Agent skill

Resume Checkpoint

by alexgreensh in alexgreensh/token-optimizer

Pulls a prior session's checkpoint as fenced, scrubbed recovery context.

Custom licenceAuto-check passedAgent Workflows

Install Resume Checkpoint

skills CLI
$ npx skills add alexgreensh/token-optimizer --skill resume-checkpoint -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install alexgreensh/token-optimizer resume-checkpoint --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/alexgreensh/token-optimizer.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/resume-checkpoint .claude/skills/resume-checkpoint && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
resume-checkpoint
GitHub stars
2.5k
Token cost
~838 tokens
SKILL.md length
302 words
Files
2 (incl. scripts)
Skills in repo
6
Repo updated
First seen
Licence
Custom licence

At a glance

Pulls a prior session's checkpoint as fenced, scrubbed recovery context.

  • The user is continuing prior work
  • SKILL.md covers When to call, When NOT to call (negative…, What it returns and Invocation
  • Runs Python scripts from its folder; calls python3
  • Skip it on a fresh

What it does

Resume Checkpoint is an agent skill from alexgreensh/token-optimizer. Pulls a prior session's checkpoint as fenced, scrubbed recovery context. Use when the user is continuing prior work; skip it on a fresh, unrelated task.

Its SKILL.md is about 840 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/pull_checkpoint.py`).

It sits in Agent Workflows. The repository describes itself as: Find the ghost tokens. Fix them. Survive compaction. Avoid context quality decay.

When your agent uses it

  • The user is continuing prior work
  • Skip it on a fresh

Example prompts

  • “Use the resume-checkpoint skill to pull a prior session's checkpoint as fenced, scrubbed recovery context”
  • “/resume-checkpoint”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit 723c19b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Resume Checkpoint loads about 838 tokens when it runs. Until then it costs about 43 tokens; SKILL.md has 302 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~43
When it runs · the whole SKILL.md, loaded when a task matches
~838

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 302 words (~838 tokens).

“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).”

— opening of SKILL.md by alexgreensh, Custom licence
name
resume-checkpoint
effort
low

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file (scripts) in skills/resume-checkpoint of alexgreensh/token-optimizer.

  • SKILL.md
  • scripts/pull_checkpoint.py

Open the folder on GitHubat commit 723c19b

Compare with similar skills

Resume Checkpoint next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Resume Checkpoint compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Resume Checkpoint this skillalexgreensh/token-optimizer2.5k—~838Automated safety check: PassCustom licence
Context Optimizationguanyang/open-agent-hub9772 repos~4kAutomated safety check: PassMIT
Sop PlanStanshy/AgentHub202—~437Automated safety check: NotesMIT
Planzereight/gitlab-mcp2k1 repos~509Automated safety check: PassMIT
Vc Autoresearchwithkynam/vibecode-pro-max-kit1.1k—~3.7kAutomated safety check: PassMIT
Ops ResumeLifecycle-Innovations-Limited/claude-ops542—~753Automated safety check: NotesMIT

Similar skills

  • Context Optimization

    guanyang/open-agent-hub

    This skill should be used for improving context efficiency: context budgeting, observation masking, prefix or KV-cache strategy, partitioning, token-cost reduction, retrieval scoping, and extending…

    977 GitHub starsUsed in 2 repos~4k tokens
    Agent WorkflowsAuto-check passed
  • Sop Plan

    Stanshy/AgentHub

    L1 計畫模式 SOP — 強制上下文載入 + Plan Mode 評估 + 任務拆解. An agent skill from Stanshy/AgentHub.

    202 GitHub stars~437 tokensUpdated 6 mo ago
    Agent WorkflowsAuto-check: notes
  • Plan

    zereight/gitlab-mcp

    Strategic planning with optional interview workflow. An agent skill from zereight/gitlab-mcp.

    2k GitHub starsUsed in 1 repo~509 tokens
    Agent WorkflowsAuto-check passed
  • Vc Autoresearch

    withkynam/vibecode-pro-max-kit

    Loop: find gaps → fix → repeat until agents find no gaps or a metric goal is hit.

    1.1k GitHub stars~3.7k tokensUpdated 3 mo ago
    Agent WorkflowsAuto-check passed
  • Ops Resume

    Lifecycle-Innovations-Limited/claude-ops

    OPS on-demand: This skill should be used when the user asks to "resume sessions", "reopen ghostty…

    542 GitHub stars~753 tokensUpdated yesterday
    Agent WorkflowsAuto-check: notes
  • Trading Agents

    LeoYeAI/openclaw-master-skills

    Multi-agent stock trading signal analysis framework with two-round debate mechanism.

    2.2k GitHub stars~4.2k tokensUpdated 2 mo ago
    Agent WorkflowsAuto-check passed

More from alexgreensh/token-optimizer

  • Token Optimizer

    alexgreensh/token-optimizer

    Audits a Claude Code or Codex setup for context-window waste, fixes it with the user's approval, and measures the saving.

    2.5k GitHub stars~2.4k tokensUpdated today
    Auto-check passed
  • Fleet Auditor

    alexgreensh/token-optimizer

    Audits token waste and cost across Claude Code, Codex, OpenClaw, Hermes and OpenCode, with dollar savings.

    2.5k GitHub stars~1.5k tokensUpdated today
    Auto-check passed
  • Token Coach

    alexgreensh/token-optimizer

    Coaches a token-efficient Claude Code or Codex setup from the user's own usage data.

    2.5k GitHub stars~2.5k tokensUpdated today
    Auto-check passed
  • Token Dashboard

    alexgreensh/token-optimizer

    Opens the Token Optimizer dashboard in the browser (context usage, quality, savings).

    2.5k GitHub stars~950 tokensUpdated today
    Auto-check passed
  • Token Optimizer

    alexgreensh/token-optimizer

    Audit your OpenClaw setup for token waste, context bloat, and cost optimization opportunities

    2.5k GitHub stars~481 tokensUpdated today
    Auto-check passed

Questions about Resume Checkpoint

What does Resume Checkpoint do?

Pulls a prior session's checkpoint as fenced, scrubbed recovery context. Resume Checkpoint is an agent skill from alexgreensh/token-optimizer. Pulls a prior session's checkpoint as fenced, scrubbed recovery context.

When should I use Resume Checkpoint?

Resume Checkpoint fits situations like: the user is continuing prior work; skip it on a fresh.

How do I install Resume Checkpoint in Claude Code?

Run `npx skills add alexgreensh/token-optimizer --skill resume-checkpoint -a claude-code`. Or copy the skill folder (skills/resume-checkpoint in alexgreensh/token-optimizer) into .claude/skills/resume-checkpoint in your project. Claude Code loads it when a task matches its description.

How do I install Resume Checkpoint in Codex?

Run `npx skills add alexgreensh/token-optimizer --skill resume-checkpoint -a codex`. Or copy the skill folder (skills/resume-checkpoint in alexgreensh/token-optimizer) into .agents/skills/resume-checkpoint in your project. Codex loads it when a task matches its description.

Can I use Resume Checkpoint in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add alexgreensh/token-optimizer --skill resume-checkpoint -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/resume-checkpoint, .gemini/skills/resume-checkpoint, .github/skills/resume-checkpoint and .opencode/skills/resume-checkpoint in your project.

What does Resume Checkpoint need to run?

Going by SKILL.md and its folder, Resume Checkpoint needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Resume Checkpoint access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Resume Checkpoint safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Resume Checkpoint use?

Resume Checkpoint has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Resume Checkpoint use?

About 838 tokens (SKILL.md is roughly 3.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Resume Checkpoint?

Skills that share tags, products or a category with Resume Checkpoint: Context Optimization (guanyang/open-agent-hub, 977 stars), Sop Plan (Stanshy/AgentHub, 202 stars), Plan (zereight/gitlab-mcp, 2k stars) and Vc Autoresearch (withkynam/vibecode-pro-max-kit, 1.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Resume Checkpoint?

alexgreensh (a GitHub user) maintains it in alexgreensh/token-optimizer, which has 2,534 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 10, 2026.

Source: alexgreensh/token-optimizer on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.