Refresh History Skills — Git skill for Claude Code
Re-verify all three agent-history skills against the currently-installed CLIs and real local history, then open one PR.
How to install Refresh History Skills
Installs to ~/.claude/commands/jlreyes-agent-history-skills-refresh-history-skills.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/jlreyes/agent-history-skills/HEAD/.claude/commands/refresh-history-skills.md -o ~/.claude/commands/jlreyes-agent-history-skills-refresh-history-skills.md Restart Claude Code, or start a new session, for it to be picked up.
What Refresh History Skills does
description: Re-verify all three agent-history skills against the currently-installed CLIs and real local history, then open one PR. allowed-tools: Read, Edit, Write, Bash, WebFetch, WebSearch, Agent
Refresh the agent-history skills
This repo documents where three coding agents store local conversation history and how to read it. Each skill is a `SKILL.md` (recipes + quick reference) and a `data-model.md` (full schema, verified against a specific CLI version and date), plus a `refere
Alternatives in Git
- OSS PR — Commit + PR workflow for open source contributions: auto-creates a user-prefixed branch when on main/master, t 19.7k ★
- CodeReview — Review local code changes against base branch 512 ★
- Drive Acquisition — Work GitHub issues that drive acquisition — verify relevance, close stale ones, fan out at most two engineer a 324 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Local Custom Loop
A review command you define, on this machine — branch, verify, commit, review, fix findings, then push and ope
Local Review Loop
Claude Code's /code-review on this machine — branch, verify, commit, review, fix findings, then push and open
Epic Plan
Plan a new epic against a real codebase and a real project board, then — only after explicit approval — create
Consolidate Issues
Review every open issue against git history, close what's already done or stale, migrate the legacy ones, slim
Tldr Update
Update TLDR from GitHub and refresh installed agent hooks/skills/rules
Agent Intern
MCP bridge that drives four coding CLIs — Google's Antigravity (agy), OpenAI Codex, GitHub Copilot, and Cursor
Related Agents
Codex Debugger
Root-cause a failing test, crash, stack trace, or misbehaving feature by delegating the investigation to OpenA
Webtester
Use this agent to verify that a web app actually works end-to-end in a real browser, driven by Playwright agai
Brand Voice Reviewer
Checks a draft (listing, buyer reply, social post) against the shop's real, currently published voice and hous