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/kobiton/automate/agents-mdgit clone --depth 1 https://github.com/kobiton/automateWrote 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/kobiton/automate/agents-md)<a href="https://agentmods.dev/instructions/kobiton/automate/agents-md"><img src="https://agentmods.dev/badge/instructions/kobiton/automate/agents-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 | $0.05337 | $0.05337 |
| Opus 5 | $0.02669 | $0.02669 |
| Sonnet 5 | $0.01067 | $0.01067 |
| Haiku 4.5 | $0.00534 | $0.00534 |
Grade B, and why
automate 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 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
| Continue / Cline | Add to `~/.continue/config.json` or equivalent (see README) | How it starts
The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kobiton Automate - Agent Guide
Cross-tool agent instructions for the Kobiton mobile testing platform's MCP plugin. This file is the host-agnostic equivalent of skills/run-automation-suite/SKILL.md. It's read by Gemini CLI (via contextFileName), GitHub Copilot CLI, and Cursor CLI. Codex CLI reads the mirrored .codex/skills/*/SKILL.md instead; Claude Code reads skills/*/SKILL.md directly.
What this plugin does
Kobiton is a real-device mobile cloud for Android + iOS testing. This MCP plugin gives AI agents tools to:
- Devices: list, get status, reserve, terminate reservation
- Apps: list, upload, confirm upload, get parsing status, get details
- Sessions: list, get, get artifacts, get user-input events, terminate
- Test management: create / list / get / update / delete test cases, test runs, and test suites;
saveTestCaseconverts a finished manual session into a reusable test case - Account:
getCredential(used by/automate:setup);getOrgSettingsfor org-level feature flags such as live remediation
The MCP server runs at https://api.kobiton.com/mcp. Authentication is OAuth 2.1 (default) or API key (CI/headless).
userIntent format
Every tool call requires a userIntent argument summarizing what the user is trying to accomplish, a natural-language sentence is sufficient (e.g., "reserve a Pixel 7 to run the checkout suite"). The plugin's audit logging consumes this; include it on every tool call.
Getting started (new users)
The full journey a first-time user takes: /automate:setup (credentials) → listDevices / reserveDevice → drive the device with one skill (routing table below) → saveTestCase on the finished session → optionally createTestRun + monitor. Frame the skills as steps of that one flow, not a menu.
Route by intent:
| The user wants… | Use |
|---|---|
| to run local Appium scripts (Node.js/Python/.NET/Java) on Kobiton devices | run-automation-suite |
| a clean hands-off run of a described flow, saveable as a test case | drive-automation-session |
| quick inspection / troubleshooting — poke at a device, pull logs, push files | run-interactive-session |
| to kick off a test run from a test case or suite | create-test-run |
| to watch a running test run and catch blockers | monitor-test-run |
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 · 193 lines · 5,337 tokens per session scan B 84cf8e3daf9e
automate AGENTS.md is an instructions file published in the GitHub repository kobiton/automate (12 stars, last pushed yesterday), licensed MIT. It adds 5,337 tokens to every session, about $0.0267 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 2026-08-30.
Other instructions, from other repositories
sumulige-claude AGENTS.md
AGENTS.md instructions for sumulige/sumulige-claude, covering agents.md - agent 系统详解, technical co-founder working agreement (always-on), layer 1: 什么是 agent？ (5 分钟), 最简单的解释 and 类比：餐厅团队.
skillsmith copilot-instructions.md
Copilot instructions for ApexIQ/skillsmith, covering github copilot instructions, project overview, required context and workflow.
skillsmith AGENTS.md
AGENTS.md instructions for ApexIQ/skillsmith, covering agents.md, 1. prime directives, 2. the 7-stage development cycle, 3. execution standard and 4. slash command registry (mcp mapping).
skillsmith CLAUDE.md
Claude Code instructions for ApexIQ/skillsmith, covering claude.md, prime directives, 7-stage workflow, strategic branching (brain-aware tooling) and slash commands.
skillsmith GEMINI.md
Gemini CLI instructions for ApexIQ/skillsmith, covering gemini.md, prime directives, 7-stage workflow, execution policy and memory and cost policy.
spellbook AGENTS.md
AGENTS.md instructions for majiayu000/spellbook, covering spellbook agent contract, routing, scope rules, threads long-run guardrails and validation.