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 skills add niki914/zafiro --skill assistant-add-supportgit clone --depth 1 https://github.com/niki914/zafiroWrote 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/skills/niki914/zafiro/assistant-add-support)<a href="https://agentmods.dev/skills/niki914/zafiro/assistant-add-support"><img src="https://agentmods.dev/badge/skills/niki914/zafiro/assistant-add-support/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/niki914/zafiro/assistant-add-support"><img src="https://agentmods.dev/badge/skills/niki914/zafiro/assistant-add-support.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00061 | $0.01005 |
| Opus 5.5 | $0.00024 | $0.00402 |
| Sonnet 5.5 | $0.00012 | $0.00201 |
| Haiku 4.5 | $0.00006 | $0.00101 |
Grade A, and why
assistant-add-support 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
assistant-add-support
为语音助手宿主适配新版本 Xposed 接管支持:提取/分析 APK、比对 Hook 点变化、生成新版本配置并完成编译验证。
宿主分支
根据目标宿主查阅对应的核心类清单与指引:
- Breeno(小布助手,
com.heytap.speechassist):阅读docs/BREENO.md - XiaoAi(小爱同学,
com.miui.voiceassist):阅读docs/XIAOAI.md(当前留空不支持)
前置环境与依赖门禁
1. REA (Reverse Engineer Anything) 门禁
优先使用 REA 分析引擎(MCP / CLI)审查 APK 内部类与方法签名。
- 上游仓库:
https://github.com/morluto/rea - 严格授权门禁:当且仅当 REA 不可用时,提示用户需先部署 REA,严禁私自自动安装或配置,由用户自主决定。
2. 提取与反编译工具
- 使用项目内的
extract-apk技能(.agents/skills/extract-apk/scripts/)定位并导出目标 APK。 - 反编译按需进行:若需全局搜索则调用
decompile_apk.py,若只需针对性核对类结构可直接用 REA MCP 直连 APK。
适配流程
Phase 1: 确认目标版本
- 通过
adb -s <serial> shell dumpsys package <package_name> | grep -E "versionCode|versionName"获取设备上的版本信息; - 与用户确认目标版本号与
versionCode。
Phase 2: 提取 APK
运行 extract_apk.py 拉取当前版本 APK。根据分析需要决定是否执行全量反编译。
Phase 3: 调研现有 Hook 机理与签名比对
- 查阅宿主分支指引(如
docs/BREENO.md),了解宿主核心类角色; - 以最近一个已支持版本的
app/src/main/res/raw/<package_name>_<prevVersion>_config.json作为基准模板(配置结构即 Single Source of Truth); - 在新版本中核对配置中涉及的每个类名、方法名与签名;
- 列出变动清单(未变 / 变动的具体点位)。
Phase 4: 实现新版本配置与编译验证
- 在
app/src/main/res/raw/新建<package_name>_<versionCode>_config.json,填入新签名的配置; - 在
app/src/main/res/raw/<package_name>_versions.json追加新<versionCode>; - 在
app/src/main/java/a0/a0/a0/a0/a0/a0/Entrance.kt的configRawIdFor中注册对应 raw 资源映射; - 同步运行
./gradlew :app:compileDebugKotlin验证编译。
Phase 5: 交付与安装门禁(严格被动)
- 严格被动原则:严禁主动向设备执行安装、推送或任何写操作!默认仅完成代码修改与编译验证,向用户汇报改动并等待代码审查(CR)。
- 仅当用户明确要求安装时:
- 执行打包:
./gradlew :app:assembleDebug - 推送并使用
pm安装:adb -s <serial> push app/build/outputs/apk/debug/app-debug.apk /data/local/tmp/app-debug.apk adb -s <serial> shell pm install -r -d -g /data/local/tmp/app-debug.apk adb -s <serial> shell rm -f /data/local/tmp/app-debug.apk - 重启宿主使 Xposed 模块生效:
adb -s <serial> shell am force-stop <package_name>
- 执行打包:
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 72 lines · 61 tokens per session scan A fa3d1aa0d6b6
assistant-add-support is a skill published in the GitHub repository niki914/zafiro (259 stars, last pushed yesterday), licensed MIT. It adds 61 tokens to every session and 1,005 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-11.
Other skills, from other repositories
compose-performance
Use when investigating Jetpack Compose recomposition cost, compiler stability reports, skippability, unstable parameters, frame-rate State reads, cross-phase snapshot back-writing, or @ReadOnlyComposable contracts.
flutter-error-handling
Implement functional repository error recovery with Either/Failure patterns in Flutter. Use when handling exceptions or dartz Either types in data flows; defer UI-only retry buttons.
kotlin-expert
Expert-level Kotlin development, Android, coroutines, and multiplatform. Use when the user mentions Android, coroutines, multiplatform, or JVM, or when the task involves Kotlin Fundamentals, Android Development, Kotlin Multiplatform, or Kotlin Style.
phone-harness
Use when an agent needs to control a real phone — iPhone via Mac iPhone Mirroring or Android via adb (open apps, tap, type, swipe, OCR the screen). Android path runs on this Linux workstation (adb), targets phonefarm devices. iOS path needs macOS + iPhone Mirroring. Use for phonefarm device debugging, OTP/2FA flows…
context-collector
Deep architecture recovery, context gathering, and root cause analysis for unfamiliar or undocumented codebases. Use when asked to analyze a codebase, understand its architecture, map dependencies, gather context before a task, do architecture recovery, explore an unknown repo, or investigate a production…
dagger-hilt-expert
Expert guidance for Dagger and Hilt dependency injection in Android. Use when implementing DI, creating modules, configuring scopes, optimizing performance, testing with Hilt, setting up multi-module architecture, using assisted injection, or debugging DI issues. Triggers on "dagger", "hilt", "dependency injection"…