checkpoint-mode
Pause autonomous agents for human feedback.
Install
mkdir -p .claude/skills/checkpoint-mode && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/3136" && unzip -o skill.zip -d .claude/skills/checkpoint-mode && rm skill.zipInstalls to .claude/skills/checkpoint-mode
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Pause for review every N tasks - selective autonomy patternKey capabilities
- →Pause agent execution after N tasks
- →Generate accomplishment summaries
- →Monitor for human approval signals
- →Resume work upon signal detection
How it works
The orchestrator tracks completed tasks against a frequency threshold, pauses execution, and waits for a specific signal file before resuming.
Inputs & outputs
When to use checkpoint-mode
- →Adding checkpoints to long-running tasks
- →Reviewing agent work in novel projects
- →Managing high-cost agent operations
About checkpoint-mode
Enforces a selective autonomy pattern by pausing agent execution after a configurable number of tasks or timeframe, requiring human approval to proceed.
Pause for review every N tasks - selective autonomy pattern
When not to use it
- →Fully automated CI/CD pipelines
Limitations
- →Requires manual approval to resume work
How it compares
It enforces a feedback loop for human oversight rather than allowing perpetual autonomous execution.
Compared to similar skills
checkpoint-mode side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| checkpoint-mode (this skill) | 1 | 10mo | Review | Beginner |
| using-superpowers | 95 | 6mo | No flags | Beginner |
| ultrawork | 11 | 6mo | No flags | Advanced |
| clawhub | 25 | 6mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by asklokesh
View all by asklokesh →You might also like
using-superpowers
obra
Use when starting any conversation - establishes mandatory workflows for finding and using skills, including using Skill tool before announcing usage, following brainstorming before coding, and creating TodoWrite todos for checklists
ultrawork
Yeachan-Heo
Parallel execution engine for high-throughput task completion
clawhub
openclaw
Use the ClawHub CLI to search, install, update, and publish agent skills from clawhub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed clawhub CLI.
skill-installer
openai
Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).
continuous-learning
affaan-m
Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.
memory-keeper-proactive-context-maintenance
b4CU-R4U
Automatically detect and maintain memory freshness by monitoring context staleness, significant code changes, task completions, and phase transitions. Proactively suggests and executes memory sync operations with user confirmation. Use when the user says "sync memory", "update context", or when the Skill detects that context is stale (>2 hours), significant changes have occurred (new commits), tasks completed, or major milestones reached. Replaces passive "context is stale" warnings with active maintenance.