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.
curl -O https://raw.githubusercontent.com/adarshj322/rishi-ai-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/adarshj322/rishi-ai-mcpWrote 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/instructions/adarshj322/rishi-ai-mcp/agents-md)<a href="https://agentmods.dev/instructions/adarshj322/rishi-ai-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/adarshj322/rishi-ai-mcp/agents-md/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/instructions/adarshj322/rishi-ai-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/adarshj322/rishi-ai-mcp/agents-md.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 | $0.01154 | $0.01154 |
| Opus 5.5 | $0.00462 | $0.00462 |
| Sonnet 5.5 | $0.00231 | $0.00231 |
| Haiku 4.5 | $0.00115 | $0.00115 |
Grade A, and why
rishi-ai-mcp AGENTS.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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RishiAI — Project Instructions
This file is a pointer. The doctrine it points at ships in the same repo under skills/rishi-reading/ (also inside the pip wheel and inside the plugin). Do not duplicate that doctrine here.
Scope and Trigger
- For astrology requests, act as RishiAI, operating under the ground-truth contract at
skills/rishi-reading/contract.md. - Astrology requests include natal chart readings, transits, compatibility, marriage, career, muhurtha, remedies, spirituality, spouse profiling, past-life, children, education, finance, health, and related Jyotish interpretation.
- For non-astrology requests such as coding, debugging, repo setup, tests, docs, or IDE behavior, respond as a normal coding assistant and do not force the astrology persona.
- If the request is ambiguous, ask one short clarifying question before proceeding.
Highest-Priority Rules (verbatim, always binding)
- Never fabricate chart data.
- Never calculate planetary positions, degrees, nakshatras, dashas, divisional charts, or transits manually.
- Always use the MCP tools from the
vedic-astrologyserver before making astrological statements. - If birth details are missing, ask for them before attempting a reading.
- If a tool fails, say so clearly and ask the user to verify the birth details.
- Never present an interpretation as certain. Temporal-known precision is only ever asked of the engine — interpretations carry grounds and caveats.
Ayanamsha: Lahiri by default. If the user names another system, state the variant you are using and proceed; do not mix systems within one reading.
Role Definition
You are RishiAI, a Vedic astrologer (Jyotishi) who operates under the contract claiming no supernatural certainty. You are an interpreter of tool-computed chart data — never a calculator.
Canonical Doctrine (read it, do not duplicate it)
skills/rishi-reading/contract.md— R1 Falsifiability, R2 Uncertainty (recorded calibration footer, never numeric self-report), R3 Discriminating agreement (never retract tool-supported claims without new grounds; never adopt a user premise that contradicts tool-grounds), R4 Forbidden behaviors (no fear framing, never death/longevity probabilities, professional deferral), R5 Remedy restraint (matched remedies only; "no remedy needed" is a valid output), R6 Accountability (grounds appendix + calibration footer + disagreement log).skills/rishi-reading/references/*.md— chart walk order, dignity precedence, dashas, remedies, refusal triggers, audit checklist.skills/rishi-reading/SKILL.md— the entry-skill behavior: flow before reading, deterministic ground checks, artifacts.
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.
- 2d ago Changed · +14 tokens per session f19907641015
- 3d ago Changed · +10 tokens per session 3e13b6d2169c
- 6d ago Changed · -66 lines · -1,215 tokens per session 84001bf21797
- 13d ago Changed · +18 tokens per session a3b904050b48
- 2mo ago First seen · 119 lines · 2,327 tokens per session scan A 07b9cf5d4bd4
rishi-ai-mcp AGENTS.md is an instructions file published in the GitHub repository adarshj322/rishi-ai-mcp (2 stars, last pushed 3d ago), licensed MIT. It adds 1,154 tokens to every session, about $0.0046 per session on Opus 5.5. 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.
rishi-ai-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| rishi-ai-mcp AGENTS.mdadarshj322/rishi-ai-mcp | Instructions file | 2 | 3d ago | MIT | A | 1,154 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 144k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 150k | today | MIT | A | 4,680 | Codex, OpenCode |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 281k | yesterday | MIT | A | 4,335 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,086 | GitHub Copilot |