- namespace
SKILL.md
The skill file stays in the publisher's repository.
Paste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add jmagly/aiwg --skill ralph-resume -a cursor -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add jmagly/aiwg --skill ralph-resume -a claude-code -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add jmagly/aiwg --skill ralph-resume -a codex -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add jmagly/aiwg --skill ralph-resume -a grok -ySend the copied message in a Grok Bot chat. The Bot fetches this SKILL.md from GitHub and adds it to the skills all your Bots share.
Install this skill: https://github.com/jmagly/aiwg/tree/HEAD/agentic/code/addons/agent-loop/skills/ralph-resumeFrom the publisher
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-nameby the platform. Reach them via:aiwg discover "<capability>" aiwg show skill <name> --bodyOnly kernel-listed skills (
aiwg-doctor,aiwg-refresh,aiwg-status,aiwg-help,use,steward) are directly invokable as slash commands. See skill-discovery rule.
Resume a paused or interrupted agent loop.
Before any confirmation below, read and apply
agent-loop authorization checkpoints.
Call aiwg config authorization check --action-file "$ACTION_FILE" --target "$TARGET_REPO"
for host-classified effects. Only auto-authorized with a signed receipt skips
that workflow prompt; retain existing prompts/refusals otherwise. Platform
prompts are never bypassed. Limits, regression and threat overrides still require review.
/ralph-resume # Resume with existing settings
/ralph-resume --max-iterations 20 # Resume with higher iteration limit
/ralph-resume --timeout 120 # Resume with longer timeout
Override the maximum iterations limit. Useful when loop stopped at limit but was making progress.
Override the timeout in minutes. Useful when loop timed out but task is close to completion.
.aiwg/ralph/current-loop.jsonIf 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"
Apply any parameter overrides:
maxIterations if --max-iterations providedtimeoutMinutes if --timeout providedContinue the agent loop pattern:
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}...
Same as ralph - generate completion report on success or limit.
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.
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
Previous loop stopped at iteration 10:
/ralph-resume --max-iterations 20
Continues with 10 more iterations available.
Previous loop timed out at 60 minutes:
/ralph-resume --timeout 120
Continues with fresh 120-minute timeout.
Loop interrupted (network, restart, etc.):
/ralph-resume
Continues from last checkpoint with original settings.
ralph-status - Check what state the loop is inralph-abort - Stop instead of resumeralph - Start new loopResume an interrupted agent loop from last checkpoint
---name: ralph-resumedescription: Resume an interrupted agent loop from last checkpoint---# agentic/code/addons/agent-loop/skills/ralph-resume/SKILL.mdFAQ
Download agentic/code/addons/agent-loop/skills/ralph-resume/SKILL.md from the publisher, or copy the path and open the repository. PlugMCP lists the skill and does not host the file.
The publisher keeps it at https://github.com/jmagly/aiwg.
Claude, Cursor, Codex, and Grok Build can read a SKILL.md you add from the publisher's repository. Grok Bot installs it when you send the skill's GitHub folder link in a chat.