improvements

improvements is a skill for Claude Code from mirkosertic/MCPLuceneServer. It costs 41 tokens per session (17,348 once invoked), scanned A, original, Apache-2.0.

A roadmap and analysis guide for improving a software project. It explains design decisions, trade-offs, current strengths, and possible future features.

In plain words
What is it for?
Use it when planning features, comparing technical approaches, prioritising improvements, or reviewing the design of a search and retrieval system.
Why use it?
It helps teams decide what to build next without duplicating work that the AI client can already handle. It also records why certain approaches were accepted or rejected.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md.

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 skills/mirkosertic/mcpluceneserver/improvements
Any agent
npx skills add mirkosertic/MCPLuceneServer --skill improvements
Clone the repo
git clone --depth 1 https://github.com/mirkosertic/MCPLuceneServer

Made for: Claude Code.

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 improvements

README.md
[![agentmods](https://agentmods.dev/badge/skills/mirkosertic/mcpluceneserver/improvements.svg)](https://agentmods.dev/skills/mirkosertic/mcpluceneserver/improvements)
Your own site
<a href="https://agentmods.dev/skills/mirkosertic/mcpluceneserver/improvements"><img src="https://agentmods.dev/badge/skills/mirkosertic/mcpluceneserver/improvements.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 17,348 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 $0.00041 $0.17348
Opus 5 $0.00020 $0.08674
Sonnet 5 $0.00008 $0.03470
Haiku 4.5 $0.00004 $0.01735

Measured 6d ago against content hash b11e22f6eb7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

improvements 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 6d 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.

.claude/skills/improvements/SKILL.md · 1,569 lines

How it starts

The opening of the file, as written. The whole thing — 1,569 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Improvement Roadmap

Core Design Principle: Client-Side Intelligence

The fundamental architecture decision is that semantic understanding lives in the MCP client (the AI), not in the server. The server is a fast, precise, lexical retrieval engine. The AI compensates for what the server doesn't do.

This means:

  • The AI generates synonym expansions via OR queries — no synonym files needed
  • The AI handles multilingual query formulation — per-language stemmed shadow fields complement this (see candidate E)
  • The AI iterates on results (search, read, refine) — no "smart" ranking needed
  • The server stays simple, fast, dependency-light, and debuggable

Any proposed improvement must be evaluated against this principle. If the AI client can do it, the server shouldn't duplicate it.


Current Strengths (Do Not Regress)

Excellent — Competitive Advantages

  1. MCP-native architecture — AI client as the semantic layer is genuinely more powerful than static synonym/stemming configuration
  2. Structured passage outputscore, matchedTerms, termCoverage, position per passage is optimized for LLM consumption
  3. Leading wildcard optimizationcontent_reversed field for efficient *vertrag-style queries (German compound words)
  4. Incremental crawling — 4-way reconciliation diff (DELETE/ADD/UPDATE/SKIP) is production-grade
  5. Operational polish — Schema version management, auto-reindex, OS-native notifications, NRT adaptive refresh, MCP App admin UI, lock file recovery

Solid — Good Foundation

  1. Tika extraction pipeline — Thorough content normalization (HTML entities, URL encoding, NFKC, ligature expansion)
  2. Faceted search — SortedSetDocValues facets with AI-guided drill-down workflow
  3. Crawler lifecycle — Pause/resume, directory watching, batch processing, config persistence

Improvement Candidates

Tier 1: High Impact — Amplify the Existing Architecture

These improve the AI client's ability to use the server effectively without duplicating semantic logic.

Read the full file on GitHub · 1,569 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. 6d ago First seen · 1,569 lines · 41 tokens per session scan A b11e22f6eb7f

Subscribe to this mod's changes

improvements is a skill published in the GitHub repository mirkosertic/MCPLuceneServer (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 41 tokens to every session and 17,348 once invoked, about $0.0002 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.