undo

undo is a skill for Claude Code from nguyenthanhtat/screen1-claude. It costs 0 tokens per session (4,452 once invoked), scanned A, original, MIT.

A guide for undoing Git changes, where Git is a system for tracking code history. It covers unstaging files, discarding edits, changing commits, restoring history, and recovering lost commits.

In plain words
What is it for?
It is for reverting mistakes, fixing commit history, restoring local work, and recovering commits through Git's reflog.
Why use it?
It helps choose an undo operation that matches whether a change is merely edited, staged, or already committed.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the screen1-skills plugin — 46 skills shipped together

Good fit It is for reverting mistakes, fixing commit history, restoring local work, and recovering commits through Git's reflog.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nguyenthanhtat/screen1-claude/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.

Any agent
npx skills add nguyenthanhtat/screen1-claude --skill undo
Clone the repo
git clone --depth 1 https://github.com/nguyenthanhtat/screen1-claude

Made for: Claude Code.

Or install screen1-skills, the plugin that ships this one along with the rest of its 46 skills.

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/skills/nguyenthanhtat/screen1-claude/undo/github.svg)](https://agentmods.dev/skills/nguyenthanhtat/screen1-claude/undo)
Your own site
<a href="https://agentmods.dev/skills/nguyenthanhtat/screen1-claude/undo"><img src="https://agentmods.dev/badge/skills/nguyenthanhtat/screen1-claude/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/skills/nguyenthanhtat/screen1-claude/undo"><img src="https://agentmods.dev/badge/skills/nguyenthanhtat/screen1-claude/undo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,452 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 $0.04452
Opus 5 $0.00000 $0.02226
Sonnet 5 $0.00000 $0.00890
Haiku 4.5 $0.00000 $0.00445

Measured 8d ago against content hash 5a7773808a6f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 8d 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.

skills/git/undo/SKILL.md · 795 lines

How it starts

The opening of the file, as written. The whole thing — 795 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git Undo

Parent Skill: /git Path: /git/undo

Purpose

Master undoing changes at every stage: unstage files, discard working changes, amend commits, reset history, revert safely, and recover lost commits with reflog.

When to Use

Trigger automatically when:

  • User mentions: undo, reset, revert, restore, reflog, recover, amend, rollback
  • Made mistake in commit
  • Need to unstage files
  • Want to discard changes
  • Recover deleted commits
  • Fix commit history

Chat commands:

/git/undo unstage this file
/git/undo discard my local changes
/git/undo fix my last commit message
/git/undo undo last commit but keep changes
/git/undo recover deleted commit

Requirements

Verification

# Check current state
git status

# See commit history
git log --oneline -5

# Check reflog (for recovery)
git reflog

Critical Rules


Undo Workflow

File States & Undo Commands:

Working Directory → Staging → Repository
   (modified)       (staged)   (committed)
       ↓               ↓            ↓
 git restore      git restore   git reset
                   --staged    or git revert

Recovery: git reflog (for any deleted commits)

Patterns

Pattern 1: Unstage Files (Restore --staged)

Problem: Staged file by mistake

# ❌ BAD: Old confusing syntax
git reset HEAD file.js  # Works but unclear

# ✅ GOOD: Modern, clear syntax (Git 2.23+)
git restore --staged file.js

# Unstage all files
git restore --staged .

# Unstage specific files
git restore --staged src/app.js src/utils.js

Read the full file on GitHub · 795 lines

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. 8d ago First seen · 795 lines · 0 tokens per session scan A 5a7773808a6f

Subscribe to this mod's changes

undo is a skill published in the GitHub repository nguyenthanhtat/screen1-claude (2 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,452 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 2026-08-31.