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/improvegit 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 | $0.00020 | $0.00244 |
| Opus 5 | $0.00010 | $0.00122 |
| Sonnet 5 | $0.00004 | $0.00049 |
| Haiku 4.5 | $0.00002 | $0.00024 |
Grade A, and why
improve 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
Run python3 ${CLAUDE_PLUGIN_ROOT}/scripts/self_correct.py --json and read the
result. Then act on the highest-priority finding:
- If
untested_scriptsis non-empty → dispatch thetest-authoragent for the first entry. Wait for it, then re-run/verify. - Else if
failure_patternsis non-empty → pick the top failure topic, search Memory Fabric for the most recent success on that scope (/recall <topic>), and propose a concrete fix. Do not apply it without snapshotting first (/checkpoint). - Else if
stale_scriptsis non-empty → summarize them; suggest archiving.
Finish by appending a one-line summary to ${SIPS_HOME:-$HOME/.codex/sips}/improvements.md under a new
## /improve sweep — <ts> heading. Do not edit ${CLAUDE_PLUGIN_ROOT}/scripts/* without a
snapshot — the autonomy gate will remind you, but snapshot proactively.
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 · 18 lines · 20 tokens per session scan A 4d12cddf5100
improve is a command published in the GitHub repository RasputinKaiser/Self-Improvement-Plugin (6 stars, last pushed 5d ago), licensed MIT. It adds 20 tokens to every session and 244 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
loop
Design and run a bounded engineering loop with durable state, human approval, and independent verification.
evolve
Run an optional AHE iteration to evaluate or improve this OpenCode harness with evidence and attribution.
loop-status
Consulta el estado durable de una misión sin adquirir locks ni escribir archivos.
evolution-engine
Scan feedback and generate evolution proposals for rule/skill upgrades.
skill-builder
Create a new Forge Skill with consistent structure.
weave
Improve active harnesses based on real use, failures, and corrections.