You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Draft for review: Maintaining wait-on at agent speed (AI, npm supply-chain risk, and a Rust engine)
title
Maintaining wait-on at agent speed: AI, npm supply-chain risk, and a Rust engine
date
2026-10-02
author
Kevin Old
tags
wait-on
open-source
ai-agents
compound-engineering
overdrive
npm
supply-chain
rust
Maintaining wait-on at agent speed: AI, npm supply-chain risk, and a Rust engine
I recently joined Jeff Barczewski, who created wait-on in 2015, as a maintainer of the project. Jeff and I met in the food line at JSConf US in 2013 and have been friends ever since. We've spoken at and attended as many tech conferences together as we can, at least one a year. Working on Jeff's project together is a new chapter of that.
Setting the model for nicknisi/consultant's gpt5-server MCP
Setting the model for nicknisi/consultant's gpt5-server MCP
The gpt5-server MCP in the nicknisi/consultant plugin does not read a model from an environment variable. It accepts model as a per-call argument, with 'gpt-5' hardcoded as the Zod default and the || fallback in callGPT5.
So you set it one of three ways.
1. Per call (cleanest)
Pass model in the tool args when invoking it directly:
overnight-ce.sh — Queue GitHub issues, run each through /slfg overnight. Review PRs over morning coffee.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Claude Code + Compound Engineering GitHub Actions — Label-driven CI agent for automated issue triage, planning, fixing, and resolution
Claude Code GitHub Actions — Label-Driven CI Agent
A set of GitHub Actions workflows that use claude-code-action enhanced with the Compound Engineering plugin to automate issue triage, planning, fixing, and end-to-end resolution — all driven by GitHub issue labels.
Why Compound Engineering?
These workflows go beyond basic Claude Code Action by integrating the Compound Engineering plugin — a set of slash commands that give Claude structured, battle-tested workflows for planning and implementation:
Output from successful run of testCompanyNameValidatorAgent.ts
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
content: '{"score":100,"reason":"Apple is a well-known and established technology company famous for its products like the iPhone, MacBook, and Apple Watch. It is widely recognized globally, making it undoubtedly a real company."}',
refusal: null,
tool_calls: [],
parsed: {
score: 100,
reason: 'Apple is a well-known and established technology company famous for its products like the iPhone, MacBook, and Apple Watch. It is widely recognized globally, making it undoubtedly a real company.'
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This script fetches the current open tabs in all Safari windows. Useful to run remotely on your mac when you are at work and want to read a page you have open (remotely) at home but don't remember the url but can log in to your home system on the command line
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Instructions for surgically removing non-existent resource from local Amplify project
Let's say we've removed a Lambda Layer from the Lambda Console and are no longer able to perform operations using the Amplify CLI.
An error occurred fetching the latest layer version metadata for ""
> amplify remove function
? Choose the resource you would want to remove 10263layer58c94806 (layer)
When you delete a layer version, you can no longer configure functions to use it.
However, any function that already uses the layer version continues to have access to it.
✖ Loading layer data from the cloud...