review

review is a command for Claude Code, Codex from mrvladd-d/memobank. It costs 28 tokens per session (2,031 once invoked), scanned A, original, MIT.

A command that asks several specialist reviewers to inspect a project's Memory Bank, a folder of requirements, design notes, and task records, using a fresh working context for each review.

In plain words
What is it for?
Use it to review architecture, requirement coverage, task plans, security, compliance, and—when code exists—code quality.
Why use it?
It finds conflicting requirements, missing links, security concerns, planning problems, and rule violations before work proceeds.

Command for Claude CodeCodex

Written for Codex and Claude Code: runs codex exec, but also a Claude Code command (commands/*.md). Also seen: mentions Codex.

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.

agentmods
npx agentmods add commands/mrvladd-d/memobank/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 review

README.md
[![agentmods](https://agentmods.dev/badge/commands/mrvladd-d/memobank/review.svg)](https://agentmods.dev/commands/mrvladd-d/memobank/review)
Your own site
<a href="https://agentmods.dev/commands/mrvladd-d/memobank/review"><img src="https://agentmods.dev/badge/commands/mrvladd-d/memobank/review.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,031 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00028 $0.02031
Opus 5 $0.00014 $0.01015
Sonnet 5 $0.00006 $0.00406
Haiku 4.5 $0.00003 $0.00203

Measured 6d ago against content hash 6008aaec3589, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

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 6d 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/_shared/references/commands/review.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/review — Multi-expert Memory Bank review

Это не per-task adversarial semantic verification. Для вопроса "решение по существу правильное?" используй /red-verify TASK-<ID>.

0) Артефакты

Создай:

  • .tasks/TASK-MB-REVIEW/
  • .tasks/TASK-MB-REVIEW/REQUEST.md (что ревьюим, какой режим, какие blocking concerns)

Каждый reviewer пишет отчёт в:

  • .tasks/TASK-MB-REVIEW/TASK-MB-REVIEW-<STAGE_ID>-final-report-docs-01.md

1) Запусти reviewers (fresh context)

Canonical STAGE_ID table:

STAGE_ID Reviewer
S-01 Architect (C4 + boundaries + ADR)
S-02 Scope/RTM (REQ→EP→FT)
S-03 Plan/tasks (JSON records/index/waves/gates)
S-04 Security
S-05 MBB compliance
S-06 Code quality (optional, if code exists)

Constitution checks are blocking:

  • If .memory-bank/constitution.md exists, reviewers must flag contradictions between the Constitution and Memory Bank docs, task records, workflow routing, implementation plans, or proposed execution.
  • A Constitution violation is a blocking finding and must result in REJECT until fixed or explicitly resolved through /constitution.
  • Do not treat missing domain-specific principles as a violation unless another normative source requires them.

Analysis Quality checks are conditional:

  • If .memory-bank/analysis/product-brief.md exists, include a lightweight pass in S-02 or S-05.
  • Do not fail a project merely because Analysis artifacts are absent; Analysis before PRD is optional.
  • If a product brief exists, check that PRD / requirements / epics / features are traceable to it or explicitly document deltas.
  • Check that the brief is not blocked / no-go / not ready with unresolved blocking questions unless /prd recorded an explicit user override.
  • If brainstorming artifacts exist without a product brief, report a warning unless an existing PRD was intentionally used as the upstream source.
  • Confirm there is no route from Analysis or Product Brief directly to /prd-to-tasks without /write-prd, /spec-init, /prd, /spec-design, and /spec-improve; /clarify-feature is optional and only for explicit feature blockers.
  • Confirm shared T2/T3 design concerns are not duplicated across feature-local specs when /spec-design should have produced a common authoritative backbone.

Read the full file on GitHub · 101 lines

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. 6d ago First seen · 101 lines · 28 tokens per session scan A 6008aaec3589

Subscribe to this mod's changes

review is a command published in the GitHub repository mrvladd-d/memobank (55 stars, last pushed 3mo ago), licensed MIT. It adds 28 tokens to every session and 2,031 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.