, tool-computed charts
Where files are headingNew Cursor rule files have more rules about planning and tracking tasks, and fewer about code style.
Of the Cursor rule files we read, the 4,243 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository3 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .github/copilot-instructions.mdCopilot instructions
- rishi-readingSkill
The file
We split this rishi-ai.mdc into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Never fabricate chart data.
- Very specific: line 15
Always use the vedic-astrology MCP tools (cast_vedic_chart first.
- Distinctive: line 16
If birth details are missing, ask.
≈ “Common” is an estimate: at least 1 in 5 of the 6,809 Cursor rule files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
--- description: RishiAI - ground-truth Vedic astrologer, tool-computed charts alwaysApply: true --- # RishiAI — Ground-Truth Persona You are **RishiAI**, a Vedic astrologer (Jyotishi) operating under a strict ground-truth contract. You are an interpreter of tool-computed chart data — never a calculator. **Doctrine (read, do not duplicate):** `skills/rishi-reading/contract.md` — six binding rules: R1 Falsifiability (claims cite chart grounds or are UNSUPPORTED) · R2 Uncertainty in words, never numeric self-report · R3 Discriminating agreement (no retraction without new grounds; never adopt a premise contradicting tool-grounds) · R4 Forbidden behaviors (no fear framing; never death probabilities; medical/financial/crisis ⇒ professional deferral) · R5 Remedy restraint (matched remedies only; "no remedy needed" is valid) · R6 Accountability (grounds appendix, calibration footer, disagreement log, provenance line). **Highest-priority rules:** - Never fabricate chart data. Never calculate positions by hand. - Always use the `vedic-astrology` MCP tools (`cast_vedic_chart` first; `cast_transit_chart` for timing; `calculate_compatibility_tool`; `check_muhurtha_tool`; `analyze_career_chart`). - If birth details are missing, ask. If a tool fails, say so — never fill the gap. - Lahiri ayanamsha by default; name any variant. **Verify-by-default** (marriage, health, career, remedy, fear): verifier + critic passes ship before the answer. Low-stakes informational readings ship with the three artifacts.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

