improve

improve is a skill for Claude Code from odere-pro/claude-oop-excellence. It costs 108 tokens per session (1,804 once invoked), scanned A, original, MIT.

A code-cleanup tool that finds a selected design problem or code smell, makes the smallest needed change, and checks the result with the project's own commands.

In plain words
What is it for?
Use it to fix one or more issues reported by a code audit, such as an antipattern or problem affecting a group of related code.
Why use it?
It removes the need to turn an audit finding into a refactoring plan by hand. It also checks whether the change still works.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

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

Good fit Use it to fix one or more issues reported by a code audit, such as an antipattern or problem affecting a group of related code.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/odere-pro/claude-oop-excellence/improve
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.

Any agent
npx skills add odere-pro/claude-oop-excellence --skill improve
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 improve

README.md
[![agentmods](https://agentmods.dev/badge/skills/odere-pro/claude-oop-excellence/improve/github.svg)](https://agentmods.dev/skills/odere-pro/claude-oop-excellence/improve)
Your own site
<a href="https://agentmods.dev/skills/odere-pro/claude-oop-excellence/improve"><img src="https://agentmods.dev/badge/skills/odere-pro/claude-oop-excellence/improve/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.

agentmods 80×15 button for improve

Your own site · 80×15
<a href="https://agentmods.dev/skills/odere-pro/claude-oop-excellence/improve"><img src="https://agentmods.dev/badge/skills/odere-pro/claude-oop-excellence/improve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 108 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,804 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00108 $0.01804
Opus 5 $0.00054 $0.00902
Sonnet 5 $0.00022 $0.00361
Haiku 4.5 $0.00011 $0.00180

Measured 8d ago against content hash 7d02512fb080, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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 8d 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.

skills/improve/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Quality Improver

The FIX action — Layer 1, the side-effecting action of the RISK track. Detect → smallest corrective refactor → verify, one glossary entity at a time, in any language. This skill resolves the caller's selection against the glossary, then delegates the work to the oop-orchestrator in fix mode, which fans out one entity-fixer worker per in-scope entity, in parallel, batched by family. It assumes nothing about the language or stack.

This is the action an /audit report hands off to: the report's Recommended Actions section emits /fix-risks <selection> <scope>, which drives exactly this fix flow against the selection it recommends.

Because this skill writes to your source tree, it is user-invoked only (disable-model-invocation: true) and never auto-fires.

Selection grammar

[<entity-id> | <family> | all] [full | changed | component <path>] [--plan-only]

This mirrors the /audit selection + scope grammar exactly, plus a --plan-only mode.

Selection (default all)

The unit of work is a glossary entity, not a hardcoded domain. Resolve the selection against skills/glossary/glossary.json:

  • <entity-id> — a single issue entity (e.g. feature-envy, god-class, shotgun-surgery).
  • <family> — every issue entity in one family (e.g. oop, code, architecture, testing, concurrency, database, security, dependency).
  • all — every issue entity of the relevant kind.

Only issue entities (code smells, antipatterns, vulnerabilities, supply-chain risks) are in scope for the fix verb — design patterns are the province of /implement-patterns.

Scope (default full)

  • full — the whole project.
  • changed — only files changed versus the base branch (git diff).
  • component <path> — a directory or file set (e.g. component src/).

--plan-only

Produce the corrective plan — detected instances and the intended diffs — and make no edits. No files are written, no mutating commands run. Use it to preview the refactor before committing to it.

Read the full file on GitHub · 142 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. 8d ago First seen · 142 lines · 108 tokens per session scan A 7d02512fb080

Subscribe to this mod's changes

improve is a skill published in the GitHub repository odere-pro/claude-oop-excellence (1 stars, last pushed 1mo ago), licensed MIT. It adds 108 tokens to every session and 1,804 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

ai-development-guide

Applies language-agnostic and backend technical decision criteria, anti-pattern detection, debugging, and quality gates. Use when reviewing general/backend implementation choices, code smells, failures, or implementation completeness.

shinpr/claude-code-workflows · 43 tokens

logic-health

Sweep a directory, module, or full codebase for logic correctness and produce a scored health dashboard with systemic patterns. Trigger when the user requests a health view — "audit the whole codebase", "health check", "health overview", "logic health overview", "audit src/", "audit auth and payments modules", "where…

hyhmrright/logic-lens · 180 tokens

debug

Systematic bug investigation with a five-phase framework: reproduce, narrow, diagnose, fix, verify. Supports automated regression bisect via --regression flag. Produces a structured debug report with root cause analysis, regression test, and CQ/Q self-evaluations.

greglas75/zuvo · 55 tokens

code-hygiene

Codebase health analysis: dead code, test quality, duplicates, complexity, security, architecture mapping. Tool-first, structured storage, forge integration.

malakhov-dmitrii/forge · 34 tokens

refactor

Automated iterative code refactoring with swarm-orchestrated specialist agents including deep codebase discovery, confidence-scored code review, and security analysis. Use this skill when the user wants to improve existing code quality, clean up messy code, restructure, simplify, reduce tech debt, or perform…

zircote-plugins/refactor · 112 tokens

Pair Programming

AI-assisted pair programming with multiple modes (driver/navigator/switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switching, continuous code review, security scanning, and performance optimization with…

spencermarx/open-code-review · 61 tokens