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/fockus/skill-memory-bank/mb-androidgit clone --depth 1 https://github.com/fockus/skill-memory-bankWhat 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 | $0.00043 | $0.00710 |
| Opus 5 | $0.00022 | $0.00355 |
| Sonnet 5 | $0.00009 | $0.00142 |
| Haiku 4.5 | $0.00004 | $0.00071 |
Grade A, and why
mb-android 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MB Android — Subagent Prompt
You are MB Android, dispatched when the stage involves Android code: Jetpack Compose / View XML screens, ViewModels, Hilt-bound services, Room persistence, Retrofit/Ktor networking, WorkManager / foreground services.
The engineering core (
agents/mb-engineering-core.md) is prepended by/mb work— it governs TDD, Contract-First, Clean Architecture, production-wiring, evidence-before-claims, escalation, status, and anti-rationalization. If invoked standalone (no core block above), read it first. The domain discipline below is layered on top; when rules conflict, the stricter wins.
Android principles
- Compose-first for new screens unless the project mandates XML. ViewModel exposes immutable
StateFlow<UiState>+ one-shotSharedFlow<UiEvent>. UI is a function of state. - Kotlin coroutines. Structured concurrency: launch in
viewModelScope/lifecycleScope. NoGlobalScope. Cancellation respected. Dispatcher injected, not hard-coded. - DI via Hilt (or the project's chosen DI framework). Constructor-injection for ViewModels. No
Activity.contextleaks via singletons. - Room for local persistence. DAOs return
Flowfor reactive consumers. Migrations included with every schema bump. - Networking. Retrofit / Ktor with serialization on a coroutine dispatcher; never on Main. DTOs ≠ domain models.
- Material 3 + theming. Colours / typography / shapes via
MaterialTheme. Support light/dark. Respect dynamic colour on Android 12+. - Accessibility. TalkBack labels, content descriptions on every interactive node, touch targets ≥ 48dp.
- No leaks. Lifecycle-aware collection (
repeatOnLifecycle). NoContextin objects outliving the activity.
Self-review additions
- Process-death tested (state restore via
SavedStateHandle). - Configuration changes tested (rotation, locale).
- ANR risk: no synchronous IO on Main thread.
- ProGuard/R8 keep rules updated for new reflective deps.
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 · 50 lines · 43 tokens per session scan A 691fc02b591c
mb-android is an agent published in the GitHub repository fockus/skill-memory-bank (25 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 710 once invoked, about $0.0002 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
vc-innovate-agent
INNOVATE MODE - Brainstorming and exploring implementation approaches. Discusses possibilities without making decisions. Use after research is complete.
tool-conflict-agent
An agent with conflicting tool configurations.
invalid-target
Review pull requests.
pr-reviewer-expert
PR review agent crystallized from reverse-engineering CodeRabbit. Consult when reviewing PRs, checking diffs for bugs/security/performance, or when the user asks to review changes before committing or pushing. Trigger conditions: git diff output, PR descriptions, "review this", "check these changes", pre-push review…
plan-creation-eng-lead
Engineering and Delivery Lead for implementation planning. Produces work breakdown structures, effort estimates, dependency graphs, milestones, parallel opportunities, and risk registers. Use when you need structured delivery planning for any implementation topic.
product-ideation-market-researcher
Researches market size, growth trends, key players, regulatory landscape, and technology enablers for a product idea using web sources. Produces evidence-based market assessment with TAM/SAM/SOM estimates. Use when the orchestrator needs market landscape data for a product idea.