patterns

A read-only report about how often tasks succeed and which working approaches tend to lead to good outcomes.

In plain words
What is it for?
Use it to review success rates, compare approaches with outcomes, and decide whether to improve a common failure area.
Why use it?
It makes recurring patterns visible without requiring you to inspect past task results manually.

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/patterns
Clone the repo
git clone --depth 1 https://github.com/RasputinKaiser/Self-Improvement-Plugin
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 174 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 $0.00019 $0.00174
Opus 5 $0.00010 $0.00087
Sonnet 5 $0.00004 $0.00035
Haiku 4.5 $0.00002 $0.00017

Measured yesterday against content hash 889e127175d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 yesterday.

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/patterns.md · 16 lines

What it actually says

Run python3 ${CLAUDE_PLUGIN_ROOT}/scripts/agent_patterns.py (full report, not --brief) and present it to the user verbatim with light formatting.

Then add a one-line interpretation:

  • If success rate < 70% → "success rate is low; consider /improve to attack the top failure topic."
  • If an approach→outcome correlation shows a bucket with >=80% success and >=3 samples → "approach <metric>=<bucket> correlates with success — lean into it."
  • If no outcomes recorded → "no outcomes yet; complete tasks with the Stop hook active to populate metrics."

Do not edit anything. This is a read-only dashboard.

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. yesterday First seen · 16 lines · 19 tokens per session scan A 889e127175d8

Subscribe to this mod's changes

patterns is a command published in the GitHub repository RasputinKaiser/Self-Improvement-Plugin (6 stars, last pushed 4d ago), licensed MIT. It adds 19 tokens to every session and 174 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.