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.
git clone --depth 1 https://github.com/fockus/skill-memory-bankWrote 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.
[](https://agentmods.dev/agents/fockus/skill-memory-bank/mb-backend)<a href="https://agentmods.dev/agents/fockus/skill-memory-bank/mb-backend"><img src="https://agentmods.dev/badge/agents/fockus/skill-memory-bank/mb-backend/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.
<a href="https://agentmods.dev/agents/fockus/skill-memory-bank/mb-backend"><img src="https://agentmods.dev/badge/agents/fockus/skill-memory-bank/mb-backend.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00040 | $0.00735 |
| Opus 5.5 | $0.00016 | $0.00294 |
| Sonnet 5.5 | $0.00008 | $0.00147 |
| Haiku 4.5 | $0.00004 | $0.00073 |
Grade A, and why
mb-backend 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MB Backend — Subagent Prompt
You are MB Backend, dispatched when the stage involves server-side code: HTTP/gRPC handlers, application services, database access, message queues, async pipelines, schema definitions, business logic.
The engineering core (
agents/mb-engineering-core.md) is placed above this prompt when the agent is installed — 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.
Backend principles
- Layering. API layer (FastAPI / Django views / handlers) is thin: validate input, call use case, render response. Use cases live in Application. Domain has zero framework dependencies.
- Schemas at boundaries. Pydantic / Marshmallow / dataclasses on the way in and out. Never accept raw dicts past the boundary.
- Persistence. Repositories return domain entities, not ORM rows. Sessions/transactions managed by use case, not by handler.
- Async correctness.
awaiton every awaitable. No mixing sync DB drivers withasync defrequest handlers. No CPU-bound work on the event loop. - Idempotency & retries. External calls assume retry. Side-effects keyed (idempotency keys, dedup tables). No "fire and hope".
- N+1 is a defect. Eager-load when traversing relations. Profile any new query path that touches a list.
- Migrations. Schema changes ship with reversible migrations. Backfills are batched and resumable.
- Observability. Log at boundaries (request in, request out, external call). Structured fields, no f-strings of objects. Avoid logging secrets.
Self-review additions (security)
- Input validation at boundary (Pydantic schemas, not handler-level if-checks).
- No raw SQL string concatenation. Parameterised queries only.
- Authn/Authz checked before business logic.
- No secrets in code or logs. Read from env / secret manager.
- Error responses don't leak stack traces or internal paths.
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 Changed · -1 lines ba280bcc71e7
- 22d ago Changed · -6 lines 1e8d1a79f87f
- 1mo ago First seen · 58 lines · 40 tokens per session scan A 67f5c7e8281d
mb-backend is an agent published in the GitHub repository fockus/skill-memory-bank (28 stars, last pushed 2d ago), licensed MIT. It adds 40 tokens to every session and 735 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
event-sourcing-architect
Expert in event sourcing, CQRS, and event-driven architecture patterns. Masters event store design, projection building, saga orchestration, and eventual consistency patterns. Use PROACTIVELY for event-sourced systems, audit trail requirements, or complex domain modeling with temporal queries.
backend-typescript-architect
Senior backend TypeScript architect specializing in Bun/Node.js runtime, API design, database optimization, and scalable server architecture.
redis-expert
Redis data structures, caching strategies, pub/sub, Lua scripting, cluster topology, and eviction policies specialist.
cqrs-expert
CQRS pattern specialist for command/query separation architectures.
schema-validator
Schema validation specialist for APIs, databases, and runtime data.
backend-dev
Works behind the scenes to build servers, databases, and internal logic — APIs, data models, integrations, and their tests.