history-hygiene

Update history.md files to record only confirmed final decision outcomes.

209|27|Updated Mar 10, 2026
One-click install
npx skills add https://github.com/dotnet/maui-labs --skill history-hygiene-dotnet
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: history-hygiene
Source: https://github.com/dotnet/maui-labs/tree/main/src/Comet/.copilot/skills/history-hygiene
Command: npx skills add https://github.com/dotnet/maui-labs --skill history-hygiene-dotnet

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Prevents future agents from acting on stale or incorrect decision records by ensuring only confirmed final outcomes are written to history.md.

Core Features & Use Cases

  • Records final outcomes only to avoid misleading “truth” in cold reads.
  • Prevents stale entries by updating history immediately when a decision is reversed.
  • Enforces confirmation-before-write so intermediate states never become durable facts.
  • Use Case: When a dependency version or implementation choice changes midstream, write the corrected final version as the single authoritative outcome to stop repeated mistakes.

Quick Start

Ask the AI to review the proposed history update and rewrite it to capture only the confirmed final outcome, updating or replacing any reversed decisions.

Frequently Asked Questions about history-hygiene

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

FAQPage Schema
How do I keep decision logs accurate for future agents reading history files cold?

To keep decision logs accurate for cold reads, record only confirmed final outcomes in history.md rather than intermediate requests. This prevents future agents from acting on reversed decisions or stale records.

Why does my agent workflow execute reversed decisions from stale history entries?

Agent workflows execute reversed decisions when history.md contains intermediate states instead of final outcomes. Updating history entries immediately after a reversal ensures downstream spawns rely on a single consistent source of truth.

What is the best way to maintain documentation hygiene when a dependency version changes midstream?

The best way to maintain documentation hygiene during midstream changes is to wait for confirmation, then rewrite the history.md entry to capture the corrected final version as the single authoritative outcome.

How do I update history.md when an implementation choice is reversed midstream?

To update history.md after a reversed implementation choice, ask the AI to review the proposed update and rewrite it immediately to replace the reversed decision with only the confirmed final outcome.

When do I need to enforce confirmation-before-write for decision logs in agent collaboration?

You need to enforce confirmation-before-write for decision logs whenever agent-driven workflows rely on history.md for prior truths, ensuring intermediate states never become durable facts that mislead downstream spawns.

Can I use process discipline to prevent intermediate requests from becoming durable facts in history files?

Yes, applying process discipline prevents intermediate requests from becoming durable facts by requiring confirmation before writing to history.md, ensuring future agents only read confirmed final outcomes.