Borrowing it
Nothing to install: this file belongs to liangjunglj-cpu/almond-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/liangjunglj-cpu/almond-mcp/master/AGENTS.mdgit clone --depth 1 https://github.com/liangjunglj-cpu/almond-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/liangjunglj-cpu/almond-mcp/agents-md)<a href="https://agentmods.dev/instructions/liangjunglj-cpu/almond-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/liangjunglj-cpu/almond-mcp/agents-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.
<a href="https://agentmods.dev/instructions/liangjunglj-cpu/almond-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/liangjunglj-cpu/almond-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01108 | $0.01108 |
| Opus 5 | $0.00554 | $0.00554 |
| Sonnet 5 | $0.00222 | $0.00222 |
| Haiku 4.5 | $0.00111 | $0.00111 |
Grade B, and why
almond-mcp AGENTS.md scanned grade B with 1 finding 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 9d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
`args = ["almond-mcp"]` in `~/.codex/config.toml`) How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup contract for AI assistants
You are setting up Almond MCP — this specific project, not a generic "Rhino MCP". Follow these steps exactly. Everything can be done headlessly.
Do NOT
- Do not substitute another implementation.
rhino-mcp,Rhino-MCP-Platform,rhino-mcp-router, and similar are different, unrelated products. The only two artifacts of this project are:- Rhino plugin:
almondbridge(Rhino 8 Package Manager / Yak) - MCP server:
almond-mcp(PyPI, run withuvx almond-mcp)
- Rhino plugin:
- Do not upgrade or downgrade Rhino. almondbridge ≥ 0.2.4 installs on
every Rhino 8 service release (yak tag
rh8_0). There is no minimum service release. If the Package Manager shows no result, the machine is not on Rhino 8, or its package index needs a refresh — never "fix" this by updating Rhino. - Do not clone or build this repo for a normal install; use the published packages.
- Do not modify or remove other entries in the user's MCP config.
Install steps (Windows, Rhino 8)
- Verify Rhino 8 exists (do not install/upgrade it yourself):
Test-Path "C:\Program Files\Rhino 8\System\Rhino.exe" - Install the bridge headlessly (no GUI needed):
(Equivalent GUI path:& "C:\Program Files\Rhino 8\System\Yak.exe" install almondbridge_PackageManagerin Rhino → searchalmondbridge.) - Install uv if missing (
Get-Command uvto check):winget install astral-sh.uv - Register the MCP server with the user's client — command
uvx, args["almond-mcp"], stdio transport:- Claude Desktop: add under
mcpServersin%APPDATA%\Claude\claude_desktop_config.json:"Almond": { "command": "uvx", "args": ["almond-mcp"] } - Claude Code:
claude mcp add Almond -- uvx almond-mcp - Codex CLI:
codex mcp add Almond -- uvx almond-mcp(or the equivalent[mcp_servers.Almond]entry withcommand = "uvx",args = ["almond-mcp"]in~/.codex/config.toml)
- Claude Desktop: add under
- Start (or restart) Rhino 8. The bridge auto-starts and listens on
127.0.0.1:5000(local only). In Rhino,AlmondMCPStatusconfirms it. - Verify end to end:
All checks should pass while Rhino is open. The "model files present 0/N" state is normal on a fresh install.uvx almond-mcp doctor - Hand the asset step back to the human. Downloading the optional
furniture/drawing models requires their Trimble sign-in:
uvx almond-mcp fetch-assets --openopens each source page; re-runningfetch-assetsverifies checksums. Do not attempt to automate the downloads or source the files from anywhere else.
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.
- 9d ago First seen · 79 lines · 1,108 tokens per session scan B 7607dc5e3add
almond-mcp AGENTS.md is an instructions file published in the GitHub repository liangjunglj-cpu/almond-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 1,108 tokens to every session, about $0.0055 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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 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.
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.