mb-doctor

mb-doctor is a command for Claude Code from nicelight/DevRails-26. It costs 18 tokens per session (4,627 once invoked), scanned A, original, MIT.

A readiness check for a project's Memory Bank, the collection of files that records project context, decisions, tasks, and workflow state.

In plain words
What is it for?
Use it to run normal or strict checks, optionally as JSON, and find documentation or task-index problems before automated execution.
Why use it?
It tells you whether autonomous or autopilot work can safely continue from the current project records.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node .memory-bank/scripts/mb-doctor.mjs.

Good fit Use it to run normal or strict checks, optionally as JSON, and find documentation or task-index problems before automated execution.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/nicelight/DevRails-26
agentmods
npx agentmods add commands/nicelight/devrails-26/mb-doctor

Made for: Claude Code.

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-doctor

README.md
[![agentmods](https://agentmods.dev/badge/commands/nicelight/devrails-26/mb-doctor.svg)](https://agentmods.dev/commands/nicelight/devrails-26/mb-doctor)
Your own site
<a href="https://agentmods.dev/commands/nicelight/devrails-26/mb-doctor"><img src="https://agentmods.dev/badge/commands/nicelight/devrails-26/mb-doctor.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,627 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 $0.04627
Opus 5 $0.00009 $0.02313
Sonnet 5 $0.00004 $0.00925
Haiku 4.5 $0.00002 $0.00463

Measured 8d ago against content hash b99a866b6fa3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

mb-doctor 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 8d 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/mb-doctor.md · 307 lines

How it starts

The opening of the file, as written. The whole thing — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/mb-doctor — Memory Bank readiness doctor

Objective

Answer one question:

Can autonomous/autopilot execution continue safely from the current Memory Bank state?

mb-doctor is a readiness gate over mb-lint. It does not replace /review-feat-plan, /review-tasks-plan, /verify, or /red-verify.

Command

Use the repository-provided script:

node .memory-bank/scripts/mb-doctor.mjs
node .memory-bank/scripts/mb-doctor.mjs --strict
node .memory-bank/scripts/mb-doctor.mjs --json
node .memory-bank/scripts/mb-doctor.mjs --strict --json

If the repository exposes another documented wrapper for the same script, use that wrapper.

Any argument other than --strict, --json, --help, or -h produces the CLI_INVALID_ARGUMENT error before readiness checks run. When --help or -h is present, the script prints help and exits without running readiness checks.

Modes

  • Default mode: health report for humans and interactive work. A fresh skeleton with an empty .memory-bank/tasks/index.json is valid and reports TASK_INDEX_EMPTY as info.
  • Strict mode: post-queue executable-readiness gate for every FT-000 foundation queue and for autonomous/autopilot product queues. Empty .memory-bank/tasks/index.json is an error because there is no executable task queue.
  • JSON mode: machine-readable report for schedulers and agents.

Default mode may emit warnings for incomplete scheduler readiness evidence that should be fixed before unattended execution. These warnings do not invalidate KISS manual closure. Strict mode promotes those readiness gaps to errors where autonomous/autopilot progression would be unsafe. Every non-empty indexed queue requires the current .memory-bank/foundation.md decision; a missing or incomplete decision is a warning in default mode and an error in --strict. Empty-index behavior is unchanged.

After /spec-init PASS, .memory-bank/spec-backbone.md may correctly have Pre-PRD Spec Status: ready_for_prd while Global Backbone Status is still absent, blocked, or otherwise incomplete. In default mode, report this as "prepared for /prd-to-features; Global Backbone Status intentionally pending until /spec-design" rather than a fix-now problem. The machine-readable finding code may remain SPEC_BACKBONE_NOT_READY; the meaning is downstream task/autonomous readiness, not failure of /spec-init.

Read the full file on GitHub · 307 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. 8d ago First seen · 307 lines · 18 tokens per session scan A b99a866b6fa3

Subscribe to this mod's changes

mb-doctor is a command published in the GitHub repository nicelight/DevRails-26 (22 stars, last pushed 3d ago), licensed MIT. It adds 18 tokens to every session and 4,627 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.