Skip to content
View jscraik's full-sized avatar
6 followers · 18 following

Achievements

Achievement: Pull Sharkx4Achievement: Pair Extraordinairex4Achievement: QuickdrawAchievement: YOLO

Achievements

Achievement: Pull Sharkx4Achievement: Pair Extraordinairex4Achievement: QuickdrawAchievement: YOLO

Highlights

  • Pro

Block or report jscraik

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
jscraik/README.md

Jamie Scott Craik

Grumpy Old Vet, Solo Harness Builder, From Demo to Duty, Codex-first engineering that ships

LinkedIn GitHub followers Twitter Follow

Grumpy Old Vet, Solo Harness Builder

British Army veteran | Founder, brAInwav | Codex-first toolmaker

From Demo to Duty: turning promising AI experiments into repeatable engineering workflows that a real project can trust.

Now (May 11, 2026): building Codex-first CLI tooling, agent instructions, and governance systems for AI-assisted engineering.

By harness, I mean the operating layer around Codex: CLI tools, instructions, validation gates, repo workflows, and review loops that make AI-assisted coding repeatable.

Last updated: 2026-05-11

Philosophy Mode Focus

From Demo To Duty

I build the harness around Codex so AI coding can move from impressive demos to dependable project work:

  • fresh implementation loops
  • CLI research and knowledge tools
  • MCP/server foundations
  • instruction packs and validation gates
  • repo governance that keeps human intent visible

Working Stack

Codex, OpenAI, MCP, TypeScript, Node.js, React, Swift, SwiftUI, Python, Bash, macOS, GitHub Actions, CircleCI, CodeRabbit.

TL;DR

Problem: OSS teams and founders need fast, reliable AI tooling they can trust.

Solution: I build pragmatic Codex-first harnesses: CLIs, instruction systems, validation gates, and governance tools that turn experiments into safe, repeatable workflows.

Why it helps: Clear defaults, fast setup, and tools that scale from solo dev to team.

Featured Work

Project Why it matters Signal
Agent-Skills Codex-first skill catalog for authoring, validating, and syncing AI coding skills across local agent workflows. 4 stars
ralph-gold A Golden Ralph Loop orchestrator for running fresh Codex sessions in a deterministic implementation loop. 2 stars
rSearch Search, fetch, and download arXiv papers from the terminal. CLI plus TypeScript client. active
wSearch Script-friendly Wikidata REST, SPARQL, and Action API queries from the terminal. active
mKit MCP server boilerplate for Cloudflare Workers. 1 star
Design-System Cross-platform UI workbench and component system for ChatGPT widgets and React apps. active

Quick Start (Pick One)

# ralph-gold
gh repo clone jscraik/ralph-gold
cd ralph-gold
uv tool install -e .
ralph --help
# rSearch
npm i -g @brainwav/rsearch
rsearch --help
# wSearch
npm i -g @brainwav/wsearch-cli
wsearch --help

More Projects

  • diagram-cli - A command-line tool for generating static architecture diagrams and enforcing architectural guardrails.
  • trace-narrative - A new way to discover the narrative, share, and collaborate across GIT and agent traces.
  • code-archaeology-kit - Tools and scripts for archeological analysis of codebases, commit history, and development patterns.
  • unfinished-cemetery - A ritualised archive of abandoned projects — post-mortems for software that died so we could learn what lives.

The Search Family

All published under @brainwav on npm:

CLI What it does Install
rSearch arXiv paper search, fetch, download npm i -g @brainwav/rsearch
wSearch Wikidata REST/SPARQL queries npm i -g @brainwav/wsearch-cli

What I'm Doing

  • Current focus - Making ralph-gold, Agent-Skills, and the brainwav CLIs more reliable and production-ready
  • Engineering deterministic AI workflows - Shipping ralph-gold to run fresh Codex sessions in a repeatable loop
  • Publishing practical AI tooling - Maintaining rSearch and wSearch CLIs for research, search, and query workflows
  • Building agent infrastructure - Evolving mKit as a practical MCP/Cloudflare Workers foundation for AI tooling
  • Improving developer operations - Building reusable tooling ecosystems like Agent-Skills, code-archaeology-kit, trace-narrative, and Design-System

Work With Me On

Agentic developer workflows - Codex, MCP, review loops, PR automation, and validation gates

CLI tools - research, knowledge, search, repo automation, and developer UX

AI governance - instructions, drift control, and repeatable workflows that keep human intent visible

Grumpy Old Vet product thinking - turning messy prototypes into dependable tools without losing the human intent

Learning In Public

I keep an archive of retired experiments at unfinished-cemetery: short post-mortems for software that taught something useful before it was retired.

📬 Connect

LinkedIn Twitter Email

Pinned Loading

  1. rSearch rSearch Public

    Search, fetch, and download arXiv papers from the terminal. CLI + programmatic TypeScript client

    JavaScript

  2. wSearch wSearch Public

    Safe, script-friendly CLI for querying Wikidata via REST, SPARQL, and Action API. Read-only by default with encrypted token storage

    TypeScript

  3. Agent-Skills Agent-Skills Public

    Governed Agent Skills Kit repo for Codex: author once, validate quality, expose command handles, and sync routed skills/plugins.

    Python 4 4

  4. ralph-gold ralph-gold Public

    A *Golden Ralph Loop* orchestrator that runs **fresh CLI-agent sessions** (Codex, Claude Code, Copilot) in a deterministic loop until your PRD is complete.

    Python 2 2

  5. code-archaeology-kit code-archaeology-kit Public

    Python

  6. trace-narrative trace-narrative Public

    A new way to discover the narrative, share, and collaborate across GIT and agent traces.

    TypeScript