rollback

A command that undoes the latest Git commit, where Git is a tool for tracking changes to code, while letting you choose what happens to the changes afterward.

In plain words
What is it for?
Use it to undo the latest commit in mixed, soft, or hard mode; hard mode also deletes the changes from the working files and should not be used casually on shared branches.
Why use it?
It lets you remove a commit while either keeping the work available for editing or discarding it after an extra confirmation.

Command

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.

agentmods
npx agentmods add commands/flasherses/claude-code-dotfiles/rollback
Clone the repo
git clone --depth 1 https://github.com/flasherses/claude-code-dotfiles
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 317 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00317
Opus 5 $0.00000 $0.00159
Sonnet 5 $0.00000 $0.00063
Haiku 4.5 $0.00000 $0.00032

Measured 2d ago against content hash 8a0d6a10b459, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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.

commands/rollback.md · 36 lines

What it actually says

/rollback — 回滚最后一次 Git Commit

撤销最近一次 git commit,根据模式保留或丢弃变更。

用法

/rollback [模式]

模式选项:

  • 不指定 = --mixed(默认):撤销 commit,保留工作区变更(未暂存)
  • soft / --soft:撤销 commit,保留暂存区和工作区
  • hard / --hard:撤销 commit + 丢弃所有变更(需二次确认

示例

/rollback              → mixed 模式,最安全
/rollback --soft       → 撤销 commit,变更留在暂存区可以重新 commit
/rollback --hard       → 完全丢弃(会要求二次确认)

执行流程

  1. 调起 git-rollback Skill
  2. Skill 执行前置检查(git 仓库?未提交变更?显示目标 commit)
  3. 如果是 hard 模式 → 二次确认
  4. 执行回滚 → 显示结果

⚠️ 警告

  • 已 push 的 commit 不要随意回滚——回滚 + force push = 覆盖远程历史
  • hard reset 不可恢复——变更只能通过 git reflog 找回
  • 不要在 main/master 上做 hard reset
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. 2d ago First seen · 36 lines · 0 tokens per session scan A 8a0d6a10b459

Subscribe to this mod's changes

rollback is a command published in the GitHub repository flasherses/claude-code-dotfiles (5 stars, last pushed 22d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 317 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.