agentmods.dev

Conduit: Instructions file for Gemini CLI

GEMINI.md

Conduit GEMINI.md is an instructions file for Gemini CLI from nickna/Conduit. It costs 2,488 tokens per session, scanned A, original, MIT.

A repository guide for Gemini CLI, the command-line coding assistant, explaining how to develop the project safely and which commands to use or avoid.

In plain words
What is it for?
Use it when Gemini CLI is working on the Conduit codebase, especially for checking changes, understanding the project structure, and avoiding unsafe WebAdmin or Docker commands.
Why use it?
It helps prevent commands that can damage the development container or require a lengthy restart. It also gives the assistant project-specific build, verification, and collaboration rules.

Instructions file for Gemini CLI

Written for Gemini CLI: the file is GEMINI.md. Also seen: mentions Gemini CLI.

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

not rated 13repo changed 25d ago A scan 2,488 tokens original MIT
View source ↗ nickna/Conduit
Reuse

Borrowing it

Nothing to install: this file belongs to nickna/Conduit. 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/nickna/Conduit/master/GEMINI.md
Clone the repo
git clone --depth 1 https://github.com/nickna/Conduit

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 Conduit GEMINI.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/nickna/conduit/gemini-md"><img src="https://agentmods.dev/badge/instructions/nickna/conduit/gemini-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,488 This file is loaded in full into every session.
When invoked 2,488 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 $0.02488 $0.02488
Opus 5.5 $0.00995 $0.00995
Sonnet 5.5 $0.00498 $0.00498
Haiku 4.5 $0.00249 $0.00249

Measured 25d ago against content hash 492c0d815968, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Conduit 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 25d 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 · 291 lines

How it starts

The opening of the file, as written. The whole thing — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GEMINI.md

This file provides guidance to Gemini Code Assist when working with code in this repository.

Table of Contents

  1. ⚠️ CRITICAL: Safety First
  2. Quick Start Guide
  3. Development Environment
  4. Build & Verification
  5. Code Quality Standards
  6. Architecture Essentials
  7. Documentation Index
  8. Repository & Collaboration

⚠️ CRITICAL: Safety First

Commands That WILL Break Development

❌ FORBIDDEN WEBADMIN COMMANDS

These commands break the development container and force a 5+ minute restart:

  • npm run build (anywhere in WebAdmin directory)
  • cd WebAdmin && npm run build
  • ./scripts/dev/dev-workflow.ps1 build-webadmin (production testing only)

Why? The development container uses an isolated .next directory. Running npm run build on the host corrupts the container's build state.

✅ SAFE WEBADMIN VERIFICATION

Use these commands instead to verify WebAdmin changes:

  • npm run lint - Check ESLint errors
  • npm run type-check - Verify TypeScript types
  • Hot reloading automatically validates code changes as you save files.

❌ FORBIDDEN DEVELOPMENT COMMANDS

  • docker compose up for development (always use ./scripts/dev.ps1)

If you run forbidden commands, you will:

  1. Break the development environment.
  2. Force a restart with --clean (which takes 5+ minutes).
  3. Waste time and ignore explicit instructions.

Quick Start Guide

Starting Development Services

⚠️ CANONICAL DEVELOPMENT STARTUP:

./scripts/dev.ps1

Available Flags

./scripts/dev.ps1              # Standard startup
./scripts/dev.ps1 -WebAdmin    # Rebuild WebAdmin container
./scripts/dev.ps1 -Clean       # Complete reset (removes all volumes)
./scripts/dev.ps1 -Build       # Force rebuild with cache
./scripts/dev.ps1 -Rebuild     # Full rebuild with --no-cache

Read the full file on GitHub · 291 lines

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. 25d ago Changed · +6 lines · +119 tokens per session 492c0d815968
  2. 2mo ago First seen · 285 lines · 2,369 tokens per session scan A 66dbf8fb91e3

Subscribe to this mod's changes

Conduit GEMINI.md is an instructions file published in the GitHub repository nickna/Conduit (13 stars, last pushed 4d ago), licensed MIT. It adds 2,488 tokens to every session, about $0.0100 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 2026-09-04.

Building agentsContainersDevOps and cloudLLMgatewayllm-gatewayopenai-proxy
Related

Conduit GEMINI.md compared with instructions from other repositories

Conduit GEMINI.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
Conduit GEMINI.mdnickna/ConduitInstructions file134d agoMITA2,488Gemini CLI
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, 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