Ralph Resume logo

Ralph Resume

Community
jmagly
ralph-resume

Resume an interrupted agent loop from last checkpoint

Overview

Publisherjmagly
Repositoryaiwg
Skill nameralph-resume
Stars
225
Forks
34
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by jmagly on GitHub. Read the source before you install it.

Installation

Install the Ralph Resume AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/jmagly/aiwg/tree/main/agentic/code/addons/agent-loop/skills/ralph-resume
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/jmagly/aiwg.git /tmp/aiwg
mkdir -p .claude/skills
cp -r /tmp/aiwg/agentic/code/addons/agent-loop/skills/ralph-resume .claude/skills/ralph-resume
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ralph Resume in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Ralph Resume on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Ralph Resume is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Skill access pattern (post-kernel-pivot, 2026.5+)

Skill names referenced in this document are AIWG skills, not slash commands. Most are not kernel-listed and cannot be invoked as /skill-name by the platform. Reach them via:

bash
aiwg discover "<capability>"
aiwg show skill <name> --body

Only kernel-listed skills (aiwg-doctor, aiwg-refresh, aiwg-status, aiwg-help, use, steward) are directly invokable as slash commands. See skill-discovery rule.

Al Resume

Resume a paused or interrupted agent loop.

Usage

/ralph-resume                       # Resume with existing settings
/ralph-resume --max-iterations 20   # Resume with higher iteration limit
/ralph-resume --timeout 120         # Resume with longer timeout

Parameters

--max-iterations N

Override the maximum iterations limit. Useful when loop stopped at limit but was making progress.

--timeout M

Override the timeout in minutes. Useful when loop timed out but task is close to completion.

Your Actions

Step 1: Load State

  1. Read .aiwg/ralph/current-loop.json
  2. Verify loop can be resumed (status != 'success', status != 'aborted')
  3. Load iteration history and learnings

If no resumable loop:

No agent loop to resume.

Status: {status}

{If success}: Loop completed successfully. Start a new loop with /ralph
{If aborted}: Loop was aborted. Start fresh with /ralph
{If no state}: No loop found. Start with /ralph "task" --completion "criteria"

Step 2: Update Settings

Apply any parameter overrides:

  • Update maxIterations if --max-iterations provided
  • Update timeoutMinutes if --timeout provided
  • Reset timeout start time for extended timeout

Step 3: Resume Execution

Continue the agent loop pattern:

  1. Display resume status:
Resuming Agent Loop

Task: {task}
Completion: {completion}
Previous iterations: {N}
Remaining iterations: {max - N}

Last result: {lastResult}
Learnings so far: {learnings}

Continuing from iteration {N+1}...
  1. Execute next iteration with accumulated learnings
  2. Follow standard agent loop verification
  3. Continue until success or new limits reached

Step 4: Handle Completion

Same as ralph - generate completion report on success or limit.

Resume Context

When resuming, include in the task context:

## Agent Loop Resume Context

**Original Task**: {task}
**Completion Criteria**: {completion}

**Previous Iterations**: {N}
**Accumulated Learnings**:
{for each iteration}
- Iteration {i}: {action} -> {result}. Learned: {learnings}
{end for}

**Current State**:
- Last attempt: {lastResult}
- Key insight: {most recent learning}

**Your Goal**:
Continue iterating from iteration {N+1}.
Apply learnings from previous iterations.
Verify against completion criteria after each attempt.

Error Handling

Loop completed successfully:

This agent loop already completed successfully.

Final status: SUCCESS
Iterations: {N}
Report: .aiwg/ralph/completion-{timestamp}.md

To run again, start a new loop:
  /ralph "task" --completion "criteria"

Loop was aborted:

This agent loop was aborted and cannot be resumed.

To start fresh with the same task:
  /ralph "{original task}" --completion "{original completion}"

State corrupted:

Agent loop state is corrupted or incomplete.

Options:
1. Start fresh: /ralph "task" --completion "criteria"
2. Clean up: rm -rf .aiwg/ralph/ then start new loop

Example Scenarios

Max Iterations Override

Previous loop stopped at iteration 10:

/ralph-resume --max-iterations 20

Continues with 10 more iterations available.

Timeout Override

Previous loop timed out at 60 minutes:

/ralph-resume --timeout 120

Continues with fresh 120-minute timeout.

Simple Resume

Loop interrupted (network, restart, etc.):

/ralph-resume

Continues from last checkpoint with original settings.

Related

  • ralph-status - Check what state the loop is in
  • ralph-abort - Stop instead of resume
  • ralph - Start new loop

References

  • @$AIWG_ROOT/agentic/code/addons/agent-loop/README.md — Ralph addon overview and loop executor documentation
  • @$AIWG_ROOT/agentic/code/addons/aiwg-utils/rules/vague-discretion.md — Loop termination and iteration limit rules
  • @$AIWG_ROOT/docs/cli-reference.md — CLI reference for ralph-resume and related commands
  • @$AIWG_ROOT/agentic/code/addons/aiwg-utils/rules/instruction-comprehension.md — Re-reading original task instructions on resume

Frequently asked questions

What does the Ralph Resume AI skill do?

Resume an interrupted agent loop from last checkpoint

Why use Ralph Resume on TypingMind?

Because you install it once and use it with any model. Ralph Resume is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Ralph Resume in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jmagly/aiwg/tree/main/agentic/code/addons/agent-loop/skills/ralph-resume. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Ralph Resume?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Ralph Resume?

As many as you like. As long as a model supports skills, you can use Ralph Resume with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Ralph Resume AI skill free?

Yes. It is published on GitHub by jmagly under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇