checkpoint

A command that saves a snapshot of the agent's working setup and creates a continuity note describing the current task and changed files.

In plain words
What is it for?
Use it before a batch of risky changes, to record what was done, and to restore the latest saved setup if something goes wrong.
Why use it?
It gives you a recovery point before risky or self-changing edits and helps preserve context after a failed edit or shortened session.

Command

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/rasputinkaiser/self-improvement-plugin/checkpoint
Clone the repo
git clone --depth 1 https://github.com/RasputinKaiser/Self-Improvement-Plugin
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 189 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 $0.00015 $0.00189
Opus 5 $0.00008 $0.00095
Sonnet 5 $0.00003 $0.00038
Haiku 4.5 $0.00002 $0.00019

Measured 2d ago against content hash ca63f765f9fb, 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.

commands/checkpoint.md · 16 lines

What it actually says

Create a safe point before any risky/self-modifying work:

  1. python3 ${CLAUDE_PLUGIN_ROOT}/scripts/snapshot_harness.py --reason "before: $ARGUMENTS"
  2. Write a continuity packet capturing the current objective and changed files so the state survives a compaction or a botched edit: python3 ${CLAUDE_PLUGIN_ROOT}/scripts/compact_continuity.py (fed the current session/transcript context).
  3. Print the snapshot hash and the continuity packet path. If anything regresses, restore with: python3 ${CLAUDE_PLUGIN_ROOT}/scripts/restore_harness.py --latest.

This is the proactive variant of the autonomy gate's snapshot-on-self-edit behavior — call it before a batch of edits, not just before a single one.

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 · 16 lines · 15 tokens per session scan A ca63f765f9fb

Subscribe to this mod's changes

checkpoint is a command published in the GitHub repository RasputinKaiser/Self-Improvement-Plugin (6 stars, last pushed 5d ago), licensed MIT. It adds 15 tokens to every session and 189 once invoked, about $0.0001 per session on Opus 5. 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 2026-08-31.