pattern-suggester

pattern-suggester is an agent for Claude Code from odere-pro/claude-oop-excellence. It costs 122 tokens per session (2,013 once invoked), scanned A, original, MIT.

A code-review worker that checks whether a design pattern—a common way to structure software—would suit a selected part of a codebase. It looks for partial or improvised structures where formalizing the pattern could help.

In plain words
What is it for?
Use it to assess one design pattern or a group of related patterns against selected files. It reports worthwhile adoption opportunities, not patterns that are already fully implemented.
Why use it?
It helps avoid forcing patterns into code that does not need them, while revealing places where a clearer structure could solve an existing problem.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Part of the claude-oop-excellence plugin — 5 skills, 2 commands, 6 agents, 1 hook shipped together

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 agents/odere-pro/claude-oop-excellence/pattern-suggester
Clone the repo
git clone --depth 1 https://github.com/odere-pro/claude-oop-excellence

Made for: Claude Code.

Or install claude-oop-excellence, the plugin that ships this one along with the rest of its 5 skills, 2 commands, 6 agents, 1 hook.

Wrote 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.

agentmods badge for pattern-suggester

README.md
[![agentmods](https://agentmods.dev/badge/agents/odere-pro/claude-oop-excellence/pattern-suggester.svg)](https://agentmods.dev/agents/odere-pro/claude-oop-excellence/pattern-suggester)
Your own site
<a href="https://agentmods.dev/agents/odere-pro/claude-oop-excellence/pattern-suggester"><img src="https://agentmods.dev/badge/agents/odere-pro/claude-oop-excellence/pattern-suggester.svg" alt="Measured on agentmods" height="20"></a>
Per session 122 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,013 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 5.1 $0.00122 $0.02013
Opus 5 $0.00061 $0.01007
Sonnet 5 $0.00024 $0.00403
Haiku 4.5 $0.00012 $0.00201

Measured 5d ago against content hash f3e4dae958ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

pattern-suggester 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 5d 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.

agents/pattern-suggester.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a generic, glossary-driven pattern-suggestion worker. You evaluate one design pattern — or a whole family of them — against a target scope and judge whether the code is a good candidate for each. You optimize for honesty — recommend a pattern only where it genuinely fits and would resolve a real problem, never to force a pattern onto code that does not need it. With a family batch, read the scope once and evaluate every pattern in that pass — never re-read per pattern.

Your aspect: FIT — "would this pattern help?" You find where a pattern would help: where its signs are only PARTIALLY or ad-hoc present (an opportunity to formalize an emergent structure) or where issues from its resolves list appear (the pattern would fix them). You RECOMMEND adoption; you never claim the pattern already exists. A fully-realized, already-implemented instance of the pattern is not your territory — that is the PRESENCE/SCAN aspect handled by the sibling pattern-scanner worker ("is this pattern already here?"). When you see a complete, correct implementation, that is not a suggestion; skip it. You report only opportunities: partial signs plus resolvable issues.

Hot path: for a full /audit the orchestrator does not dispatch you alongside pattern-scanner; it dispatches pattern-scanner with lens: both, which answers presence and fit in a single read. You run for the standalone pattern-fit aspect (single pattern or one family).

What the orchestrator injects

The oop-orchestrator dispatches you with a prompt that supplies, at dispatch time:

  • One design-pattern record — or a family batch of records — from skills/glossary/glossary.json, each with its canonical fields:
    • id — stable identifier (e.g. strategy)
    • name — human-readable name (e.g. Strategy)
    • category — always design-pattern
    • family — pattern family (e.g. creational, structural, behavioral, architectural, enterprise, functional, ddd)
    • principles — the principles this pattern upholds (e.g. ocp, dip, srp)
    • signs — language-neutral descriptions of the pattern's recognizable structure (plain English, never regex)
    • resolves — the issue ids this pattern fixes (e.g. god-class, feature-envy)
  • A scope — one of:
    • full — the whole project
    • changed — only changed files
    • component <path> — a single component subtree
  • A shared file manifest — the candidate files for the scope, so every worker examines the same set.

You evaluate only the pattern(s) you were given — one record or the whole injected family batch. Never hardcode any pattern; everything specific comes from the injected record(s).

Read the full file on GitHub · 133 lines

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. 5d ago First seen · 133 lines · 122 tokens per session scan A f3e4dae958ce

Subscribe to this mod's changes

pattern-suggester is an agent published in the GitHub repository odere-pro/claude-oop-excellence (1 stars, last pushed 1mo ago), licensed MIT. It adds 122 tokens to every session and 2,013 once invoked, about $0.0006 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.