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/jaminzhou/appkitinspector/agents-mdgit clone --depth 1 https://github.com/JaminZhou/AppKitInspectorWhat 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 | $0.00326 | $0.00326 |
| Opus 5 | $0.00163 | $0.00163 |
| Sonnet 5 | $0.00065 | $0.00065 |
| Haiku 4.5 | $0.00033 | $0.00033 |
Grade A, and why
AppKitInspector 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 yesterday.
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
AppKit Inspector — Agent Instructions
Purpose
AppKit Inspector is a reusable Debug bridge between native macOS AppKit applications and a Codex MCP App. Keep it independent from any inspected product repository.
Safety boundary
- Use public Apple SDK APIs only. ScreenCaptureKit is limited to the inspected Debug process's own
windows through
SCShareableContent.currentProcess; never request Screen Recording permission or enumerate capture content owned by another process. - Do not add code injection, private frameworks, Accessibility automation, or Screen Recording permission.
- Keep discovery on a user-private path and transport on authenticated
127.0.0.1only. - Never make the probe active in Release, archive, TestFlight, or App Store builds.
- Treat captured UI and hierarchy data as private local content.
Structure
- Put native probe and demo code under
native/. - Put MCP server code under
packages/mcp/. - Put the embedded MCP App under
packages/app/. - Treat
plugins/appkit-inspector/dist/as generated distributable output; runnpm run buildafter changing either TypeScript package and include the matching output. - Keep the plugin skill concise; place protocol detail in its
references/directory.
Verification
- Full automated check:
npm run check - Release compile:
swift build -c release - Live bridge check: run
make demo, thennpm run test:livein another terminal. - Validate the plugin and skill with their respective Codex validation scripts before release.
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.
- yesterday First seen · 34 lines · 326 tokens per session scan A 3af99374872b
AppKitInspector AGENTS.md is an instructions file published in the GitHub repository JaminZhou/AppKitInspector (0 stars, last pushed 4d ago), licensed Apache-2.0. It adds 326 tokens to every session, about $0.0016 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
DeepSeekMeter AGENTS.md
Instructions for CWNU-Open-Source-Community/DeepSeekMeter, covering agents.md — deepseekmeter 仓库操作规范, 1. 项目是什么, 2. 常用命令（改动后必须本地验证）, ios 版验证（核心包自测 + 工程结构静态校验必跑；有 xcode 时还会构建 app 冒烟） and android 核心单测（需 jdk 17 + android sdk；jvm 直跑无需设备）.
zetty AGENTS.md
Instructions for webteractive/zetty, covering zetty — agent & contributor guide, what this is, layout, build / run and design rules ← read before any ui work.
zetty CLAUDE.md
Instructions for webteractive/zetty, covering zetty — agent & contributor guide, what this is, layout, build / run and design rules ← read before any ui work.
Peekaboo AGENTS.md
AGENTS.md instructions for openclaw/Peekaboo, covering repository guidelines, start here, project structure & modules, build, test, and development commands and coding style & naming conventions.
Applite CLAUDE.md
Instructions for milanvarady/Applite, covering claude.md, project overview, build & run, architecture and data flow.
palmier-pro AGENTS.md
AGENTS.md instructions for palmier-io/palmier-pro, covering palmierpro, build, agents, engineering approach and code style.