Skip to content
View eggmasonvalue's full-sized avatar
8 followers · 25 following

Achievements

Achievement: Pull Sharkx3Achievement: Pair Extraordinairex4Achievement: QuickdrawAchievement: YOLO

Achievements

Achievement: Pull Sharkx3Achievement: Pair Extraordinairex4Achievement: QuickdrawAchievement: YOLO

Block or report eggmasonvalue

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.

Content in all repositories owned by your account will be closed.
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
eggmasonvalue/README.md

Building for agents; Clean Context is the new Clean Code

pi-subagent - Aims to be the most LLM-empowering pi subagent - intentionally designed subagent to provide a thin yet capable interface that puts the main agent in control - with human and agent observability, steerability and model policy

antigravity-agents - custom google antigravity main agents that offers nearly the same functionality with up to 55% and 70% fewer tokens in the system prompt and defensive guidelines to compensate for poor run_command tool design for significantly cleaner context through-session

secstack - Doman specific harness for full-stack US-listed company research - custom system prompt, tools and a set of composable skills. 7500+ lines within skills yet very thin surface to the agent and active context footprint due to meticulously followed progressive disclosure

pi-system-prompt-viewer - observe exactly what is in your context in pi with a. provider neutral system prompt and tools b. the full LLM provider-specific payload at any point

jules-autoresearch - agent loop engineering - autoresearch AI agent skill for long-running agent loops delegated to Google Jules coding agent in the cloud

tracky-mcp - agent-first smart body scale companion - an MCP server for tracky(Yolanda/Feelfit) smart body scales with an agent skill to interpret that data

My Pi Setup

Pinned Loading

  1. pi-subagent pi-subagent Public

    Pi extension with a very thin yet capable interface - with human and agent observability, steerability and enforced model and thinking policies

    TypeScript 3 3

  2. pi-setup pi-setup Public

    Pi package distributing maintained extensions, skills, themes, and bootstrap tooling for configuring Pi installations.

    TypeScript 1

  3. antigravity-agents antigravity-agents Public

    Custom Google Antigravity (agy) main agents (better-agy, lean-agy) with 70+% fewer tokens for ~ the same functionality

    PowerShell

  4. secstack secstack Public

    Isolated Pi profile package for bottom-up research on US-listed companies, bundling five research skills, selected Pi resources, and bootstrap tooling.

    Python

  5. jules-autoresearch jules-autoresearch Public

    AI agent skill and orchestration toolkit for iterative research and evaluation loops that delegate execution to Google's Jules coding agent.

    Python

  6. reading-freertos-strategically-course reading-freertos-strategically-course Public

    Published static course teaching software-design concepts through close reading of the FreeRTOS kernel, with lessons, quizzes, and source views.

    C