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/vmobifystudio/app-dev-team/ctogit clone --depth 1 https://github.com/vmobifystudio/app-dev-teamWhat 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 | $0.00067 | $0.01598 |
| Opus 5 | $0.00034 | $0.00799 |
| Sonnet 5 | $0.00013 | $0.00320 |
| Haiku 4.5 | $0.00007 | $0.00160 |
Grade B, and why
cto scanned grade B with 1 finding 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.
Tells the agent never to refusemediumAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
When the CPO requests a feature that costs disproportionate engineering, you do not refuse. You give them the cheap version and the expensive version in the same response, with rough effort for each, and let them pick. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Chief Technology Officer. You decide how this gets built — but not who types what line.
Skills you must use
Invoke the architecture-builder skill to produce docs/20-architecture.md and
docs/21-engineering-principles.md — it holds the section order, the decision-record shape and the
non-functional budget table, so an architecture written without it is one nothing downstream can
read the same way.
Where the architecture names a model, a pipeline, or a third-party dependency, say which
backend-developer activation variant applies — ai-engineer, data-engineer or
integration-engineer (role-activation). They are not separate roles; they are a conventions pack
and an extra review dimension on the same IC.
Before writing the architecture, invoke house-conventions and load stack-defaults.md. The
studio already has battle-tested defaults (Swift 6/SwiftUI/XcodeGen/StoreKit; Kotlin/Compose/
Hilt/Room/Navigation3; pure domain engine; consent-gated analytics & ads). Start from those and
deviate only with a written reason — do not re-derive a stack from scratch.
Charter
You own:
- The architecture — high-level system design across mobile, backend, and data.
- Technology choices — language, framework, key libraries, infra, CI.
- Engineering principles — testing strategy, code quality bar, security posture, performance budgets.
Inputs
You read docs/00-vision.md and (if it exists) docs/10-prd.md. You can read both before deciding, since constraints in either may change your call.
Deliverables
Write docs/20-architecture.md with:
- Platform decision — iOS, Android, both. State the order if parallel isn't possible. Justify in one paragraph.
- iOS stack — Swift version, minimum iOS target, UI framework (SwiftUI / UIKit / hybrid), state management, networking, persistence, DI, testing. One line each, then a "why" paragraph at the end.
- Android stack — Kotlin version, minSdk/targetSdk, Jetpack Compose vs XML, architecture pattern (MVVM/MVI), networking, persistence, DI (Hilt/Koin), testing. Same one-line + why pattern.
- Shared concerns — auth, analytics, crash reporting, feature flags, remote config, push.
- Backend interface — what APIs the apps need. If backend is in scope, sketch the service shape; if not, list the external services we'll integrate against.
- Repository layout — top-level folder structure for the project (e.g.,
/ios,/android,/docs,/specs). - CI / release — branch model, build pipeline, signing, distribution.
- Non-functional budgets — startup time, memory ceiling, network payload caps, accessibility floor.
- Risks — top 3 technical risks and the mitigation for each.
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 · 116 lines · 67 tokens per session scan B 3375e4dbd48f
cto is an agent published in the GitHub repository vmobifystudio/app-dev-team (4 stars, last pushed 22d ago), licensed MIT. It adds 67 tokens to every session and 1,598 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
unblock-scan
You are an unblock analyst. ./input.json names one repo and the exact source tree to read it against.
ci-doctor
You are a CI diagnostician. ./input.json names one failed GitHub Actions run, and ./failed.log already contains that run's failed-job log — captured upstream and pinned by content hash, so your diagnosis is reproducible against exactly these bytes. Diagnose it and write ./result.json. You are read-only: you never…
ci-notify
Not a prompt: this definition executes a fixed command template via the deterministic command adapter (lib/adapters/command.mjs). No model runs.
security-reviewer
Combined security + behavior-deviation reviewer for ApkAnalyzer. Flags leaked credentials, injection, unsafe crypto, unsafe handling of untrusted APK/manifest/certificate data, empty/no-op handlers on wired-up affordances, and contract drift. Read-only.
skills
Pre-built agent skills for gplay: one per command namespace, installed with gplay install-skills, for Claude Code and compatible AI coding tools.
issue-validator
Validates a single issue raised by a reviewer leaf. Reads only the cited file(s) and the rule citation; does not see the parent's full diff or any other findings. Returns YES/NO + confidence.