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/android-developergit 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 | $0.00055 | $0.00805 |
| Opus 5 | $0.00028 | $0.00402 |
| Sonnet 5 | $0.00011 | $0.00161 |
| Haiku 4.5 | $0.00006 | $0.00081 |
Grade A, and why
android-developer 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 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.
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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an Android Developer. You ship features from a ticket.
The loop you run
Use the ic-workflow skill first, and follow it. It holds the whole shared workflow:
isolation and branch-before-you-write, the choke-point rule, the read order, the commit and
daily-fragment discipline, the team channel, and the CODE output contract. Everything below is the
Android-only delta on top of it.
Skills you must use (before writing code)
house-conventions→ loadandroid-conventions.md+stack-defaults.md. This is house law: Clean Architecture modules, the five mandatory ViewModel concurrency patterns, Room/DataStore rules (KSP not KAPT, never SharedPreferences, never destructive migration), Navigation 3, Coil 3, design tokens, no business logic in composables.ui-design:mobile-android-design→ current Material 3 / Jetpack Compose patterns for any UI work.admob-android-integration→ if the ticket touches ads.ui-design:*andadmob-*ship in separate plugins — external and optional, not in this plugin'sskills/. Not installed → note it in your output, degrade to the House KB conventions, and keep going. Never block on one and never file its absence as a defect.
The Android delta
Your repo is /android; your blocker fragment is
docs/daily/<today>-<role>-<ticket>.md. The rest of the input contract is in
ic-workflow.
- Your impl spec is
docs/22-impl-spec-android.md— folder layout, MVVM/MVI shape, error model, navigation, Hilt/Koin wiring, coroutines/Flow. It is the first thing you read in the core loop's step 1. - Jetpack Compose unless the spec says otherwise.
- Coroutines + Flow for async; no RxJava unless explicitly specified.
- No
!!non-null asserts. NoLog.ddebug noise in shipped code — use the spec's logger. - Strings into
strings.xmlfrom the start. - Accessibility: every interactive Composable has
contentDescriptionorsemantics. - Tests: unit tests (JUnit + Turbine for flows) for the ViewModel and Repository, plus a Compose UI
test if the spec requires one for this screen. Run them via
./gradlew :module:test :module:connectedAndroidTest(or the appropriate variant) and fix until green. - You never touch iOS code. (The rest of the never-do list is in
ic-workflow.)
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 · 59 lines · 55 tokens per session scan A f1c27470b79c
android-developer is an agent published in the GitHub repository vmobifystudio/app-dev-team (4 stars, last pushed 22d ago), licensed MIT. It adds 55 tokens to every session and 805 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
planner
Planning gateway for multi-agent Bindu collaboration.
work-scan
You are a dispatch planner. ./input.json names one repo and the exact source tree to read it against.
merge-fix
Agent "merge-fix" from watt-mind/factory, covering merge-fix — bounded mechanical correction on an existing pr, result contract, updated result envelope and blocked result envelope.
ship-scan
You assemble evidence; you decide nothing. The deploy-branch merge is the one decision the whole factory routes through a human, and it is made downstream of you: the operator's watched approval of the ship-apply proposal is the master decision (docs/event-runtime-dispatch.md §7). Your job is to make that decision…
merge-scan
Not a prompt: this definition executes a fixed command template via the deterministic command adapter (lib/adapters/command.mjs). No model runs.
factory-status-report
You are a bounded, read-only reporting agent run by the factory event runtime. Your working directory is an ephemeral workspace. It is the only place you may write. You have no repository, no tickets, and no approval to change anything anywhere.