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.
git clone --depth 1 https://github.com/RasputinKaiser/Self-Improvement-PluginWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/rasputinkaiser/self-improvement-plugin/patterns)<a href="https://agentmods.dev/commands/rasputinkaiser/self-improvement-plugin/patterns"><img src="https://agentmods.dev/badge/commands/rasputinkaiser/self-improvement-plugin/patterns/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/rasputinkaiser/self-improvement-plugin/patterns"><img src="https://agentmods.dev/badge/commands/rasputinkaiser/self-improvement-plugin/patterns.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00014 | $0.00181 |
| Opus 5.5 | $0.00006 | $0.00072 |
| Sonnet 5.5 | $0.00003 | $0.00036 |
| Haiku 4.5 | $0.00001 | $0.00018 |
Grade A, and why
patterns 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 28d 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
Follow references/command-protocol.md.
Run python3 <plugin-root>/scripts/agent_patterns.py --json. Report the denominator,
unknown/conflicting outcomes, and missing metric fields alongside observed rates.
A small successful bucket is a hypothesis for a matched comparison, not a policy
recommendation. Edit counts, fewer tool calls, and absent errors are not acceptance.
For comparable chronological measurements, method drift accepts a frozen stable
baseline, explicit measurement identity, and numeric or missing observations.
Its EWMA signal suggests investigation; it identifies neither cause nor a win.
Do not pool different task families, environments, or evaluators into one chart.
No baseline, changed identity, or zero variance means no usable control chart.
Keep this command read-only and return an evidence-gathering next step.
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.
- 28d ago Changed · +1 lines · -5 tokens per session 7942a6cb020b
- 1mo ago First seen · 16 lines · 19 tokens per session scan A 889e127175d8
patterns is a command published in the GitHub repository RasputinKaiser/Self-Improvement-Plugin (8 stars, last pushed 13d ago), licensed MIT. It adds 14 tokens to every session and 181 once invoked, about $0.0001 per session on Opus 5.5. 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.
research
Research a technical or product question.
prp-plan
Create comprehensive feature implementation plan with codebase analysis and pattern extraction.
santa-loop
Adversarial dual-review convergence loop — two independent model reviewers must both approve before code ships.
gan-design
Run a generator/evaluator design loop for frontend or visual work with bounded iterations and scoring.