agentmods.dev

mobile-security-knowledge

mobile-security-knowledge is a skill for Claude Code, Codex from eaglesakura/agent-skills. It costs 352 tokens per session (2,594 once invoked), scanned A, original, MIT.

A reference guide for applying security practices to mobile apps, backends, Google Cloud Platform, and Firebase projects.

In plain words
What is it for?
Use it when working on authentication, permissions, encryption, cloud services, Firebase, mobile infrastructure, or security-focused implementation reviews.
Why use it?
It helps developers include security requirements during planning and design and catch prohibited patterns during code reviews.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 2repo 1mo ago A scan 352 tokens original MIT

Good fit Use it when working on authentication, permissions, encryption, cloud services, Firebase, mobile infrastructure, or security-focused implementation reviews.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/eaglesakura/agent-skills/mobile-security-knowledge
View source ↗ eaglesakura/agent-skills
Install

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.

Any agent
npx skills add eaglesakura/agent-skills --skill mobile-security-knowledge
Clone the repo
git clone --depth 1 https://github.com/eaglesakura/agent-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for mobile-security-knowledge

README.md
[![agentmods](https://agentmods.dev/badge/skills/eaglesakura/agent-skills/mobile-security-knowledge/github.svg)](https://agentmods.dev/skills/eaglesakura/agent-skills/mobile-security-knowledge)
Your own site
<a href="https://agentmods.dev/skills/eaglesakura/agent-skills/mobile-security-knowledge"><img src="https://agentmods.dev/badge/skills/eaglesakura/agent-skills/mobile-security-knowledge/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.

agentmods 80×15 button for mobile-security-knowledge

Your own site · 80×15
<a href="https://agentmods.dev/skills/eaglesakura/agent-skills/mobile-security-knowledge"><img src="https://agentmods.dev/badge/skills/eaglesakura/agent-skills/mobile-security-knowledge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 352 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,594 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00352 $0.02594
Opus 5.5 $0.00141 $0.01038
Sonnet 5.5 $0.00070 $0.00519
Haiku 4.5 $0.00035 $0.00259

Measured 2mo ago against content hash 05fbdfeb2c39, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mobile-security-knowledge 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 2mo 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.

packages/coding-security/.apm/skills/mobile-security-knowledge/SKILL.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mobile Security Knowledge

公式・OWASP 等を蒸留したセキュリティナレッジを、必要な文書だけ Context に載せて使う SKILL である。 条文の正本は同梱 references/ であり、本 Body にはセキュリティ知識そのものを書かない。 文書の書式は markdown-documentation に従っている（## 概要 / 原則+補足+実装例 / ### DO: / ### DO NOT: / ## 参考リンク）。

いつ使うか

  • /plan.init / Plan モードで実装計画・関連 SKILL 適用を行うとき
  • /coding.requirement で要件・技術要件・セキュリティ要件・暗黙要件を計画へ落とすとき
  • /coding.design で詳細設計し、DO／推奨に沿った実装方針を書くとき
  • /coding.loop（/loop /coding.loop）で DO NOT 監査を含む設計→実装ループを回すとき
  • コードレビュー・セキュリティレビューで、禁止事項（DO NOT）を洗い出すとき
  • 上記以外でも、認証・権限・暗号・クラウド／Firebase／モバイル基盤の話が出たとき

Coding-Commands（plan.init / coding.requirement / coding.design / coding.loop）側は本 SKILL への直リンクを持たない。 同時利用が前提のため、それらのフローに入ったら本 SKILL を自らロードし、探査手順を適用する。

Coding-Commands / Plan 併用時の振る舞い

直リンクが無くても、次の合図があれば本 SKILL をロード済みとして扱う。

合図 本 SKILL での主作業
/plan.init / Plan モード 主題に触れる領域の references/ を Stage 1 で当たり、関連 DO を計画提案に織り込む
/coding.requirement ### DO: を「セキュリティ要件」または「技術要件」（および暗黙的な要件）へ参照付きで提案する
/coding.design 詳細設計が DO に沿い、関連 ### DO NOT: を設計に残さない
/coding.loop / DO NOT 監査 ループのゲートとして関連 DO NOT を照合し、残 0 件になるまで指摘・差し戻しする

engineer-software-requirement / engineer-software-design が「関連 SKILL・ドキュメントの DO / DO NOT を使え」と指示している場合も、その正本探索先として本 SKILL の references/ を使う。

前提

  • ナレッジの正本は同梱 references/（サイト／標準ごとのディレクトリ）
  • 探索手順の正本は markdown-search（Stage 1 → 2 → 3）
  • 文書を新規に書く・直す作業は markdown-documentation（本 SKILL の主用途ではない）

ディレクトリ案内（絞り込み用）

文脈が明確なら Stage 1 の対象を次に絞る。不明なら references/ 全体から始める。

文脈 優先ディレクトリ
Android 実装・マニフェスト・権限・不正対策 references/developer.android.com/（併せて references/mas.owasp.org/）
iOS / Apple 開発者向けセキュリティ references/developer.apple.com/（併せて references/mas.owasp.org/）
OWASP MAS / MASVS / MASTG / Best Practices / Tests（Android・iOS の知識・テスト・Best Practices を含む） references/mas.owasp.org/
Google Cloud IAM・秘密・Cloud Run 等 references/cloud.google.com/
Firebase App Check・Rules・Checklist・環境分離 references/firebase.google.com/

Read the full file on GitHub · 144 lines

Files

What ships with it

60 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.

Changes

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.

  1. 2mo ago First seen · 144 lines · 352 tokens per session scan A 05fbdfeb2c39

Subscribe to this mod's changes

mobile-security-knowledge is a skill published in the GitHub repository eaglesakura/agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 352 tokens to every session and 2,594 once invoked, about $0.0014 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 2026-08-31.

MobileSecurity
Related

mobile-security-knowledge compared with skills from other repositories

mobile-security-knowledge next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mobile-security-knowledgeeaglesakura/agent-skillsSkill21mo agoMITA352Claude Code, Codex
orca-emulator-androidstablyai/orcaSkill118ktodayMITA102Claude Code, Codex
glance-canonical-layoutsandroid/skillsSkill10k2d agoApache-2.0A56Claude Code
android-tombstone-symbolicationdotnet/skillsSkill5.8ktodayMITA176Claude Code
dogfoodcallstack/agent-deviceSkill5.3ktodayMITA55Claude Code
winapp-mauimicrosoft/winappCliSkill1.4ktodayMITA68Claude Code
app_remixrome-os/romeSkill894todayMITA50Claude Code, Codex