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.
npx agentmods add commands/rasputinkaiser/self-improvement-plugin/checkpointgit clone --depth 1 https://github.com/RasputinKaiser/Self-Improvement-PluginWhat 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.
| Model | Per session | Once 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 |
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.
What it actually says
Create a safe point before any risky/self-modifying work:
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/snapshot_harness.py --reason "before: $ARGUMENTS"- 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). - 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.
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.
- 2d ago First seen · 16 lines · 15 tokens per session scan A ca63f765f9fb
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.
Other commands, from other repositories
feature
Orchestrate a complete feature through discovery, spec, implementation, and review.
test
Design or run focused test validation for a task, bug, or diff.
mvp-spec
Research and produce a strict MVP spec with small 1-2 hour tasks and explicit out of scope.
research
Research a technical or product question.
review-pr
Command "review-pr" from saski/arnesto, covering review pr, what this command does, workflow steps, phase 0: initialize review and phase 1: analysis & summary.
evolution-engine
Scan feedback and generate evolution proposals for rule/skill upgrades.