checkpoint

A command that saves the current conversation's state to memory and creates a short summary for continuing later.

In plain words
What is it for?
Use it before a break, during a long task, before risky work, or at a milestone so you can resume in a new conversation.
Why use it?
It preserves decisions, changed files, pending work, and other context before a conversation becomes too long or is paused.

Command for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/superpitt/self-improving-memory-mcp/checkpoint
Clone the repo
git clone --depth 1 https://github.com/SuperPiTT/self-improving-memory-mcp

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 441 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00441
Opus 5 $0.00000 $0.00220
Sonnet 5 $0.00000 $0.00088
Haiku 4.5 $0.00000 $0.00044

Measured 2d ago against content hash 2f83eae8f398, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

checkpoint scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/checkpoint.md · 85 lines

What it actually says

Manual Checkpoint Command

Save current conversation state to memory before it gets too long or you need to pause work.

Usage

/checkpoint [optional-description]

What this does

This command triggers the Pre-Compact Interceptor Agent manually to:

  1. Capture complete session state

    • Everything discussed and decided
    • All files modified
    • Pending tasks
    • Key context and decisions
  2. Save to memory

    • Creates checkpoint entity in knowledge base
    • Links to all related work
    • Preserves TodoWrite state
  3. Generate continuation summary

    • Compact summary to copy/paste
    • Resume instructions
    • All context preserved

When to use

  • Before taking a break
  • When context is getting long (check token count)
  • Before starting risky/complex work
  • At natural breakpoints (milestone completed)
  • When you want to continue later in fresh conversation

Example

/checkpoint before implementing authentication

After checkpoint

You'll receive:

  1. Confirmation that state is saved
  2. A continuation summary to copy
  3. Instructions to start fresh conversation

To resume later

In a NEW conversation, paste the continuation summary and Context Recovery Agent will automatically load the full context from memory.


Now activating Pre-Compact Interceptor Agent...

You are the Pre-Compact Interceptor Agent.

The user has manually triggered a checkpoint. Follow your instructions in .claude/agents/pre-compact-interceptor.md:

  1. Capture complete current session state
  2. Create comprehensive checkpoint entity
  3. Save to memory with all context
  4. Generate continuation summary
  5. Provide clear resume instructions

Additional context from command:

  • Manual trigger: yes
  • User description: "{{ARGS}}" (if provided)
  • Treat this as high-priority checkpoint

Begin checkpoint process now.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 85 lines · 0 tokens per session scan A 2f83eae8f398

Subscribe to this mod's changes

checkpoint is a command published in the GitHub repository SuperPiTT/self-improving-memory-mcp (0 stars, last pushed 11mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 441 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.