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/kaeawc/auto-mobile/agents-mdgit clone --depth 1 https://github.com/kaeawc/auto-mobileWhat 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 | $0.02830 | $0.02830 |
| Opus 5 | $0.01415 | $0.01415 |
| Sonnet 5 | $0.00566 | $0.00566 |
| Haiku 4.5 | $0.00283 | $0.00283 |
Grade A, and why
auto-mobile 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 3d 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AutoMobile
Bun TypeScript MCP server providing Android & iOS device automation capabilities through its tools and resources. Kotlin & Swift supporting libraries and apps in android/ and ios/ respectively.
Key Rules
- TypeScript only (no JavaScript)
- Write GitHub issue and pull request references as clickable Markdown links only
in AI-authored prose a human reads directly — issue and PR bodies, review
comments, commit messages, and assistant chat responses — where a clickable
link genuinely aids navigation for the reader. Do NOT require links in
checked-in repository content: neither source code comments (bare
#NNNNis the established convention — 625 references insrc/, zero linked) nor Markdown documentation files (underdocs/and elsewhere), where bare#NNNNis likewise fine. Forcing explicit links into committed files renders as noise in an editor and makes the touched file the only inconsistent one. Automated reviewers (e.g. Codex) must NOT flag bare#NNNNreferences that appear in source-code comments or Markdown files; treat those as compliant. - After implementation changes, run relevant validation commands
- Write terminal output to
scratch/when not visible - Local validation scripts live under
scripts/and should almost always be written in bash with shellcheck validation - Before adding a helper, parser, or dependency, search
src/,scripts/lib/,package.json, and the runtime standard library. Prefer the standard library, then an existing direct dependency, then an existing repository helper, then a small tested helper. Do not parse JSON, YAML, XML, or TypeScript with line regexes when a structured parser or typed module contract exists. For new packages, state which built-in and installed alternatives were checked. Preserve injected interfaces/FakeTimer seams where tests need deterministic control. - Always use interfaces & fakes & FakeTimer to decouple implementations and keep tests extremely fast and non-flaky
- Unit tests should pass in 100ms or less. Do not assume that a failing test can be allowed to fail.
- For Swift, prefer an existing standard-library or Foundation API before adding an extension, helper, or package. Use
URLComponentsplusURLQueryItemfor query values andCodablefor AutoMobile-owned stable schemas. KeepJSONSerializationonly at documented dynamic/bridge boundaries. A convenience dependency requires a stated platform-API gap, deployment-target check, and tests using interfaces/fakes. - For TypeScript changes, prefer the JavaScript/Node standard library, then an existing AutoMobile seam, before adding a local generic helper or direct dependency. Keep time, randomness, I/O, concurrency, and process access injectable when tests need control; justify any new direct dependency in
docs/decisions/. - For Kotlin changes, check the Kotlin stdlib, JDK/AndroidX, the module's existing dependencies, and dependency-compatible AutoMobile modules before adding a helper, wrapper,
*Utilfile, or dependency. Prefer the narrowest existing solution; keep one-off helpers private and adjacent to their consumer. Extract shared code only for two or more real consumers, and state any intentional exception (semantics, performance, API level, compatibility, testability, or readability) in the PR summary.
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.
- 3d ago First seen · 194 lines · 2,830 tokens per session scan A d80763b574b8
auto-mobile AGENTS.md is an instructions file published in the GitHub repository kaeawc/auto-mobile (45 stars, last pushed 3d ago), licensed Apache-2.0. It adds 2,830 tokens to every session, about $0.0141 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
mcp-baepsae AGENTS.md
Instructions for oozoofrog/mcp-baepsae, covering project knowledge base, structure, where to look, code map and conventions.
ConsultMe CLAUDE.md
Instructions for Tarek-Bohdima/ConsultMe, covering claude.md, project context, common commands, module graph and conventions enforced by tooling.
AIBattery CLAUDE.md
Instructions for KyleNesium/AIBattery, covering ai battery — ai agent guide, spec-driven workflow, build & run, bundle and launch and testing.
Clipth AGENTS.md
Instructions for wavever/Clipth, covering agent.md, 这是什么, 目录结构, 本地构建运行 and 代码签名（动签名相关的任何东西前必读）.
ComposeSample CLAUDE.md
Instructions for HeeGyeong/ComposeSample, covering claude.md — composesample project guide, tech stack, module structure, how to add a new example and step 1: add a constant to constvalue.kt.
swift-architecture-skill AGENTS.md
Instructions for efremidze/swift-architecture-skill, covering agents guidelines for swift architecture skill, working with this repository, 1. understanding the skill, 2. modifying architecture playbooks and 3. testing and validation.