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.
npx agentmods add instructions/davidmosiah/astral-mcp/agents-mdgit clone --depth 1 https://github.com/davidmosiah/astral-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/davidmosiah/astral-mcp/agents-md)<a href="https://agentmods.dev/instructions/davidmosiah/astral-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/davidmosiah/astral-mcp/agents-md.svg" alt="Measured on agentmods" 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 | $0.00433 | $0.00433 |
| Opus 5 | $0.00217 | $0.00217 |
| Sonnet 5 | $0.00087 | $0.00087 |
| Haiku 4.5 | $0.00043 | $0.00043 |
Grade A, and why
astral-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 5d 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
Agent Development Notes
Scope
This repo is astral-mcp — a local-first, precision-audited MCP server that
computes natal charts, transits, synastry and moon phases for AI agents. It is
stateless: no auth, no accounts, no persistence. The astrology engine is ported
from the Alkhemia app and kept framework-free.
Layout
src/engine/— pure computation, ported verbatim from Alkhemia (no MCP, no network exceptgeocoding.ts). Treat as a vendored core; keep it portable.src/schemas/common.ts— zod input/output schemas. Input descriptions are the agent-facing contract; write them for an LLM.src/services/— formatting + the agent-first metadata surfaces.src/tools/astral-tools.ts— tool registration.src/server.ts/src/index.ts— server factory and stdio/http entry.scripts/— node test scripts (smoke, accuracy, metadata).
Commands
- Install:
npm ci - Typecheck:
npm run typecheck - Build:
npm run build - Accuracy gate:
npm run test:accuracy - Full gate:
npm test
Rules
- Keep every tool read-only and stateless. No tokens, no disk writes, no birth data persistence.
- A natal chart must stay precision-audited by default. Don't regress the dual-engine cross-check — it's the project's reason to exist.
- When adding an output field, also add it to the matching output schema:
registerToolrebuildsz.object(shape)and validatesstructuredContentstrictly, so any undeclared top-level key fails at runtime. - Tool descriptions are written for agents: say when to call the tool, what to pass, and what comes back.
- The engine in
src/engine/mirrors Alkhemia. Fix bugs upstream too when they apply to both.
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.
- 5d ago First seen · 42 lines · 433 tokens per session scan A e4902e609880
astral-mcp AGENTS.md is an instructions file published in the GitHub repository davidmosiah/astral-mcp (0 stars, last pushed 4d ago), licensed MIT. It adds 433 tokens to every session, about $0.0022 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.
Other instructions, from other repositories
astrology-ai-chatbot AGENTS.md
AGENTS.md instructions for RoxyAPI/astrology-ai-chatbot, covering agents guide, canonical roxyapi references (use these, do not guess), setup, how data flows and rule: location first, charts second.
auseklis AGENTS.md
AGENTS.md instructions for igmizo/auseklis, covering agents.md, commands, architecture (load-bearing facts), gotchas and testing philosophy.
rishi-ai-mcp copilot-instructions.md
Copilot instructions for adarshj322/rishi-ai-mcp, covering rishiai — system instruction, role definition, available tools (vedic-astrology mcp server), 1. castvedicchart and 2. casttransitchart.
nanami-products CLAUDE.md
Claude Code instructions for haserisa0810-gif/nanami-products, covering claude.md, what this is, running locally, deploy and architecture.
rishi-ai-mcp AGENTS.md
AGENTS.md instructions for adarshj322/rishi-ai-mcp, covering rishiai - project instructions, scope and trigger, highest-priority rules in this file, role definition and available tools (vedic-astrology mcp server).
astro AGENTS.md
AGENTS.md instructions for aryaminus/astro, covering astro — agent integration guide, install, cloud endpoints (render free tier), 18 mcp tools and dev commands.