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/exon-research/genomi/agents-mdgit clone --depth 1 https://github.com/exon-research/genomiWrote 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/exon-research/genomi/agents-md)<a href="https://agentmods.dev/instructions/exon-research/genomi/agents-md"><img src="https://agentmods.dev/badge/instructions/exon-research/genomi/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 | $0.05815 | $0.05815 |
| Opus 5 | $0.02908 | $0.02908 |
| Sonnet 5 | $0.01163 | $0.01163 |
| Haiku 4.5 | $0.00581 | $0.00581 |
Grade A, and why
genomi 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.
How it starts
The opening of the file, as written. The whole thing — 518 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Genomi Development Agent Instructions
This file is for agents developing Genomi itself. It is not host-agent runtime
guidance. Host-facing runtime guidance lives in SKILL.md, focused skill docs,
and Genomi MCP tool metadata.
Genomi Design Principles
Edit this section only with explicit owner approval.
-
Genomi should balance deterministic computation with agent judgment. Tools should structure evidence, not become a bottleneck that prevents the agent from using its reasoning.
-
Tool contracts should carry the architecture. Routing and answer-selection rules belong in schemas, required parameters, tool names, and runtime validation, not mainly in skill Markdown.
-
Tool names must be distinct verbs that say what the tool does. If multiple tools share the same real job, refactor or consolidate them. Do not keep aliases or backward-compatible duplicate names.
-
Candidate-gene evidence must preserve source priors. Drug-target, GWAS, screen, rare-disease, and locus-to-gene evidence can point to different candidates. Do not collapse them into one universal "best" gene.
-
Agent decisions need their evidence everywhere. Any tool surface that presents a candidate, ranking, or answer-shaped result must also present the evidence that led to it. The agent host decides.
-
Progressive disclosure should move from capability to focused tools, without mandatory ceremony. Do not expose the whole toolset at once, but do not force bootstrap and repeated discovery before ordinary evidence work.
-
Internal coherence is not enough. A cleaner tool surface can still reduce answer quality if it makes the wrong evidence prior feel authoritative.
-
Agent-facing documents should not expose Genomi internals. They should describe capabilities, privacy boundaries, and how to use tools, not internal implementation details.
-
Agent-facing surfaces must preserve the Active Genome Index boundary. Raw genome sources and parsed Active Genome Index artifacts are session-scoped. Do not expose or reuse them across chats unless the current session explicitly supplies or approves that context.
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 · 518 lines · 5,815 tokens per session scan A 4a3d7f93752d
genomi AGENTS.md is an instructions file published in the GitHub repository exon-research/genomi (481 stars, last pushed 4d ago), licensed Apache-2.0. It adds 5,815 tokens to every session, about $0.0291 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 2026-08-30.
Other instructions, from other repositories
Sponsio CLAUDE.md
Claude Code instructions for SponsioLabs/Sponsio, covering agent guide for sponsio, what sponsio is, positioning, what to read first and repository map.
holaOS CLAUDE.md
Claude Code instructions for holaboss-ai/holaOS, covering holaos — repo guide and hola — debug the hola (pi) brain from the cli.
nulnul-harness AGENTS.md
AGENTS.md instructions for SeoNaRu/nulnul-harness: This repository builds plugins/nulnul-harness/, a Codex plugin that selects the strongest justified project-local capability system for the requested outcome, verifies the user's work, removes non-contributing setup, and evolves from measured outcomes without…
pixir AGENTS.md
Instructions for Ranvier-Technologies/pixir, covering agents.md - pixir harness, progressive discovery, screaming architecture, beta stance and commands.
pixir CLAUDE.md
Instructions for Ranvier-Technologies/pixir, covering pixir harness - legacy agent guide, current map and commands.
The-Ideal-Harness AGENTS.md
AGENTS.md instructions for bharat3645/The-Ideal-Harness, covering agents.md, read this before you write code, 1. enforce below the model, 2. zero overlap and 3. clean-room.