re_gent: Skill for Claude Code

.claude/skills/rewind/SKILL.md

rewind is a skill for Claude Code from regent-vcs/re_gent. It costs 30 tokens per session (149 once invoked), scanned A, original, Apache-2.0.

A workspace and conversation restore tool that returns work to an earlier recorded step while keeping an automatic backup.

In plain words
What is it for?
Use it to rewind files and conversation history to a specified step.
Why use it?
It helps recover from mistakes or safely explore a different direction without losing the current state.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is regent-vcs/re_gent's own configuration. It tells Claude Code how to work on re_gent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything re_gent configures →

Reuse

Borrowing it

Nothing to install: this file belongs to regent-vcs/re_gent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/regent-vcs/re_gent/main/.claude/skills/rewind/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/regent-vcs/re_gent

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 rewind

README.md
[![agentmods](https://agentmods.dev/badge/skills/regent-vcs/re_gent/rewind.svg)](https://agentmods.dev/skills/regent-vcs/re_gent/rewind)
Your own site
<a href="https://agentmods.dev/skills/regent-vcs/re_gent/rewind"><img src="https://agentmods.dev/badge/skills/regent-vcs/re_gent/rewind.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 149 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00030 $0.00149
Opus 5 $0.00015 $0.00075
Sonnet 5 $0.00006 $0.00030
Haiku 4.5 $0.00003 $0.00015

Measured 8d ago against content hash b68f15c51ac5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

rewind 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.

.claude/skills/rewind/SKILL.md · 19 lines

What it actually says

⚠️ Warning: This will restore files and conversation state to the specified step.

Automatic backup is created at .regent/backups/ before rewinding.

Rewind to a step:

rgt rewind $ARGUMENTS

The step hash can be shortened (first 7+ characters).

After rewinding, the current conversation transcript will be saved and the workspace files will match the target step's state.

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 · 19 lines · 30 tokens per session scan A b68f15c51ac5

Subscribe to this mod's changes

rewind is a skill published in the GitHub repository regent-vcs/re_gent (791 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 30 tokens to every session and 149 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 2026-08-30.

Related

Other skills, from other repositories