by Flamerix AI · MIT License
Platforms: Linux and Windows 11 tested by us; macOS reported by others. Tested on Claude Code 2.1.257–2.1.317. The binary is not modified (
BUN_OPTIONS=--preload). An update can silently undo it, so see Verify.
Every ~30 seconds, Claude Code re-sends each background agent's full transcript to the model to
Audit this entire codebase for materially useful simplifications in its data structures, state representation, control flow, algorithms, and ownership.
This is an audit-only exercise. Do not edit files, run tests, implement recommendations, commit, or push. Read-only inspection commands are allowed.
You are the coordinator. Continue until the complete codebase has been reviewed and the final audit is validated.
Inspect the repository and inventory every identifiable subsystem.
Reconstructed from Danny Postma's talk How I Built My Own AgentOS on Claude's Agent SDK (So You Can Too) (2026). This document is both a product spec for a human and an implementation prompt for an AI coding agent. Build exactly this system. Do not invent features that are not specified here.
Role contracts and prompts in this file are reconstructed from the talk, not his verbatim files. Mark every reconstructed prompt in code comments and docs as such.
| #!/usr/bin/env bash | |
| # pr-restack — rebuild a working branch by cherry-picking my open PRs | |
| # on top of an upstream base. Relies on git rerere to replay conflict | |
| # resolutions across runs. | |
| # | |
| # Usage: | |
| # pr-restack # from inside any git repo with gh access | |
| # pr-restack -b my-branch # custom branch name | |
| # pr-restack -r upstream/main # custom base ref | |
| # pr-restack -o origin -u upstream # remote names |
name: tufte-viz description: | Ideate and critique data visualizations using Edward Tufte's principles from "The Visual Display of Quantitative Information." Use this skill when: (1) Designing new data visualizations or charts (2) Critiquing or improving existing visualizations (3) Reviewing dashboards or reports for graphical integrity (4) Deciding between visualization approaches (5) Reducing chartjunk or improving data-ink ratio (6) Planning small multiples or high-density displays
| # OpenClaw Implementation Prompts | |
| Each prompt below is a self-contained brief you can hand to an AI coding assistant (or use as a project spec) to build that use case from scratch. Adapt the specific services to whatever you already use — the patterns are what matter. | |
| --- | |
| ## 1) Personal CRM Intelligence | |
| ``` | |
| Build me a personal CRM system that automatically tracks everyone I interact with, with smart filtering so it only adds real people — not newsletters, bots, or cold outreach. |
See the new site: https://postgresisenough.dev
| /* Heap based virtual machine described in section 3.4 of Three Implementation Models for Scheme, Dybvig | |
| */ | |
| #include <stdio.h> | |
| #include <stdlib.h> | |
| #include <string.h> | |
| #include <ctype.h> | |
| #include <assert.h> | |
| char token[128][32]; |
ChatGPT appeared like an explosion on all my social media timelines in early December 2022. While I keep up with machine learning as an industry, I wasn't focused so much on this particular corner, and all the screenshots seemed like they came out of nowhere. What was this model? How did the chat prompting work? What was the context of OpenAI doing this work and collecting my prompts for training data?
I decided to do a quick investigation. Here's all the information I've found so far. I'm aggregating and synthesizing it as I go, so it's currently changing pretty frequently.
