Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/eclipse-langium/langium-ainpx agentmods add skills/eclipse-langium/langium-ai/laiWrote 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/eclipse-langium/langium-ai/lai)<a href="https://agentmods.dev/skills/eclipse-langium/langium-ai/lai"><img src="https://agentmods.dev/badge/skills/eclipse-langium/langium-ai/lai.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00052 | $0.03978 |
| Opus 5 | $0.00026 | $0.01989 |
| Sonnet 5 | $0.00010 | $0.00796 |
| Haiku 4.5 | $0.00005 | $0.00398 |
Grade A, and why
lai 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 7d 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 — 464 lines — stays where its author put it; the contents beside it link to each section on GitHub.
langium-ai CLI (LAI) - Usage Guide
A CLI for bootstrapping AI-powered tooling in Langium projects. It generates language descriptors from your project structure, synthesizes system prompts from those descriptors, and runs evaluations to measure prompt quality — forming a refinement loop where you iteratively improve your descriptor and prompts based on evaluation results.
Workflow Overview
The core workflow is a loop:
init → generate descriptor → refine descriptor → generate sysprompt → evaluate → analyze results → refine → repeat
- Initialize (
lai init) — one-time project setup - Generate descriptor (
lai gen descriptor) — map your Langium project into a structured YAML descriptor - Validate descriptor (
lai validate) — check the descriptor schema and verify all referenced files exist - Refine the descriptor — manually correct and enrich the generated descriptor so it accurately represents your language
- Generate system prompt (
lai gen sysprompt) — produce a system prompt from the descriptor - Evaluate (
lai evaluate) — run evaluation cases against the system prompt via your configured LLM - Analyze results — use
lai show,lai compare,lai stats,lai historyto understand what passed and failed - Refine and repeat — adjust the descriptor, or evaluation cases, then regenerate and re-evaluate
Step 1: Initialize
lai init
Interactive setup that:
- Detects your Langium project structure (grammar files, langium-config.json, custom services)
- Detects your registered languages from
langium-config.json - Creates
lai.config.jsoncwith detected paths - Sets up an
evals/directory with starter template files (utils.tsandbasic.eval.ts)
Your LLM provider (OpenAI, Anthropic, Ollama, etc.) is not configured here — it's wired up in evals/utils.ts by implementing generateResponse(). Pass -y/--yes to skip all prompts and use defaults (non-interactive/CI).
Reinitializing Parts of the Setup
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.
- 7d ago First seen · 464 lines · 52 tokens per session scan A 0410ee164ebe
lai is a skill published in the GitHub repository eclipse-langium/langium-ai (30 stars, last pushed 10d ago), licensed MIT. It adds 52 tokens to every session and 3,978 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
testing-llm
LLM and AI testing patterns — mock responses, evaluation with DeepEval/RAGAS, structured output validation, and agentic test patterns (generator, healer, planner). Use when testing AI features, validating LLM outputs, or building evaluation pipelines.
golden-dataset
Golden dataset lifecycle patterns for curation, versioning, quality validation, and CI integration. Use when building evaluation datasets, managing dataset versions, validating quality scores, or integrating golden tests into pipelines.
evaluating-llms-harness
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.
evaluating-llms-harness
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.
ai-engineer
Builds production AI/ML systems — model training, fine-tuning, MLOps pipelines, model serving, evaluation frameworks, RAG optimization, and agent orchestration at scale. Use when the user asks to build, train, or deploy ML models, set up MLOps pipelines, optimize RAG systems, create inference endpoints, or design…
evaluating-code-models
Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.