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/leaf76/lazy_mobile_mcp/agents-mdgit clone --depth 1 https://github.com/leaf76/lazy_mobile_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/leaf76/lazy_mobile_mcp/agents-md)<a href="https://agentmods.dev/instructions/leaf76/lazy_mobile_mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/leaf76/lazy_mobile_mcp/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 | $0.02621 | $0.02621 |
| Opus 5 | $0.01311 | $0.01311 |
| Sonnet 5 | $0.00524 | $0.00524 |
| Haiku 4.5 | $0.00262 | $0.00262 |
Grade A, and why
lazy_mobile_mcp AGENTS.md scanned grade A 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- Worker path: in-process async TypeScript `Worker` via `src/workerClient.ts` + `src/worker.ts` (async `spawn`, not `spawnSync`). Routes tools to Android/iOS adapters and SQLite-backed telemetry/artifacts. How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Purpose and Scope
- This file governs
/Users/cy76/WorkSpace/sideProject/mcp_projects/lazy_mobile_mcp. - The repo is a single local-first Model Context Protocol (MCP) npm package for Android/iOS device automation and performance telemetry.
- Keep instructions operational and repo-specific. Do not add generic tool inventories or process rules that are not supported by this repo.
- Ignore
.tmp/,artifacts/,dist/,coverage/, caches (.venv/,node_modules/,.pytest_cache/,.mypy_cache/), and generated build output unless the user explicitly asks to inspect or clean them. - Inventory tools may over-count languages or flag monorepo signals from ignored
.tmp/WebDriverAgentcheckouts. Do not treat.tmp/as product architecture. There is no Python runtime path in this package.
Language
- Use English for code, comments, logs, config, UI strings, docs content, and commit messages.
- Use Traditional Chinese (Taiwan) for planning, status updates, and explanations to the user.
Repo Snapshot
- Runtime: Node.js 20+, TypeScript ESM (
"type": "module"), npm, Vitest. - Package name:
lazy_mobile_mcp; binary:lazy-mobile-mcp(bin/lazy-mobile-mcp.js→dist/cli.js). - Published package contents (
package.jsonfiles):bin/,dist/only. - CLI: bare invocation starts MCP over stdio;
setup-codexregisters the server in Codex;--help/-hprint usage. - Core MCP path:
src/index.ts— stdio registration, Zod validation, audit start/update,trace_id, worker calls. - Worker path: in-process async TypeScript
Workerviasrc/workerClient.ts+src/worker.ts(asyncspawn, notspawnSync). Routes tools to Android/iOS adapters and SQLite-backed telemetry/artifacts. - Adapters:
src/adapters/androidAdapter.ts(ADB),src/adapters/iosAdapter.ts(simctl/devicectl/ WDA). - Public tool schemas:
src/toolSchemas.ts+ domain checks insrc/mobileValidation.ts; public contract:docs/tool-contract.md. - Other core modules:
src/config.ts,src/policyGuard.ts,src/storage.ts,src/setupCodex.ts,src/errors.ts,src/logger.ts,src/perfCollector.ts. - Config env vars (from
src/config.ts/ docs):SQLITE_PATH,ARTIFACTS_DIR,DEVICE_ALLOWLIST,MOBILE_APPROVAL_POLICY(off|high|medium),LOG_LEVEL,ADB_BIN,WDA_BASE_URL,DEVICE_LIST_TTL_MS,WORKER_TIMEOUT_MS. - Docs set:
README.md,docs/tool-contract.md,docs/security.md,docs/runbook.md,docs/capability-matrix.md. - Runtime is TypeScript-only. Do not reintroduce a Python worker path unless the user explicitly requests it.
- CI:
.github/workflows/ci.ymlruns lint, test, build, andnpm pack --dry-runon push/PR.
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 · 116 lines · 2,621 tokens per session scan A bfff8acf14d5
lazy_mobile_mcp AGENTS.md is an instructions file published in the GitHub repository leaf76/lazy_mobile_mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 2,621 tokens to every session, about $0.0131 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
Maestro AGENTS.md
AGENTS.md instructions for mobile-dev-inc/Maestro, covering agents.md — maestro, module map, e2e test fixtures (e2e/), passing/ vs failing/ suites and test-e2e.yaml workflow contract.
scrcpy-mcp AGENTS.md
Instructions for JuanCF/scrcpy-mcp, covering agents.md, project overview, project documentation, build/lint/test commands and build the project.
android-agent CLAUDE.md
Instructions for ghost-in-the-droid/android-agent, covering ghost in the droid — agent tool rules, mcp tool: opencamera, mcp tool: speaktext and general rule.
native-devtools-mcp AGENTS.md
AGENTS.md instructions for vectora-foundry/native-devtools-mcp, covering agent context: native-devtools-mcp, 🧠 core reasoning loop, 🗺️ capabilities matrix (strategy guide), 🛠️ tool definitions & schemas and 1. vision & perception (the "eyes").
AppBootstrapAI CLAUDE.md
Instructions for kelvinkosbab/AppBootstrapAI, covering claude.md, project overview, what's in the box, how to onboard this into a new app project and update an already-managed repo — never a plain re-install.
uiautomator2-mcp-server CLAUDE.md
Instructions for tanbro/uiautomator2-mcp-server, a project described as: A MCP (Model Context Protocol) server that provides tools for controlling and interacting with Android devices using uiautomator2.