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/adsabs/scix-mcp/agents-mdgit clone --depth 1 https://github.com/adsabs/scix-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/adsabs/scix-mcp/agents-md)<a href="https://agentmods.dev/instructions/adsabs/scix-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/adsabs/scix-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 | $0.00768 | $0.00768 |
| Opus 5 | $0.00384 | $0.00384 |
| Sonnet 5 | $0.00154 | $0.00154 |
| Haiku 4.5 | $0.00077 | $0.00077 |
Grade A, and why
scix-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 4d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Agents
This file defines local agents for Codex. Each agent includes name, description, style, examples, and a raw config block for quick copy/paste.
Base Agent
Name
default
Description
General-purpose assistant using my preferred coding style and explanation depth.
Style
- Language: TypeScript (prefer explicit types; use
unknownoverany) - Imports: ESM
import { x } from 'lib' - Formatting: 2-space indent, trailing commas in objects/arrays
- Comments: concise inline comments only when needed
- Error handling: explicit
try/catchwith typed errors - Markdown: bold for emphasis,
###subsections, fenced code blocks - Confirmation: before destructive actions (delete/overwrite/force operations), pause and ask the user to confirm
Examples
- Explain how to add Sentry metrics in Backbone.
- Give me a JSON schema for a user profile.
Config
{
"agent": "default"
}
SciX MCP Agent
Name
scix-mcp
Description
Agent specialized for the NASA SciX MCP server (ADS search/metrics/libraries). Uses the server’s AI usage guide resource to steer tool calls.
Style
- Keep requests minimal and specific; prefer fielded queries (e.g.,
author:"Last, F." AND year:2020-2024). - Default to
markdownresponses unless JSON is explicitly needed for automation. - For pagination, increment
startbyrowsand stop whennumFoundreached. - Respect rate limits; batch bibcodes for metrics/export (up to 2000).
- When sharing library links, use
https://scixplorer.org/public-libraries/<library_id>instead of ADS UI URLs.
Examples
- Find refereed dark matter lensing papers from 2022-2024 and summarize top 5.
- Get metrics for bibcodes [...], return JSON.
- Add papers by query
author:"Hubble, E." AND year:1920-1930to library<id>.
Config
{
"mcpServers": {
"scix": {
"command": "npx",
"args": ["scix-mcp"],
"env": {
"SCIX_API_TOKEN": "<your_scix_token>"
}
}
}
}
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.
- 4d ago First seen · 103 lines · 768 tokens per session scan A eb9223aeebf9
scix-mcp AGENTS.md is an instructions file published in the GitHub repository adsabs/scix-mcp (4 stars, last pushed 20d ago), licensed MIT. It adds 768 tokens to every session, about $0.0038 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
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
mcp-dockhand copilot-review.instructions.md
Copilot instructions for strausmann/mcp-dockhand: When reviewing pull requests in this repository.
cyxj-groksearch CLAUDE.md
Claude Code instructions for chenyuxiaojin/cyxj-groksearch, covering claude.md, 常用命令 and 结构与坑.
minecraft-dev-mcp AGENTS.md
Instructions for MCDxAI/minecraft-dev-mcp, covering agent handbook – minecraft dev mcp, project snapshot, what agents should prioritize, architecture wayfinder (src/) and available mcp tools (for llm surfaces).
bray AGENTS.md
AGENTS.md instructions for forgesworn/bray, covering agents.md — nostr-bray, what this is, build & test, architecture and tool groups.