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/witchan/ios-mcp/agents-mdgit clone --depth 1 https://github.com/witchan/ios-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/witchan/ios-mcp/agents-md)<a href="https://agentmods.dev/instructions/witchan/ios-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/witchan/ios-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 | $0.06883 | $0.06883 |
| Opus 5 | $0.03442 | $0.03442 |
| Sonnet 5 | $0.01377 | $0.01377 |
| Haiku 4.5 | $0.00688 | $0.00688 |
Grade A, and why
ios-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 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.
How it starts
The opening of the file, as written. The whole thing — 1,129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
本文件用于约束 Codex 在本仓库中的 Git 操作、提交日志生成、版本发布流程。
本项目是一个在 GitHub 上维护的开源项目,日常开发场景主要包括:
- 优化已有功能
- 修复 bug
- 新增功能
- 更新文档
- 发布新版本
Codex 在执行 Git 相关操作时,必须严格遵守本文件中的规范。
一、AGENTS.md 使用规则
1. 文件命名规则
如果希望 Codex 自动读取项目规则,文件名应使用:
AGENTS.md
不要将本文件改名为:
GIT.md
SKILL.md
AGENT.md
agents.md
如果项目中已经存在 AGENTS.md,不要新建第二个同名文件,也不要直接覆盖原文件。应该把本文件中的 Git 规范、提交流程、发布流程合并到已有 AGENTS.md 中。
2. 多个 AGENTS.md 的处理方式
如果仓库里已经有其他 AGENTS.md,优先按以下方式处理:
- 根目录已有
AGENTS.md:把本文件内容合并进去,建议放在Git 工作流规范章节。 - 子目录已有
AGENTS.md:子目录规则只用于该子目录相关任务,根目录仍应保留全局 Git 规范。 - 如果已有
AGENTS.md中的规则和本文件冲突,以更具体的规则为准;如果都是全局规则,以用户最新明确要求为准。 - 不要因为新增 Git 规范而删除已有项目规则、构建规则、测试规则或代码风格规则。
3. 推荐组织方式
推荐在根目录 AGENTS.md 中使用以下结构:
# AGENTS.md
## 项目说明
## 开发规范
## 测试规范
## Git 工作流规范
## 发布流程规范
本文件主要提供:
Git 工作流规范
发布流程规范
二、基础原则
1. 所有关键操作必须经过用户确认
以下内容必须先展示给用户,并等待用户明确确认后才能继续执行:
- commit 提交日志
git addgit commitgit push- release 分支创建或切换
- tag 创建
- GitHub Release 标题
- GitHub Release 内容
- GitHub Release 创建
- 合并 release 分支到 main
用户没有明确确认之前,不允许直接执行提交、推送、打 tag、创建 GitHub Release。
2. 禁止危险操作
除非用户明确要求,否则禁止执行以下命令:
git reset --hard
git push --force
git clean -fd
git branch -D
git push origin --delete
尤其注意:发布完成后不要删除 release 分支。
三、分支命名规范
1. 分支命名格式
分支名称统一使用:
类型-简短描述
类型和描述之间使用 - 分隔,不使用 /。
2. 常用分支类型
feature-xxx 新功能开发
fix-xxx 普通问题修复
hotfix-xxx 紧急问题修复
release-x.x.x 版本发布分支
docs-xxx 文档修改
refactor-xxx 代码重构
chore-xxx 构建、配置、依赖等调整
perf-xxx 性能优化
3. 分支命名示例
推荐:
feature-ui-query
feature-screenshot-api
fix-click-position
fix-rootless-install
hotfix-launch-crash
release-1.1.0
docs-update-readme
refactor-element-parser
chore-update-makefile
perf-optimize-screenshot
不推荐:
feature/ui-query
release/v1.1.0
release-v1.1.0
fix_click_position
Feature-Login
我的分支
update
4. main 分支规则
main 分支代表当前最新稳定版本。
发布完成后,release 分支必须合并回 main,保证 main 始终对应最新正式发布版本。
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 · 1,129 lines · 6,883 tokens per session scan A e436aedbc040
ios-mcp AGENTS.md is an instructions file published in the GitHub repository witchan/ios-mcp (620 stars, last pushed 1mo ago), licensed MIT. It adds 6,883 tokens to every session, about $0.0344 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
FluidAudio copilot-instructions.md
Copilot instructions for FluidInference/FluidAudio, covering fluidaudio - agent development guide, build & test commands, architecture, critical rules and code style (swift-format config).
speech-swift AGENTS.md
Instructions for soniqo/speech-swift, covering agent instructions, communication style, workflow, running tests and benchmarks — sequential and memory-aware and git conventions.
maui-labs AGENTS.md
AGENTS.md instructions for dotnet/maui-labs, covering agent instructions, repository overview, products, technology stack and building.
maui-labs testing.instructions.md
Instructions for dotnet/maui-labs, covering testing guide, test framework, test projects, running tests and all tests.
AppClaw CLAUDE.md
Instructions for appclawhq/AppClaw, covering claude.md, what is appclaw?, build & run commands, architecture and entry point & cli modes (src/index.ts).
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.