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.
git clone --depth 1 https://github.com/mrvladd-d/memobanknpx agentmods add commands/mrvladd-d/memobank/mb-doctorWrote 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/commands/mrvladd-d/memobank/mb-doctor)<a href="https://agentmods.dev/commands/mrvladd-d/memobank/mb-doctor"><img src="https://agentmods.dev/badge/commands/mrvladd-d/memobank/mb-doctor/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/commands/mrvladd-d/memobank/mb-doctor"><img src="https://agentmods.dev/badge/commands/mrvladd-d/memobank/mb-doctor.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 | $0.00018 | $0.02249 |
| Opus 5 | $0.00009 | $0.01125 |
| Sonnet 5 | $0.00004 | $0.00450 |
| Haiku 4.5 | $0.00002 | $0.00225 |
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 10d 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 — 161 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, /verify, or /red-verify.
Command
Use the repository-provided script:
node scripts/mb-doctor.mjs
node scripts/mb-doctor.mjs --strict
node scripts/mb-doctor.mjs --json
node scripts/mb-doctor.mjs --strict --json
If the repository exposes another documented wrapper for the same script, use that wrapper.
Modes
- Default mode: health report for humans and interactive work. A fresh skeleton with an empty
.memory-bank/tasks/index.jsonis valid and reportsTASK_INDEX_EMPTYasinfo. - Strict mode: post-queue autonomous/autopilot readiness gate. Empty
.memory-bank/tasks/index.jsonis 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.
Use --strict before /autopilot or the scheduler phase of /autonomous, before each task-selection pass, and after each /mb-sync before promoting dependents or declaring success.
Status transitions have two modes. In scheduler mode, /autopilot and /autonomous own closure/failure/blocking decisions, T2/T3 scheduler closure requires VERDICT: PASS plus SEMANTIC_VERDICT: semantic-pass, and T3 scheduler closure also requires exact HUMAN_CHECKPOINT: done and ROLLBACK_RECOVERY_NOTE: present. In manual mode, /verify PASS may close only T0/T1 with explicit closure ownership; T2/T3 require /red-verify SEMANTIC_VERDICT: semantic-pass before final closure//mb-sync.
Required checks
mb-doctor must check only readiness-critical conditions:
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.
- 10d ago First seen · 161 lines · 18 tokens per session scan A a6fefdaf09ac
mb-doctor is a command published in the GitHub repository mrvladd-d/memobank (55 stars, last pushed 3mo ago), licensed MIT. It adds 18 tokens to every session and 2,249 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.
Other commands, from other repositories
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
learn
Force claude-smart to extract learnings from this session now.
memory-store
Store an insight, decision, or pattern to memory.
cc-memory
Configure persistent memory that survives across sessions using a layered approach: split rule files for always-loaded context, auto-memory for organic learning, and optional MCP-backed long-term memory for large codebases.
analyze-context
USE WHEN you want to analyze project context before starting work on a task. Calls context + recall, then synthesizes goals, decisions, gotchas, and relevant memories into a pre-task brief.
lians-recall
Recall current (non-stale) facts from Lians memory, optionally as-of a past date.