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 agentmods add instructions/eclipse-langium/langium-ai/claude-mdgit 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/instructions/eclipse-langium/langium-ai/claude-md)<a href="https://agentmods.dev/instructions/eclipse-langium/langium-ai/claude-md"><img src="https://agentmods.dev/badge/instructions/eclipse-langium/langium-ai/claude-md.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 | $0.00780 | $0.00780 |
| Opus 5 | $0.00390 | $0.00390 |
| Sonnet 5 | $0.00156 | $0.00156 |
| Haiku 4.5 | $0.00078 | $0.00078 |
Grade A, and why
langium-ai CLAUDE.md 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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
Langium AI is a TypeScript monorepo for integrating LLMs with Langium DSLs. It provides tools to evaluate LLM-generated DSL output, split/process DSL documents respecting language structure, and a CLI for bootstrapping AI-powered tooling in Langium projects.
Commands
# Build & test (all workspaces)
npm run build
npm run test
# Lint & format
npm run lint # oxlint
npm run format # biome format (check only)
npm run format:fix # biome format --write (auto-fix)
# Single package (from root)
npm run build -w packages/cli
npm run test -w packages/cli
npm run test -w packages/langium-ai-tools
# CLI dev mode
cd packages/cli && npm run dev
# Detect unused code
npm run knip
Monorepo Structure
Four npm workspaces under packages/:
cli(langium-aion npm) — Commander.js CLI with commands for init, gen, evaluate, status, history, etc. Binary:lai.langium-ai-tools— Provider-agnostic core library: evaluator (LangiumEvaluator, EvalMatrix), splitter (ProgramMapper, splitByNode), analyzer (DocumentAnalyzer), and a vitest-style testing API. Uses protobuf for type definitions (interface.proto→src/gen/).langium-ai-mcp— Model Context Protocol server exposing alangium-syntax-checkertool via LangiumEvaluator.examples/example-dsl-evaluator— Example project demonstrating the evaluation workflow.
Architecture
CLI command flow: Each command is a separate module in packages/cli/src/commands/, registered in index.ts. Core logic lives in src/core/ (langium detection, descriptor management, config, sysprompt generation, versioning).
Key abstractions:
LaiConfig— project config persisted as YAML, tracks langium paths, descriptor/sysprompt pathsDescriptor— YAML-based language descriptor with grammar, examples, and docsLangiumEvaluator— validates LLM output using actual Langium parser/validator servicesEvalMatrix— compares multiple runners (models) against test suites
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.
- 6d ago First seen · 73 lines · 780 tokens per session scan A 77952aec2c06
langium-ai CLAUDE.md is an instructions file published in the GitHub repository eclipse-langium/langium-ai (30 stars, last pushed 9d ago), licensed MIT. It adds 780 tokens to every session, about $0.0039 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 instructions, from other repositories
index pr-reviewer.instructions.md
Instructions for indexnetwork/index, covering architecture layering, typescript, optional / nullable columns in drizzle upserts, database & migrations and version bumping.
tc39-mcp AGENTS.md
AGENTS.md instructions for xyzzylabs/tc39-mcp, covering project rules for ai agents, what tc39-mcp is, hard rules, code conventions and what you can reference.
voltagent CLAUDE.md
Instructions for VoltAgent/voltagent, a project described as: AI Agent Engineering Platform built on an Open Source TypeScript AI Agent Framework.
contexture typescript.instructions.md
Instructions for AcKeskin/contexture, covering typescript rules, typescript async, typescript modules, typescript narrowing and exhaustiveness and typescript type system.
sublayer CLAUDE.md
Instructions for sublayerapp/sublayer, covering claude.md, project overview, development commands, setup and testing.
tools CLAUDE.md
Claude Code instructions for avifenesh/tools, covering claude.md — @agent-sh/harness- monorepo, what counts as a test for an llm tool, operational rules for this repo, stack & tooling (context, not instructions) and working-agreement reminders.