bioinformatics-agent-skills AGENTS.md

Integration instructions for scientific AI-agent skills used with tools such as Cursor, Claude Code, Codex, Gemini CLI, and LangChain. They define where skills go and the YAML header each skill file must contain.

In plain words
What is it for?
Use them when adding, packaging, or integrating computational-biology skills with an AI coding agent, including checking skill metadata and choosing the host-specific skill directory.
Why use it?
They help different agent hosts discover the skills consistently and set clear requirements for metadata, security, and sandboxed code execution.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/yulianuzhnenko/bioinformatics-agent-skills/agents-md
Clone the repo
git clone --depth 1 https://github.com/YuliaNuzhnenko/bioinformatics-agent-skills

Made for: Codex, OpenCode.

Per session 307 This file is loaded in full into every session.
When invoked 307 The same file โ€” it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00307 $0.00307
Opus 5 $0.00153 $0.00153
Sonnet 5 $0.00061 $0.00061
Haiku 4.5 $0.00031 $0.00031

Measured yesterday against content hash c729ad0fb98c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bioinformatics-agent-skills AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories โ€” prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency โ€” measured yesterday.

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.

AGENTS.md ยท 39 lines

What it actually says

Agent Integration & Specification Guide ๐Ÿค–

This document provides technical guidance for integrating Bioinformatics & Scientific AI Agent Skills with autonomous coding agents (Cursor, Claude Code, Google Antigravity, OpenAI Codex, Gemini CLI, LangChain).


๐Ÿ“Œ Supported Agent Host Architectures

Agent Host Recommended Skill Directory Configuration Hook
Cursor .cursor/skills/ or .cursorrules Automatic discovery via .cursorrules
Claude Code CLI ~/.agents/skills/ claude --prompt or global config
Google Antigravity .agents/skills/ Agent Tools registry
LangChain / AutoGPT skills/ Custom Tool Loader (scan_skills.py)

๐Ÿงช Skill Frontmatter Specification

Every SKILL.md file MUST conform to the YAML frontmatter schema:

---
name: skill-name-slug
description: Clear, 1-line description of the skill capability.
version: "1.0.0"
metadata:
  author: Yulia Nuzhnenko
  domain: Scientific Domain Name
  frameworks: [Framework1, Framework2]
---

๐Ÿ”’ Security & Sandboxing

Skills execute code within the host agent's environment. Ensure network permissions and local file access are appropriately scoped before running tasks against production datasets.

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. yesterday First seen ยท 39 lines ยท 307 tokens per session scan A c729ad0fb98c

Subscribe to this mod's changes

bioinformatics-agent-skills AGENTS.md is an instructions file published in the GitHub repository YuliaNuzhnenko/bioinformatics-agent-skills (8 stars, last pushed 23d ago), licensed MIT. It adds 307 tokens to every session, about $0.0015 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

scientific-agent-skills AGENTS.md

AGENTS.md instructions for K-Dense-AI/scientific-agent-skills, covering repository guidance, what belongs here, layout, creating a skill and skill title.

K-Dense-AI/scientific-agent-skills ยท 4,326 tokens

scientific-agent-skills CLAUDE.md

Claude Code instructions for K-Dense-AI/scientific-agent-skills: Repository guidance for this project lives in AGENTS.md. Read it and follow it.

K-Dense-AI/scientific-agent-skills ยท 28 tokens

asb-skill-collections CLAUDE.md

Instructions for HolobiomicsLab/asb-skill-collections, covering claude.md โ€” asb metabolomics skills, install (claude code plugin) and use.

HolobiomicsLab/asb-skill-collections ยท 343 tokens

cryocore AGENTS.md

Instructions for BioSymphony/cryocore, covering biosymphony cryocore agent guide, operating rules, ownership boundary, dev commands and key patterns and conventions.

BioSymphony/cryocore ยท 945 tokens

asb-skill-collections copilot-instructions.md

Instructions for HolobiomicsLab/asb-skill-collections: This repository publishes the ASB Metabolomics Skill Collection (collections/metabolomics/v2/): 5,859 evidence-grounded skills over 909 software tools for computational LC-MS/MS metabolomics, each derived from a peer-reviewed method paper.

HolobiomicsLab/asb-skill-collections ยท 379 tokens

structure-factory AGENTS.md

Instructions for BioSymphony/structure-factory, covering biosymphony structure factory agent guide, mission, how to drive a mission, compute available and orchestrators supported.

BioSymphony/structure-factory ยท 1,610 tokens