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.
npx agentmods add commands/kuku0922/awesome-ai-coding-enhance/git-rollbackgit clone --depth 1 https://github.com/kuku0922/awesome-ai-coding-enhanceWrote 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.
[](https://agentmods.dev/commands/kuku0922/awesome-ai-coding-enhance/git-rollback)<a href="https://agentmods.dev/commands/kuku0922/awesome-ai-coding-enhance/git-rollback"><img src="https://agentmods.dev/badge/commands/kuku0922/awesome-ai-coding-enhance/git-rollback.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00037 | $0.04536 |
| Opus 5 | $0.00018 | $0.02268 |
| Sonnet 5 | $0.00007 | $0.00907 |
| Haiku 4.5 | $0.00004 | $0.00454 |
Grade A, and why
git-rollback 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 490 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Command: Enterprise Git Rollback with Multi-Tier Safety
🚨 Production-Ready Safety: Comprehensive rollback system with four distinct safety modes, automatic backup creation, collaborative impact warnings, and complete audit trails. Dry-run enabled by default for maximum safety.
🎯 Four-Tier Rollback Safety Modes
1. Quick Rollback ⚡ (Emergency Mode)
- Use Case: Production hotfixes, critical security issues
- Features: Minimal prompts, automatic backup, fast execution
- Safety: Essential checks only, designed for speed
- Best For: When time is critical and you know exactly what to rollback
2. Safe Preview 🔍 (Visual Mode)
- Use Case: Regular development, uncertain impact scope
- Features: Color-coded diff display, file change summary, impact visualization
- Safety: Comprehensive preview with visual confirmation
- Best For: When you need to see exactly what will change
3. Comprehensive Analysis 📋 (Detailed Mode)
- Use Case: Critical branches, complex rollbacks, team environments
- Features: Collaborative impact detection, CI/CD status check, dependency analysis
- Safety: Maximum validation with enterprise-grade warnings
- Best For: When rollback could affect team members or dependent systems
4. Standard Mode 🎯 (Balanced Mode)
- Use Case: Daily development workflow
- Features: Interactive selection with essential safety checks
- Safety: Balanced approach between speed and thoroughness
- Best For: Most rollback scenarios (default behavior)
Usage
# Interactive mode with mode selection
/git-rollback # Full interactive: select mode, branch, target, action
# Four-Tier Mode Selection
/git-rollback --mode quick # Emergency rollback with minimal prompts
/git-rollback --mode safe-preview # Visual diff preview before action
/git-rollback --mode comprehensive # Full analysis with team impact warnings
/git-rollback --mode standard # Balanced interactive mode (default)
# Branch and Target Specification
/git-rollback --branch feature/calculator # Specify branch, interactive for rest
/git-rollback --target v1.2.0 # Specify target, interactive for branch/mode
# Advanced Combinations
/git-rollback --branch main --target 1a2b3c4d --mode quick --yes --backup
/git-rollback --branch release/v2.1 --target v2.0.5 --mode comprehensive --team-notify
/git-rollback --mode safe-preview --depth 50 # Extended history with visual preview
# Enterprise Features
/git-rollback --backup --team-notify # Create backup and suggest team notification
/git-rollback --mode comprehensive --yes # Full analysis with auto-confirmation
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.
- 5d ago First seen · 490 lines · 0 tokens per session scan A 8edcd743a784
git-rollback is a command published in the GitHub repository kuku0922/awesome-ai-coding-enhance (3 stars, last pushed 9mo ago), licensed MIT. It adds 37 tokens to every session and 4,536 once invoked, about $0.0002 per session on Opus 5. 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.
Other commands, from other repositories
address-review
Address all reviewer recommendations from a PR code review systematically.
pragmatic-code-review
Perform a comprehensive pragmatic code review of recent changes against requirements.
sugar-task
Create a comprehensive Sugar task with rich context and metadata.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.