undo

undo is a command for Claude Code from owainlewis/youtube-tutorials. It costs 0 tokens per session (314 once invoked), scanned A, original, MIT.

A command for safely reversing common Git mistakes, such as an unwanted commit or incorrectly staged files. It explains what each recovery action does and checks related Git state before acting.

In plain words
What is it for?
Use it to undo the last commit while keeping its files, unstage files, move an accidental commit off the main branch, inspect the reflog, or review stashed changes.
Why use it?
It helps preserve local work while correcting mistakes and avoids silently using the most destructive reset option. For changes already shared, it recommends making a reversing commit instead.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Good fit Use it to undo the last commit while keeping its files, unstage files, move an accidental commit off the main branch, inspect the reflog, or review stashed changes.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/owainlewis/youtube-tutorials/undo
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/owainlewis/youtube-tutorials

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for undo

README.md
[![agentmods](https://agentmods.dev/badge/commands/owainlewis/youtube-tutorials/undo/github.svg)](https://agentmods.dev/commands/owainlewis/youtube-tutorials/undo)
Your own site
<a href="https://agentmods.dev/commands/owainlewis/youtube-tutorials/undo"><img src="https://agentmods.dev/badge/commands/owainlewis/youtube-tutorials/undo/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for undo

Your own site · 80×15
<a href="https://agentmods.dev/commands/owainlewis/youtube-tutorials/undo"><img src="https://agentmods.dev/badge/commands/owainlewis/youtube-tutorials/undo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 314 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00314
Opus 5.5 $0.00000 $0.00126
Sonnet 5.5 $0.00000 $0.00063
Haiku 4.5 $0.00000 $0.00031

Measured 1mo ago against content hash 653cfbb955a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

undo scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

tutorials/ai-git-workflow/resources/commands/undo.md · 46 lines

What it actually says

Undo

Undo a recent git mistake safely.

What happened?

$ARGUMENTS — describe the mistake (e.g. "committed to main by accident", "undo last commit", "wrong files got committed")

Common scenarios

Undo last commit, keep the changes

git reset --soft HEAD~1

Changes go back to staging. Nothing lost.

Undo last commit, unstage the changes

git reset HEAD~1

Changes stay in working directory but are unstaged.

Accidentally committed to main

  1. Create a new branch from current state
  2. Switch back to main
  3. Reset main to before the commit
  4. Push the changes on the new branch instead

Wrong files got committed

  1. git reset --soft HEAD~1 to undo the commit
  2. Unstage the wrong files
  3. Re-commit with only the correct files

Need to recover something lost

  1. Check git reflog to find the state you want
  2. Explain each reflog entry in plain language
  3. Ask before taking any action

Rules

  • Always explain what will happen before running destructive commands
  • Prefer --soft over --hard to preserve work
  • Never run git reset --hard without explicit confirmation
  • If changes have been pushed, use git revert instead of git reset
  • Check git stash list — the user might have stashed work they forgot about
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago First seen · 46 lines · 0 tokens per session scan A 653cfbb955a8

Subscribe to this mod's changes

undo is a command published in the GitHub repository owainlewis/youtube-tutorials (403 stars, last pushed 18d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 314 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.