auseklis: Instructions file for Codex

AGENTS.md

auseklis AGENTS.md is an instructions file for Codex, OpenCode from igmizo/auseklis. It costs 534 tokens per session, scanned A, original, MIT.

Project instructions for Auseklis, an astrology MCP server written in TypeScript with command-line and Cloudflare Worker transports. They document its architecture, tests, build commands, and rules for astronomy calculations and server versions.

In plain words
What is it for?
Building, testing, and running the astrology server locally or on Cloudflare, changing its MCP tools, and maintaining its astronomy backend and version metadata.
Why use it?
They record design decisions that must remain consistent across both ways of running the server. They also highlight testing and version-matching requirements that prevent broken releases.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is igmizo/auseklis's own configuration. It tells Codex and OpenCode how to work on auseklis 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 auseklis configures →

Reuse

Borrowing it

Nothing to install: this file belongs to igmizo/auseklis. 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/igmizo/auseklis/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/igmizo/auseklis

Made for: Codex, OpenCode.

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 auseklis AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/igmizo/auseklis/agents-md/github.svg)](https://agentmods.dev/instructions/igmizo/auseklis/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/igmizo/auseklis/agents-md"><img src="https://agentmods.dev/badge/instructions/igmizo/auseklis/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.

agentmods 80×15 button for auseklis AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/igmizo/auseklis/agents-md"><img src="https://agentmods.dev/badge/instructions/igmizo/auseklis/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 534 This file is loaded in full into every session.
When invoked 534 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 $0.00534 $0.00534
Opus 5.5 $0.00214 $0.00214
Sonnet 5.5 $0.00107 $0.00107
Haiku 4.5 $0.00053 $0.00053

Measured 2mo ago against content hash 543cdd97ede3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

auseklis 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 2mo 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

AGENTS.md · 30 lines

What it actually says

AGENTS.md

Astrology MCP server. TypeScript ESM, official MCP SDK, dual transport (stdio bin + Cloudflare Worker).

Commands

  • npm run typecheck — strict TS, no emit
  • npm test — 20-check smoke suite (esbuild-bundles test/smoke.ts, runs on Node)
  • npm run build — tsc -p tsconfig.build.json → dist/
  • npm run dev — wrangler dev server on :8787
  • node dist/stdio.js — run the built stdio server

Architecture (load-bearing facts)

  • src/ephemeris/engine.ts defines EphemerisBackend — the ONLY place astronomy-engine may be imported for runtime use. Everything else derives from its primitives so the backend can be swapped (planned Rust/WASM v1).
  • src/mcp/server.ts exports createServer(); both entries (src/stdio.ts, src/index.ts) attach transports to it. The Worker creates a fresh server per request (stateless).
  • Tool pattern: Zod raw-shape inputSchema + outputSchema, READONLY annotations, handlers wrap pure functions in run() from src/mcp/schemas.ts (errors → isError text).
  • SERVER_VERSION in src/mcp/server.ts must match package.json, server.json, manifest.json.

Gotchas

  • astronomy-engine's Ecliptic() ALREADY rotates EQJ→ecliptic-of-date. Never pre-rotate with Rotation_EQJ_ECT — that double-rotates (~50″/yr drift; was a real 0.1.0 bug).
  • astronomy-engine ships broken ESM packaging; engine.ts imports it via namespace + default-interop fallback. Don't "simplify" to named imports — plain Node ESM breaks.
  • Timezone conversion (src/ephemeris/time.ts) uses Intl only — no tz dependency. Works on Node and Workers.
  • LICENSING: never add sweph/swisseph deps or .se1/.se2 files (AGPL contamination — see NOTICE).

Testing philosophy

Reference facts over shape checks: published eclipse dates, the 2026 equinox, NOVAS SunPosition agreement, an independent Placidus fixture (CircularNatalHoroscopeJS, LA 2019-07-20 17:10Z). When adding astronomy, find an external anchor.

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. 2mo ago First seen · 30 lines · 534 tokens per session scan A 543cdd97ede3

Subscribe to this mod's changes

auseklis AGENTS.md is an instructions file published in the GitHub repository igmizo/auseklis (1 stars, last pushed 3mo ago), licensed MIT. It adds 534 tokens to every session, about $0.0021 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.

Related

auseklis AGENTS.md compared with instructions from other repositories

auseklis AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
auseklis AGENTS.mdigmizo/auseklisInstructions file13mo agoMITA534Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode