What is core GEMINI.md?

Project instructions for kondukt, a TypeScript tool for testing, validating, debugging, and scaffolding MCP servers. MCP is a standard way for AI clients to connect to tools and data.

Use them to build, develop, test, lint, type-check, and understand the key files of the kondukt project.

They give an agent the project structure, commands, runtime requirements, and validation steps needed to work consistently in the repository.

core GEMINI.md — Instructions file by kondukt-dev

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/kondukt-dev/core/gemini-md

Clone the repo

git clone --depth 1 https://github.com/kondukt-dev/core

Made for: Gemini CLI.

Per session 499 This file is loaded in full into every session.

When invoked 499 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin 92% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5	$0.00499	$0.00499
Opus 5	$0.00249	$0.00249
Sonnet 5	$0.00100	$0.00100
Haiku 4.5	$0.00050	$0.00050

Measured 2d ago against content hash 151c97bf719a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

core 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 2d 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.

Origin

This is a copy

92% identical to core AGENTS.md — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

GEMINI.md · 59 lines

What it actually says

kondukt

MCP DevTools — test, validate, debug, and scaffold MCP servers for Claude Code, Codex, Gemini CLI, and any MCP client.

Context file for Gemini CLI — auto-generated by Kondukt.

Project overview

Language: TypeScript (ESM)
Runtime: Node.js >=20
Package manager: pnpm
Test framework: Vitest

Commands

pnpm build — Build production artifacts
(tsup && node scripts/copy-templates.mjs)
pnpm dev — Start development server / watcher
(tsup --watch)
pnpm test — Run the test suite
(vitest run)
pnpm test:watch — Run tests in watch mode
(vitest)
pnpm test:coverage — Run tests with coverage
(vitest run --coverage)
pnpm lint — Lint the codebase
(eslint . && prettier --check .)
pnpm lint:fix — Lint and auto-fix
(eslint . --fix && prettier --write .)
pnpm typecheck — Type-check the TypeScript sources
(tsc --noEmit)

Architecture

scripts/ — build / maintenance scripts
src/ — source code
tests/ — test suite

Key files

.gitignore
.prettierrc.json — Prettier config
eslint.config.js — ESLint flat config
package.json — package manifest
pnpm-lock.yaml — pnpm lockfile
tsconfig.json — TypeScript config
tsup.config.ts — bundler config
vitest.config.ts — test runner config
README.md — project readme
LICENSE
.github/workflows/ — CI pipelines

Conventions

Test framework: Vitest
Linter: ESLint
Formatter: Prettier
TypeScript strict mode: enabled
Module format: ESM ("type": "module")

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.

2d ago First seen · 59 lines · 499 tokens per session scan A 151c97bf719a

Subscribe to this mod's changes

core GEMINI.md is an instructions file published in the GitHub repository kondukt-dev/core (5 stars, last pushed 4mo ago), licensed MIT. It adds 499 tokens to every session, about $0.0025 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to core AGENTS.md, differing in 2 lines, and is treated as a copy.

Code review Debugging Testing ai claude claude-code cli codex cursor

core GEMINI.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

This is a copy

What it actually says

kondukt

Project overview

Commands

Architecture

Key files

Conventions

What this file has done since we first saw it

Other instructions, from other repositories

awesome-copilot-id AGENTS.md

hiveshare CLAUDE.md

llm-safe-haven CLAUDE.md

kleosrules AGENTS.md

coding-agent-safety-gate AGENTS.md

yapcap CLAUDE.md