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/lai-gen-descriptorWrote 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-descriptor)<a href="https://agentmods.dev/skills/eclipse-langium/langium-ai/lai-gen-descriptor"><img src="https://agentmods.dev/badge/skills/eclipse-langium/langium-ai/lai-gen-descriptor/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-descriptor"><img src="https://agentmods.dev/badge/skills/eclipse-langium/langium-ai/lai-gen-descriptor.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 | $0.00049 | $0.02801 |
| Opus 5 | $0.00024 | $0.01401 |
| Sonnet 5 | $0.00010 | $0.00560 |
| Haiku 4.5 | $0.00005 | $0.00280 |
Grade A, and why
lai-gen-descriptor 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 13d 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 — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate or Refine a Language Descriptor
This skill covers the full lifecycle of a language.descriptor.yml — from initial generation to iterative refinement. If no descriptor exists yet, it bootstraps one using lai gen descriptor. If one already exists, it guides you through reviewing and improving it so that downstream artifacts (system prompts, evaluations, MCP servers) are as accurate as possible.
You may also use the lai and langium skills for deeper understanding of the CLI workflow and Langium project structure.
When to Use
- No descriptor yet — you have a Langium project initialized with
lai initand need to generate the first descriptor - Descriptor exists but is incomplete — auto-detection missed custom services, examples, or documentation
- Paths are wrong — the generated descriptor references files that don't exist or are in the wrong location
- Language has evolved — grammar, validation rules, or project structure changed since the descriptor was generated
- Evaluation failures — poor eval results trace back to incomplete or inaccurate descriptor content
- Adding examples or docs — new example programs or documentation have been added to the project
Prerequisites
The target Langium project must have:
lai initcompleted — alai.config.jsoncexists at the project root- A working Langium grammar (
.langiumfile) and generated TypeScript artifacts - Node.js and npm available
Step 1: Generate the Descriptor (if not present)
If no language.descriptor.yml exists, generate one:
# generate from project analysis (uses LLM to synthesize)
lai gen descriptor
# regenerate from scratch, ignoring any existing descriptor
lai gen descriptor --fresh
This produces a YAML file that maps your Langium project. It is a starting point — the auto-detector does its best but will likely need corrections.
If a descriptor already exists and you want to refine it, skip to Step 2.
Step 2: Review and Refine the Descriptor
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.
- 13d ago First seen · 286 lines · 49 tokens per session scan A 5f10ed0491a7
lai-gen-descriptor is a skill published in the GitHub repository eclipse-langium/langium-ai (30 stars, last pushed 16d ago), licensed MIT. It adds 49 tokens to every session and 2,801 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 2026-08-30.
Other skills, from other repositories
build-and-test
How to build and test .NET projects in the Agent Framework repository. Use this when verifying or testing changes.
python-feature-lifecycle
Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.
python-code-quality
Code quality checks, linting, formatting, and type checking commands for the Agent Framework Python codebase. Use this when running checks, fixing lint errors, or troubleshooting CI failures.
python-development
Coding standards, conventions, and patterns for developing Python code in the Agent Framework repository. Use this when writing or modifying Python source files in the python/ directory.
effect-v4
Write, review, or upgrade Effect v4 code in the Composio CLI, cli-keyring, and json-schema-to-effect-schema packages, all pinned exactly to [email protected] — Context.Service and explicit layers, Schema.TaggedError and typed recovery, the effect/unstable/cli command surface, and the vendored effect source oracle.…
python-release
Handle Python SDK release, build, bump, packaging metadata, PyPI client pin, uv.lock, nox/build workflow, and publish verification changes. Use for Python release process work or dependency pin bumps; do not use for ordinary Python feature implementation.