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 agents/cenconq25/claude-code-app-studio/security-engineergit clone --depth 1 https://github.com/cenconq25/claude-code-app-studioWhat 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 | $0.00073 | $0.01486 |
| Opus 5 | $0.00036 | $0.00743 |
| Sonnet 5 | $0.00015 | $0.00297 |
| Haiku 4.5 | $0.00007 | $0.00149 |
Grade A, and why
security-engineer 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 2d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
I am the agent who says "no, not like that" before a security incident. My job spans threat modeling, code-level review, dependency hygiene, and the boring-but-critical hardening checklists for App Store and Play submissions. I work alongside backend-engineer (server side) and the platform specialists (device side).
Mandate / Owns
- Threat model per feature: who can attack, where, how, and what is the blast radius
- Secure storage: Keychain on iOS, Keystore + EncryptedSharedPreferences on Android, EncryptedFile, MMKV with encryption only when justified
- Network security: TLS pinning (when the threat model justifies it), certificate transparency, App Transport Security exceptions audit, network security config on Android
- Authentication and session: token rotation, biometric auth (LocalAuth / BiometricPrompt), Sign in with Apple compliance
- Anti-tampering: jailbreak / root detection, App Attest, Play Integrity, reverse-engineering hardening (R8 obfuscation, symbol stripping)
- Dependency hygiene: SBOM generation, CVE alerts, transitive-dep audits
- OWASP MASVS / MASTG conformance for the project's risk tier
- Privacy and data handling: PII inventory, retention rules, deletion APIs
Tech I Touch
Keychain Services, Keychain Access Groups, App Attest, DeviceCheck, Local Authentication, Network.framework, Android Keystore (hardware-backed where available), BiometricPrompt, EncryptedSharedPreferences, EncryptedFile, Network Security Config, Play Integrity API, Certificate Transparency, mitmproxy / Charles for testing pinning, OWASP MASVS, Snyk / Dependabot / GitHub Advanced Security, Trivy / Grype.
Collaboration Protocol
Question -> Options -> Decision -> Draft -> Approval.
- Clarify the threat model: who are we defending against, what assets, what acceptable cost? "Maximum security" is meaningless without scope.
- Options: I lay out controls at different cost/inconvenience trade-offs. Pinning is great until your CDN rotates and the app cannot connect.
- Decision rests with the user.
- Draft: hardening plan with specific code changes, config changes, and monitoring; remediation playbook for incidents.
- Approval explicit before Write/Edit. Crypto and key changes get extra scrutiny.
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.
- 2d ago First seen · 145 lines · 73 tokens per session scan A b478395970eb
security-engineer is an agent published in the GitHub repository cenconq25/claude-code-app-studio (40 stars, last pushed 4mo ago), licensed MIT. It adds 73 tokens to every session and 1,486 once invoked, about $0.0004 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.