software by Stafford Williams

blog more

• 2026-01-04 Twelve months of agentic AI code-assist
• 2025-12-29 Steering the Vibe: Refactor
• 2025-12-21 Porting Jekyll to Astro with Claude Code
• 2025-12-14 Steering the Vibe: Verify
• 2025-12-07 Steering the Vibe: Commits
• 2025-06-04 AI Code Assistance: Are we talking about the same thing?
• 2025-03-16 Embrace Vibe Coding, Know Its Limits
• 2025-03-09 You Might Not Need an AI Framework
• 2025-03-03 Understanding AI-assisted Coding Workflows
• 2025-01-29 Running DeepSeek R1 Locally
• 2025-01-12 LLM Agent Assisted Coding
• 2024-10-14 Comparing Netlify and Azure Static Web Apps
• 2024-04-16 Evaluating ngrok
• 2024-03-09 Getting Started Programming Spaceships

links more

GitHub to start charging $0.002/min for self-hosted runners, potentially to combat competitors with cheaper/faster (self-hosted) approaches:

• Depot
• Blacksmith
• WarpBuild

github, moat • 2025-12-17 • 10:16am

If I did read this in 2012 when it was leaked then I’ve completely forgotten. Valve’s (2012) Employee Handbook includes a section on stack ranking.

ways-of-working • 2025-12-10 • 1:29pm

knip discovers typescript files that are present but not referenced. I find this handy during code-assist so the agent can clean up stuff it doesn’t need anymore.

code-assist, types • 2025-11-12 • 8:27pm

Some really basic tables that help illustrate the benefit of reducing work in progress.

ways-of-working • 2025-11-05 • 5:58pm

If you had to access RavenDb 3.5 over REST API and were pondering how to so using a supplied api key and oauth, then this page is very helpful indeed.

ravendb • 2025-10-27 • 2:15pm

Effective context engineering for AI agents

good context engineering means finding the smallest possible set of high-signal tokens that maximize the likelihood of some desired outcome

ai, anthropic, prompting • 2025-10-01 • 10:45pm

Anthropic releases Claude Sonnet 4.5 claiming it’s

the best coding model in the world.

API price remains the same as earlier versions at

$3/$15 per million tokens.

Also, ccusage deprecates blocks --live as the official way to track claude usage is via claude.ai/settings/usage.

ai, claude, anthropic, model • 2025-09-30 • 7:45am

Every team is at a different stage of collaboration and so it’s difficult to find a team charter template that fits all teams - I like this atlassian one even if just for the Team Preferences and Communication Channels sections.

ways-of-working, collaboration • 2025-09-26 • 11:14am

Microsoft announces auto-model selection for VS Code that prioritizes Claude Sonnet 4 over GPT-5 for paid users

ai, code-assist, microsoft, vscode, anthropic, moat • 2025-09-18 • 7:25pm

notes more

• 2025-12-15 [netsh, iisexpress, wsl] excluding ports from hyper-v
• 2025-03-29 [ssl] mac keychain
• 2025-03-03 [javascript, timezones, vitest] timezones
• 2025-01-14 [bookmarklet, chrome] add text to clipboard
• 2024-12-11 [javascript, timezones] datetime libraries
• 2024-05-01 [mikro-orm] type annotations
• 2024-03-13 [azure-b2c] limits
• 2024-03-11 [azure-b2c] phone mfa - microsoft samples
• 2024-03-06 [http] testing

devlog more

• 2026-01-04 [assist] v0.10.1 - Devlog command refinements
• 2026-01-04 [blog] v4.3 - Project info and link syntax
• 2026-01-02 [procgen] v0.1 - Low-poly ocean scene with React Three Fiber
• 2026-01-02 [assist] v0.10 - New project scaffolding commands
• 2026-01-01 [puzbox] v0.6 - Menu and level navigation +3 ▸
  • 2025-12-31 v0.5 - Four new puzzles, analytics, and widget polish
  • 2025-12-30 v0.4 - Three new puzzles and Playwright testing
  • 2025-12-29 v0.3 - Puzzle08 with hinged box
• 2025-12-29 [assist] v0.9 - Major refactoring and filename conventions
• 2025-12-28 [puzbox] v0.2 - Puzzle07 and interaction fixes
• 2025-12-28 [assist] v0.8 - Refactor check now runs verify scripts
• 2025-12-28 [blog] v4.2 - Blog post series navigation