mb-review

mb-review is a skill for Claude Code, Codex from mrvladd-d/memobank. It costs 18 tokens per session (504 once invoked), scanned A, original, MIT.

A review process for a Memory Bank, a set of project documents that preserve architecture, scope, plans, and decisions between work sessions. It uses several specialist reviews to produce a prioritized list of fixes.

In plain words
What is it for?
Use it to review an existing .memory-bank directory after setup, before execution, or before relying on its project documentation.
Why use it?
It exposes missing information, contradictions, weak links between requirements and tasks, and documentation problems before implementation starts.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Use it to review an existing .memory-bank directory after setup, before execution, or before relying on its project documentation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mrvladd-d/memobank/mb-review
Install

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.

Any agent
npx skills add mrvladd-d/memobank --skill mb-review
Clone the repo
git clone --depth 1 https://github.com/mrvladd-d/memobank

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for mb-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/mrvladd-d/memobank/mb-review/github.svg)](https://agentmods.dev/skills/mrvladd-d/memobank/mb-review)
Your own site
<a href="https://agentmods.dev/skills/mrvladd-d/memobank/mb-review"><img src="https://agentmods.dev/badge/skills/mrvladd-d/memobank/mb-review/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.

agentmods 80×15 button for mb-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/mrvladd-d/memobank/mb-review"><img src="https://agentmods.dev/badge/skills/mrvladd-d/memobank/mb-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 504 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00018 $0.00504
Opus 5 $0.00009 $0.00252
Sonnet 5 $0.00004 $0.00101
Haiku 4.5 $0.00002 $0.00050

Measured 12d ago against content hash 77547a0a2a51, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

mb-review 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 12d 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.

skills/mb-review/SKILL.md · 63 lines

What it actually says

mb-review — Multi-expert Memory Bank review

  • What it does: runs independent reviewers over architecture, scope, task planning, security, and Memory Bank discipline.
  • Use it when: you need a clean review gate before execution, after bootstrap, or before trusting the docs.
  • Input: an existing .memory-bank/.
  • Output: reviewer reports in .tasks/TASK-MB-REVIEW/ plus a synthesized list of fixes and review verdicts.

Goal

Detect gaps, contradictions, broken traceability, and non-compliance early.

This is not the same as per-task semantic verification. Use mb-red-verify when the question is “did this task solve the right problem in substance?”

Preconditions

  • .memory-bank/ exists.

Process

1) Create review task folder

Create:

  • .tasks/TASK-MB-REVIEW/

2) Spawn reviewers (fresh contexts)

Spawn these subagents in parallel (max 5–7):

  1. Architect — ./agents/shared-review-architect.md
  2. Scope/RTM — ./agents/shared-review-scope.md
  3. Task planning — ./agents/shared-review-plan.md
  4. Security — ./agents/shared-review-security.md
  5. MBB compliance — ./agents/shared-mb-reviewer.md
  6. Code quality (conditional: if repo has code) — ./agents/shared-review-code.md

Each reviewer must:

  • write a detailed report to .tasks/TASK-MB-REVIEW/
  • return only a short summary + verdict to the orchestrator

3) Synthesize and decide

As orchestrator:

  • combine findings
  • deduplicate
  • rank issues P0–P3
  • produce a concrete fix plan

If the repo is preparing for /autonomous:

  • treat unresolved P0/P1 issues as blocking
  • do not allow batch execution until the final verdict is APPROVE

4) Gate

If any reviewer returns REJECT:

  • fix MB
  • re-run mb-review

Definition of done

  • .tasks/TASK-MB-REVIEW/ contains the reviewer reports.
  • Orchestrator produced an actionable prioritized fix list.
  • Final verdict: APPROVE.
Changes

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.

  1. 12d ago First seen · 63 lines · 18 tokens per session scan A 77547a0a2a51

Subscribe to this mod's changes

mb-review is a skill published in the GitHub repository mrvladd-d/memobank (55 stars, last pushed 3mo ago), licensed MIT. It adds 18 tokens to every session and 504 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens