ReddRadar
Agent skill
checkpoint-manager
Session checkpoint management: save, restore, list, clear state snapshots
Install this agent skill to your Project
npx add-skill https://github.com/alfredolopez80/multi-agent-ralph-loop/tree/main/.claude/skills/checkpoint-manager
SKILL.md
v2.88 Key Changes (MODEL-AGNOSTIC)
- Model-agnostic: Uses model configured in
~/.claude/settings.jsonor CLI/env vars - No flags required: Works with the configured default model
- Flexible: Works with GLM-5, Claude, Minimax, or any configured model
- Settings-driven: Model selection via
ANTHROPIC_DEFAULT_*_MODELenv vars
Checkpoint Manager
Manage session state checkpoints for the Ralph orchestration system.
Subcommands
save - Create checkpoint
/checkpoint save "before-refactor"
@cp save "Pre-deployment state"
restore - Restore checkpoint
/checkpoint restore "before-refactor"
@cp restore cp_20260107_143015
list - List all checkpoints
/checkpoint list
@cp list
clear - Remove checkpoint(s)
/checkpoint clear "old-checkpoint"
@cp clear --all
Storage
Checkpoints are stored in ~/.ralph/checkpoints/ as JSON files.
Output Examples
Save Output
✅ Checkpoint saved: cp_20260214_143015_before-refactor
📁 Location: ~/.ralph/checkpoints/cp_20260214_143015.json
⏱️ Expires: 24 hours (2026-02-15 14:30:15)
List Output
╭───────────────────────────────────────────────────────╮
│ CHECKPOINTS (3) │
├───────────────────────────────────────────────────────┤
│ cp_20260214_143015 │ before-refactor │ 2h ago │
│ cp_20260214_120000 │ pre-deployment │ 5h ago │
│ cp_20260213_180000 │ feature-complete │ 1d ago │
╰───────────────────────────────────────────────────────╯
Workflow Integration
/checkpoint save "Before risky changes"
↓ (make changes)
/checkpoint restore "Before risky changes" # if needed
↓ (or continue)
/checkpoint clear "Before risky changes" # cleanup
Related Skills
/orchestrator- Full orchestration workflow/iterate- Iterative execution with checkpointing/gates- Quality validation before checkpoints
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
alfredolopez80/multi-agent-ralph-loop
browser-test
Browser testing using Chrome DevTools MCP and Playwright for visual verification. Start dev server, navigate, screenshot, Lighthouse audit, console errors, network check. Use when: (1) verifying frontend changes, (2) accessibility auditing, (3) performance testing, (4) visual regression. Triggers: /browser-test, 'test in browser', 'visual test', 'lighthouse audit'.
alfredolopez80/multi-agent-ralph-loop
crafting-effective-readmes
Use when writing or improving README files. Not all READMEs are the same — provides templates and guidance matched to your audience and project type.
alfredolopez80/multi-agent-ralph-loop
stop-slop
A skill for removing AI-generated writing patterns ('slop') from prose. Eliminates telltale signs of AI writing like filler phrases, excessive hedging, overly formal language, and mechanical sentence structures. Use when: writing content that should sound human and natural, editing AI-generated drafts, cleaning up prose for publication, or any content that needs to sound authentic rather than AI-generated. Triggers: 'stop-slop', 'remove AI tells', 'clean up prose', 'make it sound human', 'edit AI writing'.
alfredolopez80/multi-agent-ralph-loop
bugs
Bug hunting with Codex CLI Use when: (1) /bugs is invoked, (2) task relates to bugs functionality.
alfredolopez80/multi-agent-ralph-loop
adversarial
Multi-Agent Adversarial Analysis System for code security
alfredolopez80/multi-agent-ralph-loop
senior-software-engineer
Global skill enforcing senior software engineering best practices
Didn't find tool you were looking for?