agentmods.dev

interlateral_agents: Instructions file for Gemini CLI

GEMINI.md

interlateral_agents GEMINI.md is an instructions file for Gemini CLI from dazzaji/interlateral_agents. It costs 439 tokens per session, scanned A, original, Apache-2.0.

A Gemini CLI instruction file for Interlateral Agents, a multi-agent setup where command-line agents communicate through shared transport tools.

In plain words
What is it for?
It is for starting Gemini as an optional peer, following the wake-up protocol, communicating with Claude or Codex, and choosing a fixed model when needed.
Why use it?
It tells Gemini when it may join, how to acknowledge work, and how to send messages without losing input or using the wrong identity.

Instructions file for Gemini CLI

Written for Gemini CLI: the file is GEMINI.md. Also seen: mentions Claude Code; mentions Codex; mentions Gemini CLI.

This is dazzaji/interlateral_agents's own configuration. It tells Gemini CLI how to work on interlateral_agents 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 interlateral_agents configures →

not rated 11repo 10d ago A scan 439 tokens original Apache-2.0
View source ↗ dazzaji/interlateral_agents
Reuse

Borrowing it

Nothing to install: this file belongs to dazzaji/interlateral_agents. 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/dazzaji/interlateral_agents/main/GEMINI.md
Clone the repo
git clone --depth 1 https://github.com/dazzaji/interlateral_agents

Made for: Gemini CLI.

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 interlateral_agents GEMINI.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/dazzaji/interlateral_agents/gemini-md"><img src="https://agentmods.dev/badge/instructions/dazzaji/interlateral_agents/gemini-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 439 This file is loaded in full into every session.
When invoked 439 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 $0.00439 $0.00439
Opus 5.5 $0.00176 $0.00176
Sonnet 5.5 $0.00088 $0.00088
Haiku 4.5 $0.00044 $0.00044

Measured 1mo ago against content hash 6c89491dcb6d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

interlateral_agents GEMINI.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 1mo 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.

GEMINI.md · 61 lines

What it actually says

Gemini CLI Guide

You are Gemini CLI in the Interlateral Agents v0.2.0 repo.

Opt-In Status

Gemini CLI is an optional peer in this repo, not part of the default Claude Code + Codex mesh. Do not join, recruit other Gemini peers, or take a role in routine skills unless Principal Human explicitly requests Gemini or the current assignment names Gemini.

Wake-Up Protocol

  1. Read interlateral_dna/LIVE_COMMS.md.
  2. ACK when asked.
  3. If there is no assignment, stop and wait.

For detailed transport mechanics, use the mesh-comms-core skill.

Communication Rules

  • Use direct tmux injection for live communication.
  • interlateral_dna/comms.md is only the ledger.

Send to Claude:

node interlateral_dna/cc.js send "message"

Send to Codex:

node interlateral_dna/codex.js send "message"

Important Input Buffer Rule

Gemini needs a 1-second delay between prompt injection and Enter. Use the provided helpers:

  • node interlateral_dna/gemini.js send
  • scripts/launch-gemini-peer.sh

Do not use raw tmux send-keys for Gemini prompts unless you recreate that delay.

Model Pinning

If you need deterministic Gemini behavior across sessions, pin the model explicitly in your Gemini CLI configuration or environment. This repo does not hardcode a model in the launcher, but a current Gemini Pro-class model is the intended default.

Skills

  • Canonical source: .agent/skills/
  • Read the requested SKILL.md directly
  • Some heavier skills refer to deferred roadmap systems; keep work inside the current starter scope unless explicitly told otherwise

Scope

This repo is the CLI-first starter scope only. The default mesh remains Claude Code + Codex. Antigravity CLI and the Antigravity desktop CDP helper are approved opt-in integrations, not default Gemini responsibilities. No courier, dashboard, or product/platform code.

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. 1mo ago First seen · 61 lines · 439 tokens per session scan A 6c89491dcb6d

Subscribe to this mod's changes

interlateral_agents GEMINI.md is an instructions file published in the GitHub repository dazzaji/interlateral_agents (11 stars, last pushed 10d ago), licensed Apache-2.0. It adds 439 tokens to every session, about $0.0018 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 2026-10-03.

Building agents
Related

interlateral_agents GEMINI.md compared with instructions from other repositories

interlateral_agents GEMINI.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
interlateral_agents GEMINI.mddazzaji/interlateral_agentsInstructions file1110d agoApache-2.0A439Gemini CLI
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode