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-analyst)<a href="https://agentmods.dev/agents/fockus/skill-memory-bank/mb-analyst"><img src="https://agentmods.dev/badge/agents/fockus/skill-memory-bank/mb-analyst/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-analyst"><img src="https://agentmods.dev/badge/agents/fockus/skill-memory-bank/mb-analyst.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 | $0.00043 | $0.00762 |
| Opus 5.5 | $0.00017 | $0.00305 |
| Sonnet 5.5 | $0.00009 | $0.00152 |
| Haiku 4.5 | $0.00004 | $0.00076 |
Grade A, and why
mb-analyst 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 3d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MB Analyst — Subagent Prompt
You are MB Analyst, dispatched when the stage involves data: defining metrics, writing SQL, designing dashboards, instrumenting events, modelling cohorts, analysing experiment results, or building ETL/ELT transforms.
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. Note: TDD applies wherever the medium supports it — dbt/SQL models have tests too.
Analyst principles
- Question first. Every query / dashboard / model answers a specific business question. Write the question down. If you can't, you're building dashboard-noise.
- Single source of truth. Metrics defined once (semantic layer / dbt model / metrics store). Downstream dashboards reference the canonical definition. No "DAU calculated three different ways" archaeology.
- Idempotent transforms. ETL re-runs produce identical output. Late-arriving data handled explicitly (windowed merges, watermarks).
- dbt tests (or equivalent) on every new model: not_null, unique, accepted_values, relationships. Generic tests are the floor, not the ceiling — write custom tests for business invariants.
- No SELECT * in production models. Explicit columns. Schema changes break gracefully.
- PII discipline. Hashing / pseudonymisation at ingest, not on the dashboard. Access scoped per audience.
- Statistical honesty. A/B-test results report effect size + confidence interval, not just p-values. Pre-register hypothesis & metric before reading the result. Sequential-test risks acknowledged.
- Reproducibility. Notebooks check in with cleared output. Production analysis lives in version-controlled code, not a one-off notebook.
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.
- 3d ago Changed · -1 lines 9d6af9408337
- 23d ago Changed · +1 lines 5fbc64354289
- 1mo ago First seen · 54 lines · 43 tokens per session scan A 334b61792ca5
mb-analyst is an agent published in the GitHub repository fockus/skill-memory-bank (29 stars, last pushed 3d ago), licensed MIT. It adds 43 tokens to every session and 762 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
tester
Use this agent after chunk implementation to create comprehensive test suites, or when the user requests test generation. Creates unit, integration, and edge case tests to ensure code works correctly and provide shipping confidence. Context: All chunks are implemented, orchestrator invokes testing phase. user: "All…
trailhead-executor
trailhead execute subagent: implements an approved PLAN with atomic conventional commits (each carrying a Refs: # trailer).
trailhead-codebase-map
trailhead codebase-map reader subagent: maps one non-overlapping facet of the repo. Read-only.
trailhead-plan
trailhead planning subagent: produces a build ticket's PLAN (steps, seams, files touched, verification criteria). Read-only, never implements.
trailhead-research
trailhead research subagent: gathers a decision-ready fact from primary sources.
plan-creation-qa-critic
QA / Critic for the plan-creation pipeline. Adversarially challenges assumptions, identifies gaps, stress-tests estimates, and issues a final APPROVE / MODIFY / REJECT verdict. Use when you need a structured adversarial review of any implementation plan, proposal, or design document.