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/shenyuexin/mobile-e2e-mcp/agents-mdgit clone --depth 1 https://github.com/shenyuexin/mobile-e2e-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/shenyuexin/mobile-e2e-mcp/agents-md)<a href="https://agentmods.dev/instructions/shenyuexin/mobile-e2e-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/shenyuexin/mobile-e2e-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 5.1 | $0.02050 | $0.02050 |
| Opus 5 | $0.01025 | $0.01025 |
| Sonnet 5 | $0.00410 | $0.00410 |
| Haiku 4.5 | $0.00205 | $0.00205 |
Grade A, and why
mobile-e2e-mcp AGENTS.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 5d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS Guide for mobile-e2e-mcp
This file is for AI coding agents and contributors who need a fast, reliable way to understand and modify this repository.
1) Project Identity
mobile-e2e-mcp is an AI-first mobile E2E orchestration monorepo for Android/iOS/React Native/Flutter.
Core execution model:
- deterministic-first action path
- bounded OCR/CV fallback
- policy-guarded, session-oriented execution
2) Start Here (Required Reading Order)
repomix-output.xml(global context snapshot)README.mdorREADME.zh-CN.md(entry-level architecture + scripts)docs/engineering/ai-first-capability-expansion-guideline.md(mandatory capability-expansion guardrails).planning/PROJECT.md,.planning/ROADMAP.md,.planning/STATE.mdwhen the task is non-trivial or depends on current execution context.planning/PLANNING-PROTOCOL.mdwhen the task adds, inserts, completes, or re-scopes planned work- Live repo delta-check (
git ls-files+ targeted file reads) - For implementation lookup, use
repomix-output.xmlfor broad context first, then use Serena for symbol-level discovery (find_symbol,find_referencing_symbols,get_symbols_overview) and impact analysis
Do not treat repomix-output.xml as the only source of truth.
Internal planning workspace rule
This repository keeps its internal planning system under .planning/.
PROJECT.md= stable planning charter and long-lived decisionsROADMAP.md= phase sequencing, dependencies, and completion trackingSTATE.md= current execution reality and resume pointPLANNING-PROTOCOL.md= update order and sync rules for new plans, summaries, verification, and roadmap/state changes
Use .planning/ for execution coordination and session continuity. Do not treat it as the only source of shipped product truth; formal behavior still lives in code, tests, CI, and public docs.
Mandatory activation rule for AI coding agents
If your task adds or changes any of the following, you must read docs/engineering/ai-first-capability-expansion-guideline.md before planning or editing code:
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.
- 5d ago First seen · 161 lines · 2,050 tokens per session scan A ab443a7b2a1d
mobile-e2e-mcp AGENTS.md is an instructions file published in the GitHub repository shenyuexin/mobile-e2e-mcp (2 stars, last pushed 3mo ago), licensed MIT. It adds 2,050 tokens to every session, about $0.0103 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
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.
im_flutter_sdk AGENTS.md
AGENTS.md instructions for easemob/im_flutter_sdk, covering agents.md, 协作约定, 项目架构, 开发环境初始化 and 命名约定.
cloudx-sdk-agents AGENTS.md
Instructions for cloudx-io/cloudx-sdk-agents, covering agents.md, the one rule, repository map and for agent tooling maintainers.
tv-maniac GEMINI.md
Gemini CLI instructions for thomaskioko/tv-maniac, covering tv maniac agent rules, project overview, architecture & tech stack, core mandates & conventions and 1. modularization & dependencies.
ios-simulator-skill CLAUDE.md
Instructions for conorluddy/ios-simulator-skill, covering claude.md - developer guide, project overview, project structure, architecture patterns and pattern 1: class-based script design.
expo-targets AGENTS.md
AGENTS.md instructions for csark0812/expo-targets, covering agents, product posture, sealed zones, docs ssot and safe commands.