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/spatialy/huly-mcp/claude-mdgit clone --depth 1 https://github.com/spatialy/huly-mcpWrote 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/spatialy/huly-mcp/claude-md)<a href="https://agentmods.dev/instructions/spatialy/huly-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/spatialy/huly-mcp/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 | $0.00951 | $0.00951 |
| Opus 5 | $0.00476 | $0.00476 |
| Sonnet 5 | $0.00190 | $0.00190 |
| Haiku 4.5 | $0.00095 | $0.00095 |
Grade A, and why
huly-mcp 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 4d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Instructions
Rules are reflexive: when adding a rule, apply it immediately.
Design Principle: LLM-First API
The primary consumer of this MCP server is an LLM coding agent, not a human developer. All design decisions — tool naming, parameter shapes, description writing, error messages, defaults — must optimize for LLM comprehension and single-call correctness. Prefer fewer tool calls with clear semantics over multi-step protocols. Auto-resolve identifiers where possible rather than requiring the caller to decompose them. Write tool descriptions as if the reader has no documentation beyond the schema and the description string.
Package Manager
Use pnpm, not npm. Prefer package.json scripts over raw commands (e.g., pnpm typecheck not pnpm tsc --noEmit).
Verification
Run before considering work complete:
pnpm build && pnpm typecheck && pnpm lint && pnpm test- Integration tests against local Huly (Docker) — required for any new feature, major change, or pre-release. Do not defer to the user; run them yourself. See
INTEGRATION_TESTING.mdfor test patterns andCLAUDE.local.mdfor credentials/setup.
Code Style
No comments that repeat the code. If the code says what it does, don't add a comment saying the same thing.
No Dead Code
Every function, type, and export must have at least one call site at time of writing. Never write code "for future use" unless the user explicitly requests it.
Tests
Don't write tests that only verify compile-time guarantees (type assignments, interface conformance). If the compiler already checks it, a test adds nothing.
Type Safety
Type casts (as T) are a sin. Avoid them. When unavoidable:
- Add a comment explaining WHY the cast is necessary
- Document what evidence/API docs support the cast being safe
- Consider if a generic type parameter or type guard could eliminate the cast
All data crossing system boundaries (APIs etc.) must be strongly typed — both inbound (decoding) and outbound (encoding), with Effect Schema.
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.
- 4d ago First seen · 89 lines · 951 tokens per session scan A b616a7989230
huly-mcp CLAUDE.md is an instructions file published in the GitHub repository spatialy/huly-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 951 tokens to every session, about $0.0048 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.