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.
npx skills add mirkosertic/MCPLuceneServer --skill improvementsgit clone --depth 1 https://github.com/mirkosertic/MCPLuceneServerWrote 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/skills/mirkosertic/mcpluceneserver/improvements)<a href="https://agentmods.dev/skills/mirkosertic/mcpluceneserver/improvements"><img src="https://agentmods.dev/badge/skills/mirkosertic/mcpluceneserver/improvements/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/skills/mirkosertic/mcpluceneserver/improvements"><img src="https://agentmods.dev/badge/skills/mirkosertic/mcpluceneserver/improvements.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 1526 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- medium Rogue Agent · line 395 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- low Excessive Agency · line 117 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
- low Excessive Agency · line 664 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 | $0.00041 | $0.17348 |
| Opus 5.5 | $0.00016 | $0.06939 |
| Sonnet 5.5 | $0.00008 | $0.03470 |
| Haiku 4.5 | $0.00004 | $0.01735 |
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 1mo 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.
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
- MCP-native architecture — AI client as the semantic layer is genuinely more powerful than static synonym/stemming configuration
- Structured passage output —
score,matchedTerms,termCoverage,positionper passage is optimized for LLM consumption - Leading wildcard optimization —
content_reversedfield for efficient*vertrag-style queries (German compound words) - Incremental crawling — 4-way reconciliation diff (DELETE/ADD/UPDATE/SKIP) is production-grade
- Operational polish — Schema version management, auto-reindex, OS-native notifications, NRT adaptive refresh, MCP App admin UI, lock file recovery
Solid — Good Foundation
- Tika extraction pipeline — Thorough content normalization (HTML entities, URL encoding, NFKC, ligature expansion)
- Faceted search — SortedSetDocValues facets with AI-guided drill-down workflow
- 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.
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.
- 1mo ago First seen · 1,569 lines · 41 tokens per session scan A b11e22f6eb7f
improvements is a skill published in the GitHub repository mirkosertic/MCPLuceneServer (6 stars, last pushed 4d ago), licensed Apache-2.0. It adds 41 tokens to every session and 17,348 once invoked, about $0.0002 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 skills, from other repositories
specimen-authoring
Workflow and hard-won TD patterns for authoring Embody Specimens (the transparent TDXN gallery networks). Load before building or persisting a Specimen.
externalize-operator
MUST READ before calling externalizeop or saveexternalization. Required workflow steps.
multi-instance
Workflow for running multiple TD instances with Envoy, switching between them, and understanding the instance registry.
coding-flow
Light coding workflow: features, fixes, refactors, unit tests, etc.; scales small to large.
coding-agents-prompting-flow
Workflow for authoring and adapting AI-agent prompts: skills, agents, workflows, rules, etc.
adhoc-flow
Workflow for the rest of tasks: lightweight documentation, build, track, synchronize, etc.