history-hygiene

Record final decision outcomes to history.md and update on reversals.

7|Updated Oct 24, 2020
One-click install
npx skills add https://github.com/snow-jallen/HomeSpeaker --skill history-hygiene-snow-jallen
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: history-hygiene
Source: https://github.com/snow-jallen/HomeSpeaker/tree/main/.copilot/skills/history-hygiene
Command: npx skills add https://github.com/snow-jallen/HomeSpeaker --skill history-hygiene-snow-jallen

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

History files (.md files tracking decisions, spawns, outcomes) are read cold by future agents. Stale or incorrect entries poison decision-making downstream. The Kobayashi incident proved this: history said "Brady decided v0.6.0" when Brady had reversed that to v0.8.17. Future spawns read the wrong truth and repeated the mistake.

Core Features & Use Cases

  • Record the final outcome to history.md to ensure a single source of truth for decisions.
  • Update the history immediately when a decision reverses to reflect the actual result.
  • Use this in team projects to prevent stale entries from guiding future actions.

Quick Start

Log the final outcome to history.md immediately after a decision is settled.

Frequently Asked Questions about history-hygiene

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I prevent stale decision logs from misguiding future agents in team collaboration?

Log only final outcomes to history.md to prevent stale decision logs from misguiding future agents. This maintains a single source of truth by excluding intermediate requests and immediately updating reversed decisions.

What is the best way to track decision history when a previous choice gets reversed?

Immediately update history.md with the actual final result when a decision is reversed. This prevents outdated entries from poisoning downstream decision-making and ensures future spawns read the correct truth.

Why does logging intermediate requests to history files cause problems for downstream spawns?

Logging intermediate requests causes problems because future agents read these entries cold and treat them as truth. Stale or incorrect entries poison downstream decision-making by causing future spawns to repeat reversed decisions.

Can I use history.md to document every step of the decision-making process for my project?

No, you should not use history.md to document every step of the decision-making process. It is designed to record only final outcomes to maintain a single source of truth and avoid confusing future agents with intermediate requests.

When do I need to update decision tracking logs in collaborative documentation?

Update decision tracking logs immediately when a decision reverses to reflect the actual final result. This prevents stale entries in collaborative documentation from guiding future actions and downstream spawns incorrectly.