History Hygiene
Record final outcomes to history.md, not intermediate requests or reversed decisions
Install
npx skills add Azure-Samples/agent-skills-dotnet-demo --skill history-hygienegit clone --depth 1 https://github.com/Azure-Samples/agent-skills-dotnet-demo.git /tmp/agent-skills-dotnet-demo
mkdir -p ~/.claude/skills
cp -r /tmp/agent-skills-dotnet-demo/.squad/templates/skills/history-hygiene ~/.claude/skills/history-hygienePersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
## Context 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. ## Patterns - **Record the final outcome**, not the initial request. - **Wait for confirmation** before writing to history — don't log intermediate states. - **If a decision reverses**, update the entry immediately — don't leave stale data. - **One read = one truth.** A future agent should never need to cross-reference other files to understand what actually happened. ## Examples ✓ **Correct:** - "Migration target: v0.8.17 (initially discussed as v0.6.0, corrected by Brady)" - "Reverted to Node 18 per Brady's explicit request on 2024-01-15" ✗ **Incorrect:** - "Brady directed v0.6.0" (when later reversed) - Recording what was *requested* instead of what *actually happened* - Logging entries before outcome is confirmed ## Anti-Patterns - Writing intermediate or "for now" states to disk - Attributing decisions without confirming final direction - Treating history like a draft — history is the source of truth - Assuming readers will cross-reference or verify; they won't
Details
- Skill name
history-hygiene- Repository
- Azure-Samples/agent-skills-dotnet-demo
- Path
.squad/templates/skills/history-hygiene/SKILL.md- License
- MIT
- Repo updated
- 10 April 2026
FAQ
What does the History Hygiene skill do?
Record final outcomes to history.md, not intermediate requests or reversed decisions
How do I install the History Hygiene skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add Azure-Samples/agent-skills-dotnet-demo --skill history-hygiene. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is History Hygiene popular?
It lives in Azure-Samples/agent-skills-dotnet-demo, which has 45 GitHub stars and 11 forks.
Related skills
Agent Collaboration
45Azure-Samples/agent-skills-dotnet-demo
Standard collaboration patterns for all squad agents — worktree awareness, decisions, cross-agent communication
Agent Conduct
45Azure-Samples/agent-skills-dotnet-demo
Shared hard rules enforced across all squad agents
Architectural Proposals
45Azure-Samples/agent-skills-dotnet-demo
How to write comprehensive architectural proposals that drive alignment before code is written
Humanizer
45Azure-Samples/agent-skills-dotnet-demo
Tone enforcement patterns for external-facing community responses
Executing Plans
33okgrit/done-is-a-claim
Carry an actionable change plan through implementation, checks, review and an evidence-backed report. Use when executing several planned steps or integrating bounded worker returns, within existing authorization.
Init Mode
45Azure-Samples/agent-skills-dotnet-demo
Team initialization flow (Phase 1 proposal + Phase 2 creation)
Browse the most popular Claude skills, all other skills, or write your own with the skills generator.