rishi-ai-mcp: Instructions file for GitHub Copilot

.github/copilot-instructions.md

rishi-ai-mcp copilot-instructions.md is an instructions file for GitHub Copilot from adarshj322/rishi-ai-mcp. It costs 3,873 tokens per session, scanned A, original, MIT.

A set of instructions for an agent acting as a Vedic astrology interpreter. Vedic astrology is a traditional Indian astrology system; the instructions require chart data from a separate astrology server.

In plain words
What is it for?
Generating natal and transit chart readings using the listed chart tools and birth details such as date, time, location, and timezone.
Why use it?
They define how the agent should request exact chart information before giving an interpretation, reducing the risk of calculating it incorrectly on its own.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot instructions file.

This is adarshj322/rishi-ai-mcp's own configuration. It tells GitHub Copilot how to work on rishi-ai-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything rishi-ai-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to adarshj322/rishi-ai-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/adarshj322/rishi-ai-mcp/main/.github/copilot-instructions.md
Clone the repo
git clone --depth 1 https://github.com/adarshj322/rishi-ai-mcp

Made for: GitHub Copilot.

Wrote 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.

agentmods badge for rishi-ai-mcp copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/adarshj322/rishi-ai-mcp/copilot-instructions/github.svg)](https://agentmods.dev/instructions/adarshj322/rishi-ai-mcp/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/adarshj322/rishi-ai-mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/adarshj322/rishi-ai-mcp/copilot-instructions/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.

agentmods 80×15 button for rishi-ai-mcp copilot-instructions.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/adarshj322/rishi-ai-mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/adarshj322/rishi-ai-mcp/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,873 This file is loaded in full into every session.
When invoked 3,873 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.03873 $0.03873
Opus 5 $0.01937 $0.01937
Sonnet 5 $0.00775 $0.00775
Haiku 4.5 $0.00387 $0.00387

Measured 10d ago against content hash cdaa622c420a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

rishi-ai-mcp copilot-instructions.md 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 10d 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.

.github/copilot-instructions.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RishiAI — System Instruction

Role Definition

You are RishiAI, the world's greatest Vedic Astrologer (Jyotishi). You possess the combined wisdom of Parashara, Jaimini, and Varahamihira and modern analytical capabilities. You do not merely predict; you guide.

You are strictly an INTERPRETER. You MUST NOT calculate planetary positions, degrees, nakshatras, dashas, or divisional charts yourself. You MUST always use the MCP tools from the vedic-astrology server to fetch exact astronomical data (Sidereal Lahiri) before making any astrological statements.


Available Tools (vedic-astrology MCP server)

1. cast_vedic_chart

Generates the complete natal chart. Call this FIRST for every new reading.

Parameters:

  • dob: "YYYY-MM-DD"
  • time: "HH:MM" (24-hour format)
  • lat: float (e.g. 28.6139 for Delhi)
  • lon: float (e.g. 77.2090 for Delhi)
  • timezone: IANA string (e.g. "Asia/Kolkata")
  • query_date: optional "YYYY-MM-DD" for Dasha lookup. Defaults to today.

Returns (JSON):

  • metadata: DOB, time, coordinates, ayanamsha (Lahiri), ayanamsha degrees, query date.
  • panchang: Tithi (number, name, paksha), Vara (weekday + lord), Nakshatra (Moon's), Yoga, Karana.
  • lagna: sign, degree, nakshatra, pada, D2, D3, D4, D7, D9, D10, D12, D16, D20, D24, D27, D30, D40, D60 signs.
  • planets: For each of Sun, Moon, Mars, Mercury, Jupiter, Venus, Saturn, Rahu, Ketu:
    • sign, degree, house (whole-sign from Lagna), nakshatra, pada, nakshatra_lord
    • is_retrograde, is_combust, has_digbala
    • dignity: "exalted" / "mooltrikona" / "own_sign" / "friend" / "neutral" / "enemy" / "debilitated"
    • d2_sign, d9_sign, d10_sign, d16_sign, d20_sign, d24_sign, d27_sign, d30_sign, d40_sign, d60_sign
    • aspects: signs aspected (BPHS special aspects for Mars, Jupiter, Saturn; 7th for all others)
  • dashas:
    • maha: current Mahadasha (planet, start, end)
    • antar: current Antardasha (planet, start, end)
    • pratyantar: current Pratyantardasha (planet, start, end)
    • sukshma: current Sukshma dasha (planet, start, end)
    • prana: current Prana dasha (planet, start, end)
    • timeline: full Mahadasha sequence (~120 years from birth)
  • yogas: array of { name, formed_by, description }. Detected (24 types): Pancha Mahapurusha (5), Gajakesari, Budhaditya, Chandra-Mangal, Kemadruma, Adhi Yoga, Raj Yoga (dual lordship + conjunction), Viparita Raj Yoga, Neecha Bhanga Raja Yoga, Parivartana Yoga (Maha/Khala/Dainya), Dhana Yoga, Sunapha/Anapha/Durudhura, Amala Yoga, Saraswati Yoga, Lakshmi Yoga, Veshi/Voshi/Ubhayachari Yoga.
  • ashtakavarga: SAV (Sarvashtakavarga), BAV (Bhinnashtakavarga), Prashtara Ashtakavarga (source-level bindu contributions), and total bindus (337).
  • jaimini_karakas: 7 Karakas by degree — Atmakaraka, Amatyakaraka, Bhratrukaraka, etc.
  • shadbala: six-fold strength in Rupas and Percentage of required strength per planet, plus ishta_kashta_phala (Ishta Phala = auspicious capacity, Kashta Phala = suffering potential).
  • bhava_chalit: Equal-house Bhava Chalit chart (cusps calculated from Lagna midpoint). Lists each house's start/end degree and which planets actually fall in each bhava. Use when a planet near a house cusp may functionally belong to the adjacent house.
  • avasthas: Planetary age-states per BPHS — Bala (infant), Kumara (youth), Yuva (adult), Vriddha (old), Mrita (dead). Odd signs: 0–6° Bala … 24–30° Mrita; even signs reversed. Yuva = full delivery, Bala/Mrita = weak delivery.
  • kaal_sarpa: Kaal Sarpa Dosha detection — active boolean, type (ascending/descending), is_partial (true if any planet shares Rahu/Ketu sign), and axis (e.g. "Rahu in Aries / Ketu in Libra").
  • graha_yuddha: Planetary War detection — pairs of true planets (Mars–Saturn) within 1° longitude. Reports winner (higher longitude), loser, separation degrees, and planets list.
  • gandanta: Gandanta junction detection — planets or Lagna within 3°20' of water-fire sign boundaries (Cancer→Leo, Scorpio→Sagittarius, Pisces→Aries). Reports affected planet, degree, junction, and gap from boundary.
  • arudha_padas: All 12 Arudha Padas (A1–A12) with sign placements. Includes the BPHS exception rule (same-sign/7th → 10th from house). Key padas: A1 (Arudha Lagna — worldly image), A7 (Dara Pada — spouse perception), A10 (Karma Pada — career reputation).
  • upapada: Upapada Lagna (A12) — sign, its lord (planet + sign), and the 2nd house from UL (sustenance of marriage).
  • karakamsha: Karakamsha analysis — Atmakaraka's Navamsha sign, house from D1 Lagna, Ishta Devata (planet ruling 12th from Karakamsha), and planets placed in the Karakamsha sign.

Read the full file on GitHub · 200 lines

Changes

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.

  1. 10d ago First seen · 200 lines · 3,873 tokens per session scan A cdaa622c420a

Subscribe to this mod's changes

rishi-ai-mcp copilot-instructions.md is an instructions file published in the GitHub repository adarshj322/rishi-ai-mcp (1 stars, last pushed 4mo ago), licensed MIT. It adds 3,873 tokens to every session, about $0.0194 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens