Resume Checkpoint

Resume Checkpoint is an AI Engineering skill for Claude Code, published by alexgreensh in token-optimizer.

1.9K stars154 forkson alexgreensh/token-optimizerAdded 2026/08/18+3% in starsRepository updated 2026/08/17

agentskillsclaude-codeclaude-code-skillclaude-plugincontext-engineeringcontext-windowghost-tokenstoken-optimizationtoken-optimizertoken-usage

Install in seconds

Install Resume Checkpoint

Copy Resume Checkpoint into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/alexgreensh/token-optimizer/tree/main/skills/resume-checkpoint ~/.claude/skills/resume-checkpoint

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/alexgreensh/token-optimizer.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: skills/resume-checkpoint/SKILL.md in alexgreensh/token-optimizer
Installs to: ~/.claude/skills/resume-checkpoint
Collection: One of 6 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Resume Checkpoint does

Resume Checkpoint fetches a prior session's checkpoint on demand when continuing prior work, returning fenced, source-labeled recovery context. Call it when a user says continue or resume and the SessionStart pointer was not enough.

Resume Checkpoint is cataloged under AI Engineering on DirSkills. Resume Checkpoint comes from a repository tagged agentskills, claude-code, claude-code-skill, claude-plugin and context-engineering.

Documentation

README

Excerpt

Resume Checkpoint (pull tool)

A model-invokable tool that fetches and judges a prior session's checkpoint on demand, when the user is continuing prior work and the SessionStart pointer was not enough (or was declined).

When to call

Call this skill when the user is continuing prior work and you need the prior session's context to proceed efficiently:

The user says "continue", "resume", "pick up where we left off", "what were we working on", or names a prior task/topic.
A ⤸resumable statusline signal is showing and the user's ask relates to prior work.
The SessionStart pointer offered a checkpoint and the user's first prompt confirms they intend to resume.

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Resume Checkpoint

What else does alexgreensh publish alongside Resume Checkpoint?
Resume Checkpoint is one of 6 skills that DirSkills catalogs from alexgreensh/token-optimizer, the repository it ships in. Its siblings there include Fleet Auditor, Token Coach and Token Dashboard. Each one is a separate skill with its own page in this directory, installs the same way Resume Checkpoint does, and is maintained by alexgreensh in that same repository. The rest of the collection is listed on the alexgreensh/token-optimizer page.
How does Resume Checkpoint compare to other AI Engineering skills?
Resume Checkpoint ranks #897 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Resume Checkpoint against them. Open each page to compare what they document and how they install.