What is mhl-core-runtime CLAUDE.md?

Repository instructions for mhl, a Go implementation of a language for describing AI-agent pipelines, tools, memory, servers, prompts, and their connections. They cover the runtime, a VS Code extension, documentation, and example skills.

Use them to navigate the Go source, language-server extension, documentation, and agent skills when implementing or validating mhl changes.

They provide the project map and warn that documentation examples may not match the implemented language. This helps an agent check the actual runtime before relying on reference material.

How mh-language/mhl-core-runtime configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to mh-language/mhl-core-runtime. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/mh-language/mhl-core-runtime/develop/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/mh-language/mhl-core-runtime

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/mh-language/mhl-core-runtime/claude-md/github.svg)](https://agentmods.dev/instructions/mh-language/mhl-core-runtime/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/mh-language/mhl-core-runtime/claude-md"><img src="https://agentmods.dev/badge/instructions/mh-language/mhl-core-runtime/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/mh-language/mhl-core-runtime/claude-md"><img src="https://agentmods.dev/badge/instructions/mh-language/mhl-core-runtime/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 7,226 This file is loaded in full into every session.

When invoked 7,226 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.07226	$0.07226
Opus 5.5	$0.02890	$0.02890
Sonnet 5.5	$0.01445	$0.01445
Haiku 4.5	$0.00723	$0.00723

Measured yesterday against content hash 258c6d68ffa4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mhl-core-runtime 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 yesterday.

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.

CLAUDE.md · 359 lines

How it starts

The opening of the file, as written. The whole thing — 359 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.

Repository overview

This repo is the implementation of mhl (Meta-Harness Language, .mh): a declarative language for describing AI agent pipelines — agents, tools, memory, MCP servers, prompts, and the pipelines that wire them together. It has four tracked parts:

src/mhl-runtime/ — the Go implementation of the mhl CLI (parser, interpreter, runtime, LSP). This is where nearly all engineering work happens.
vscode-mhl/ — a VS Code extension providing syntax highlighting, diagnostics, and completion for .mh files; it's a thin vscode-languageclient wrapper around mhl lsp.
docs/site/ — reference.html (and index.html) is the single, canonical language reference, deployed as-is to GitHub Pages by .github/workflows/page.yml. There is no separate wiki; some example fields may still be aspirational, not yet implemented — see "Docs vs. implementation" below before trusting an example as ground truth.
skills/ — agent skills teaching models to write .mh. Every ```mh block is a complete program checked by MHL=src/mhl-runtime/dist/mhl skills/check.sh, not by CI; run it and update the matching skill when a language change invalidates what they teach.

A dotnet/ directory may be present locally but is .gitignored in its entirety — it is not part of this repository and unrelated to mhl.

Commands

All Go commands run from src/mhl-runtime:

make build            # builds dist/mhl and sample/mhl
make test             # go test ./...
make functional-test  # runs `mhl test` against sample/syntax and sample/features
go vet ./...
make release          # cross-compiles linux-amd64, darwin-arm64, windows-amd64
make verify-release   # release + asserts each binary is non-empty

Focused iteration:

go test ./internal/lang/parser/...          # one package
go test -run TestName ./...                 # one test by name, across packages
go test ./internal/cli/... -run TestName -v # one test, verbose

Read the full file on GitHub · 359 lines

Changes

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.

yesterday First seen · 359 lines · 7,226 tokens per session scan A 258c6d68ffa4

Subscribe to this mod's changes

mhl-core-runtime CLAUDE.md is an instructions file published in the GitHub repository mh-language/mhl-core-runtime (9 stars, last pushed yesterday), licensed MIT. It adds 7,226 tokens to every session, about $0.0289 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 2026-11-07.

Building agents Go Languages

mhl-core-runtime CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mhl-core-runtime CLAUDE.mdmh-language/mhl-core-runtime	Instructions file	9	yesterday	MIT	A	7,226	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

mhl-core-runtime: Instructions file for Claude Code