agyenvoy CLAUDE.md

agyenvoy CLAUDE.md is an instructions file for coding agents from yinjs/agyenvoy. It costs 785 tokens per session, scanned A, original, MIT.

Repository instructions for a Claude Code plugin that wraps the agy command-line tool, Antigravity/Gemini's command-line interface, as an MCP server, a way for an agent to call external tools. It also defines the plugin's skills, build commands, tests, and architecture.

In plain words
What is it for?
Use it when working on the repository, especially for installing dependencies, running tests or development mode, building the TypeScript source, bundling the server, and understanding how delegation skills are organized.
Why use it?
It gives the coding agent the project-specific commands and constraints needed to build, test, lint, format, and modify the plugin safely.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/yinjs/agyenvoy/claude-md
Clone the repo
git clone --depth 1 https://github.com/yinjs/agyenvoy

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.

agentmods badge for agyenvoy CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/yinjs/agyenvoy/claude-md.svg)](https://agentmods.dev/instructions/yinjs/agyenvoy/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/yinjs/agyenvoy/claude-md"><img src="https://agentmods.dev/badge/instructions/yinjs/agyenvoy/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 785 This file is loaded in full into every session.
When invoked 785 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00785 $0.00785
Opus 5 $0.00392 $0.00392
Sonnet 5 $0.00157 $0.00157
Haiku 4.5 $0.00078 $0.00078

Measured 4d ago against content hash 979252c337a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agyenvoy 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.

CLAUDE.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 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.

Commands

npm install
git config core.hooksPath .githooks   # once per clone: pre-commit lints/format-checks + rebuilds server.mjs if stale; commit-msg runs commitlint

npm test                              # tsc build → dist/, then node --test test/*.test.mjs
node --test --test-name-pattern="agy_ask" test/server.test.mjs   # single test (needs dist/ built)
npm run build                         # tsc typecheck + emit dist/
npm run bundle                        # esbuild → server.mjs (the shipped artifact)
npm run dev                           # tsx watch src/index.ts
npm run lint                          # oxlint
npm run fmt                           # oxfmt --write; fmt:check for CI/hook mode

What this is

A Claude Code plugin wrapping the agy (Antigravity/Gemini) CLI as an MCP server plus three skills. .claude-plugin/plugin.json launches node server.mjs; skills/*/SKILL.md teach the host agent when to delegate to agy (image gen, media understanding, second opinions).

Architecture

All server code is one module: src/index.ts. CONTEXT.md is the domain glossary — use its terms (agy runner, auth store, print mode).

  • The agy runner seam: createServer(deps: AgyDeps) takes { runAgy, readAuthStatus }, defaulting to prod adapters. All four tool handlers go through deps. Tests pass fakes and drive tools through a real MCP client over InMemoryTransport — never by spawning agy. Keep new tool logic behind this seam so it stays testable that way.
  • server.mjs is a tracked build artifact (self-contained bundle; plugin users never npm install). Any src/ change requires npm run bundle in the same commit — the pre-commit hook enforces this.
  • Tests import from dist/, not src/npm test builds first; running node --test directly against stale dist/ tests old code.
  • One version, three files: .claude-plugin/plugin.json, marketplace.json, and package.json all carry the same version (package.json's is surfaced in MCP serverInfo via pkgVersion()). Bump all three together when releasing.

Read the full file on GitHub · 41 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.

  1. 4d ago First seen · 41 lines · 785 tokens per session scan A 979252c337a2

Subscribe to this mod's changes

agyenvoy CLAUDE.md is an instructions file published in the GitHub repository yinjs/agyenvoy (1 stars, last pushed 1mo ago), licensed MIT. It adds 785 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 2026-08-31.

Related

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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.

openai/codex · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

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).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens