Christoffer Niska cniska

How I use AI

Why I'm writing this

AI is now part of how I write code every day, and the workflow I run has evolved into something specific enough to be worth describing. This post is the snapshot: how I work, what I've learned along the way, and the reasoning behind building my own coding agent.

How I work

I run Claude Code in the terminal almost every day at work — and Codex too, though less often. AI does the implementation, I direct and verify. The goal is to automate as much of my workflow as possible and partner with AI on the rest, so I can focus on building things instead of repeating the routine parts of the job.

name	handoff
description	Summarize the session and reset context to save costs. Use when the context is getting long or before switching focus.

Handoff

Summarize what matters, clear the noise, and continue without paying for stale tokens.

Workflow

Coding Agent Landscape

Updated April 2026

Open Source

Agent	Category	Lang	Notes
Acolyte	Terminal agent	TS	Local-first, lifecycle-driven, observable
Codex	Terminal agent	Rust	OpenAI's agent, sandbox execution

name	plan
description	Design a feature or behavior change through dialogue. Use when asked to plan, scope, design, or break down work before coding.

Plan

Design a feature or behavior change through dialogue. The plan emerges from the conversation, not in isolation.

If an issue number is given, fetch it with gh issue view $ARGUMENTS and use it as the starting point.

Acolyte Benchmarks

Measured comparisons of Acolyte against prominent open-source AI coding agents. All metrics are from source code analysis — no opinions, just counts.

Metrics extracted with benchmark.sh

Projects Compared

Setting Up Codex

Prerequisites

Codex installed
Recommended: install Codex via Homebrew for easy updates
GitHub CLI authenticated (gh auth login)
Copy config.toml to ~/.codex/config.toml

Quick Start

Setting Up Claude Code

Prerequisites

Claude Code installed
Recommended: install Codex via Homebrew for easy updates
GitHub CLI authenticated (gh auth login)
Copy settings.json to ~/.claude/settings.json

	import { type EffectCallback, useEffect, useRef } from "react";

	/**
	* Run an effect exactly once on mount. This is the only sanctioned way to
	* call `useEffect` in chat-layer code — prefer derived state, event handlers,
	* or render-time adjustments for everything else.
	*/
	export function useMountEffect(effect: EffectCallback): void {
	const effectRef = useRef(effect);
	effectRef.current = effect;

	#!/usr/bin/env bash
	set -euo pipefail

	# Validate a commit message against project conventions.
	# Usage: check-commit-message.sh <subject> [body]
	#
	# Rules:
	# - Conventional Commit format: type(scope): description
	# - Allowed types: feat, fix, refactor, docs, test, chore
	# - Single-line subject, no body

	import {
	OpenAPIRegistry,
	OpenApiGeneratorV3,
	RouteConfig,
	ZodRequestBody,
	extendZodWithOpenApi,
	} from '@asteasolutions/zod-to-openapi';
	import { OpenAPIObjectConfig } from '@asteasolutions/zod-to-openapi/dist/v3.0/openapi-generator';
	import { Application, NextFunction, Request, RequestHandler, Response, Router } from 'express';
	import fs from 'node:fs/promises';