checkpoint

Save session state to .etc_sdlc/checkpoint.md for resumption after context resets.

8|1|Updated Feb 13, 2026
One-click install
npx skills add https://github.com/Heavy-Chain-Engineering/etc --skill checkpoint-heavy-chain-engineering
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: checkpoint
Source: https://github.com/Heavy-Chain-Engineering/etc/tree/main/skills/checkpoint
Command: npx skills add https://github.com/Heavy-Chain-Engineering/etc --skill checkpoint-heavy-chain-engineering

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Saving and preserving long-running session state to enable resumption after context resets or compaction.

Core Features & Use Cases

  • Auto-checkpoint on /compact to persist state; manual /checkpoint for richer, reasoned checkpoints; and automatic journal updates.
  • Maintains a durable checkpoint file at .etc_sdlc/checkpoint.md and a governance journal to reconstruct context after resets.
  • Integrates with the PreCompact hook to avoid clobbering recent user-defined checkpoints within a freshness window.

Quick Start

Run /checkpoint before ending a long session to persist the current state.

Frequently Asked Questions about checkpoint

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I save session state before a context compaction?

Session state is saved automatically on /compact via a PreCompact hook that writes a best-effort checkpoint.md and journal entry, preserving your workflow context across context resets.

What is the best way to resume a long-running session after a restart?

Session resumption relies on a durable checkpoint file and governance journal stored at .etc_sdlc/checkpoint.md, which reconstruct the necessary context and working state after unexpected resets.

How does the manual checkpoint command differ from automatic checkpointing?

Manual /checkpoint creates a richer, reasoned save, while automatic checkpointing on /compact is best-effort and avoids clobbering recent manual checkpoints within a defined freshness window.

When do I need to persist session state during iterative prompts?

Session state persistence is needed during long-running workflows or iterative prompts where context must be preserved across restarts, ensuring no progress is lost during compaction.

Does the checkpoint functionality work with existing SDLC workflows?

Checkpoint integrates with SDLC workflows by maintaining a governance journal and durable checkpoint file, allowing you to reconstruct context and resume work after context resets.

Why does my automatic checkpoint not overwrite my recent manual save?

Automatic checkpoints avoid overwriting recent manual checkpoints by enforcing a freshness window, ensuring your richer, user-defined saves are protected from being clobbered during compaction.