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/jaycrl/mobilevc/claude-mdgit clone --depth 1 https://github.com/JayCRL/MobileVCWrote 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/jaycrl/mobilevc/claude-md)<a href="https://agentmods.dev/instructions/jaycrl/mobilevc/claude-md"><img src="https://agentmods.dev/badge/instructions/jaycrl/mobilevc/claude-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 | $0.00684 | $0.00684 |
| Opus 5 | $0.00342 | $0.00342 |
| Sonnet 5 | $0.00137 | $0.00137 |
| Haiku 4.5 | $0.00068 | $0.00068 |
Grade A, and why
MobileVC 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.
What it actually says
MobileVC 项目规则
代码改动与编译
后端改动流程
- 在项目根目录执行编译：
go build -o server ./cmd/server - 停止旧进程：
pkill -f './server' - 启动新进程（必须带完整环境变量）：
AUTH_TOKEN="test-token-12345" \
APNS_AUTH_KEY_PATH="/Users/wust_lh/AuthKey_UUZWBMP5Z5.p8" \
APNS_KEY_ID="UUZWBMP5Z5" \
APNS_TEAM_ID="4YFXZ5X5YJ" \
APNS_TOPIC="com.justprove.mobilevc" \
APNS_PRODUCTION="false" \
nohup ./server > server.log 2>&1 &
- 验证启动成功：检查
server.log确认看到APNs service ready和Ready: addr=:8001
Flutter 改动流程
- 编译检查
- 打包上传 iOS OTA：调用
/ios-ota-deployskill 或直接执行source ~/.zshrc && mobilevc-ota - 详细流程参考 memory 中的
ios_ota_build_workflow.md
改动范围原则
- 只改动后端 → 只重启后端
- 只改动 Flutter → 只打包上传 iOS
- 同时改动两端 → 分别执行各自的流程
核心稳定区
以下模块是与 Claude 交互的核心逻辑，改动前必须：
- 先查 memory 和 CONTEXT.md
- 理解现有实现
- 不确定时先问用户
核心模块：
internal/session/- 会话管理和控制器状态internal/runner/- 命令执行和 Claude 交互internal/ws/- WebSocket 处理和协议通信internal/runtime/- 运行时管理
前后端对接规则
涉及 Flutter 端与后端对接的功能改动时：
- 必须读两端的代码
- 理解对接方式（协议、数据结构、事件流）
- 确保改动后两端协议一致
代码理解原则
当不知道具体的代码逻辑时：
- 必须先问用户
- 不要想当然或猜测实现
- 先读代码理解现有逻辑，不确定时再问
Git 提交规则
- 可以自动 commit 到本地仓库
- push 到 GitHub 远程仓库前必须经过用户确认
- 提交时排除
.claude/worktrees/等环境噪音
遇到不确定的情况
- 代码逻辑不清楚 → 先问用户
- 改动方案有多种选择 → 先问用户
- 编译/启动失败 → 报告错误，等待用户指示
- 涉及核心稳定区 → 先查 memory，不确定时问用户
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 · 69 lines · 684 tokens per session scan A 7a11edf88c03
MobileVC CLAUDE.md is an instructions file published in the GitHub repository JayCRL/MobileVC (209 stars, last pushed 2mo ago), licensed MIT. It adds 684 tokens to every session, about $0.0034 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 2026-08-30.
Other instructions, from other repositories
flutter-intellij CLAUDE.md
Claude Code instructions for flutter/flutter-intellij, covering flutter intellij plugin — claude code guide, additional rules and agent skills & workflows.
flutter_enterprise_starter_kit CLAUDE.md
Instructions for nicolinx/flutter_enterprise_starter_kit, covering claude.md, start here, commands and non-negotiables.
wind dynamic.instructions.md
Instructions for fluttersdk/wind, covering dynamic json renderer (lib/src/dynamic/), json schema, security model (whitelist first), state binding (id-keyed widgets) and action dispatch.
wind widgets.instructions.md
Instructions for fluttersdk/wind, covering widget conventions (lib/src/widgets/), canonical shape (stateless composition widgets), statefulwidget exceptions (only when warranted), debug logger (mandatory in stateless widgets) and wanchor auto-wrapping.
platform AGENTS.md
Instructions for qorm/platform, covering agents.md — orienting an ai agent in the qorm repo, understand it, write / edit an app, drive a live app as an agent and build & test.
clawdex-mobile AGENTS.md
Instructions for Mohit-Patil/clawdex-mobile, covering agents, purpose, read first, repo map and active code.