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 eclipse-langium/langium-ai --skill lai-gen-syspromptgit clone --depth 1 https://github.com/eclipse-langium/langium-aiWrote 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-gen-sysprompt)<a href="https://agentmods.dev/skills/eclipse-langium/langium-ai/lai-gen-sysprompt"><img src="https://agentmods.dev/badge/skills/eclipse-langium/langium-ai/lai-gen-sysprompt/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/eclipse-langium/langium-ai/lai-gen-sysprompt"><img src="https://agentmods.dev/badge/skills/eclipse-langium/langium-ai/lai-gen-sysprompt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00051 | $0.01700 |
| Opus 5 | $0.00026 | $0.00850 |
| Sonnet 5 | $0.00010 | $0.00340 |
| Haiku 4.5 | $0.00005 | $0.00170 |
Grade A, and why
lai-gen-sysprompt 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 10d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate or Refine a System Prompt
This skill covers the full lifecycle of a system prompt for a Langium DSL — from initial generation to iterative refinement. If no system prompt exists yet, it bootstraps one using lai gen sysprompt. If one already exists, it guides you through diagnosing issues from evaluation results and making targeted improvements.
You may also use the lai and langium skills for deeper understanding of the CLI workflow and Langium project structure.
When to Use
- No system prompt yet — you have a descriptor and need to generate the first system prompt
- Evaluation results show low pass rates or recurring failure categories
- The system prompt is missing key language details — grammar rules, validation constraints, scoping rules
- LLM-generated code consistently has specific error patterns
- The descriptor or language has changed since the prompt was last generated
- The prompt is too verbose, unfocused, or missing edge cases
Prerequisites
The target Langium project must have:
lai initcompleted — alai.config.jsoncexists- A language descriptor (
language.descriptor.yml) — generate one first using thelai-gen-descriptorskill if needed - Node.js and npm available
Step 1: Generate the System Prompt (if not present)
If no system prompt exists, generate one from the descriptor:
# generate a system prompt
lai gen sysprompt
# regenerate from scratch, ignoring any existing prompt
lai gen sysprompt --fresh
This produces a markdown file (e.g., language.sysprompt.md) that instructs an LLM how to generate valid code in your DSL. It is driven entirely by the descriptor content.
If a system prompt already exists and you want to refine it, skip to Step 2.
Step 2: Identify What Needs Fixing
Read the current system prompt and any recent evaluation results to understand the gaps:
# check latest evaluation results
lai show latest --verbose
# compare against a previous good run if available
lai compare <good-run-id> latest
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.
- 10d ago First seen · 182 lines · 51 tokens per session scan A db3f057a0ed8
lai-gen-sysprompt is a skill published in the GitHub repository eclipse-langium/langium-ai (30 stars, last pushed 14d ago), licensed MIT. It adds 51 tokens to every session and 1,700 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
ai-engineering-toolkit
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
prompts
Version and manage your agent's prompts with LangWatch Prompts CLI. Use for both onboarding (set up prompt versioning for an entire codebase) and targeted operations (version a specific prompt, create a new prompt version). Supports Python and TypeScript.
prompt-regression
Use when the user has changed a prompt (system prompt, RAG template, agent instruction, etc.) and wants to know whether the candidate is better or worse than the baseline. Also use when the user mentions prompt A/B testing, prompt comparison, prompt optimization validation, "did my prompt change help," or prompt…
llm-integration
LLM integration patterns for function calling, streaming responses, local inference with Ollama, and fine-tuning customization. Use when implementing tool use, SSE streaming, local model deployment, LoRA/QLoRA fine-tuning, or multi-provider LLM APIs.
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.