memory-health

memory-health is a skill for Claude Code from mubit-ai/claude-plugins. It costs 28 tokens per session (695 once invoked), scanned A, original, Apache-2.0.

A health report for Mubit memory, a stored collection of information used by the system. It examines entry counts, outdated information, contradictions, and the condition of each section.

In plain words
What is it for?
Use it to inspect what is actually stored in memory and identify missing, old, or conflicting entries.
Why use it?
It distinguishes an empty or stale memory store from a connection problem, which requires a different diagnosis.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Part of the mubit-memory plugin — 15 skills, 1 agent, 13 hooks, 1 MCP server shipped together

Good fit Use it to inspect what is actually stored in memory and identify missing, old, or conflicting entries.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mubit-ai/claude-plugins/memory-health
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 mubit-ai/claude-plugins --skill memory-health
Clone the repo
git clone --depth 1 https://github.com/mubit-ai/claude-plugins

Made for: Claude Code.

Or install mubit-memory, the plugin that ships this one along with the rest of its 15 skills, 1 agent, 13 hooks, 1 MCP server.

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 memory-health

README.md
[![agentmods](https://agentmods.dev/badge/skills/mubit-ai/claude-plugins/memory-health/github.svg)](https://agentmods.dev/skills/mubit-ai/claude-plugins/memory-health)
Your own site
<a href="https://agentmods.dev/skills/mubit-ai/claude-plugins/memory-health"><img src="https://agentmods.dev/badge/skills/mubit-ai/claude-plugins/memory-health/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 memory-health

Your own site · 80×15
<a href="https://agentmods.dev/skills/mubit-ai/claude-plugins/memory-health"><img src="https://agentmods.dev/badge/skills/mubit-ai/claude-plugins/memory-health.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 695 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 $0.00028 $0.00695
Opus 5.5 $0.00011 $0.00278
Sonnet 5.5 $0.00006 $0.00139
Haiku 4.5 $0.00003 $0.00069

Measured 1mo ago against content hash 5f96b164d424, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

memory-health 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 1mo 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.

integrations/claude-code/skills/memory-health/SKILL.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Call mubit_memory_health — POST /v2/control/memory_health — and report what it says about the store. limit (1 to 500) is how many entries it samples; the default is enough unless the user is specifically asking about an old part of a large run.

This inspects the store. mubit_status inspects the connection.

The two answer different questions and are easy to confuse, because both fail as "memory isn't working".

  • mubit_status dials the instance. It tells you whether there is something at the other end, whether the key is accepted, and which typed ConnState applies. It knows nothing about what is stored.
  • mubit_memory_health asks what is in there: how many entries, how stale they are, whether any of them contradict each other, and how each section is doing. It says nothing about the connection — if the instance is unreachable this call does not answer at all.

So a healthy connection over an empty store and a full store behind a dead endpoint look identical from the status line, and they have opposite fixes. Answer the question the user actually asked before offering a remedy for the other one.

Reading the answer

  • Zero entries, connection fine. Nothing was ever written. Check that capture is on, and remember that an accepted ingest is queued, not stored — a run that just started can be legitimately empty for a minute.
  • Entries present, but recall keeps returning nothing. The store is not the problem. That is a retrieval or scope question: go to /mubit-memory:doctor step 1 and read recall.empty_reason from the local status marker, which names the cause outright.
  • Contradictions. Two stored lessons that disagree. Neither is automatically wrong and deleting both loses the argument: prefer a negative mubit_outcome on the one that turned out false, or /mubit-memory:forget if it should never have existed. Report the pair to the user rather than picking a winner yourself.
  • Staleness. Old is not broken. Say so — a lesson that has not been touched in months is usually one that has not been contradicted either.

Read the full file on GitHub · 51 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. 1mo ago Changed · -23 tokens per session 5f96b164d424
  2. 2mo ago First seen · 51 lines · 51 tokens per session scan A f3cca2feeb33

Subscribe to this mod's changes

memory-health is a skill published in the GitHub repository mubit-ai/claude-plugins (12 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 28 tokens to every session and 695 once invoked, about $0.0001 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.

Related

memory-health compared with skills from other repositories

memory-health next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
memory-healthmubit-ai/claude-pluginsSkill121mo agoApache-2.0A28Claude Code
knowledge-ingestopenclaw/openclawSkill394kyesterdayMITA80Claude Code, Codex
mem0-oss-to-platformmem0ai/mem0Skill68k2d agoApache-2.0A217Claude Code, Codex
forgetasgeirtj/system_prompts_leaksSkill71k2d agoCC0-1.0A74Claude Code, Codex
Cortexdanielmiessler/LifeOSSkill20kyesterdayMITA184Claude Code
memoryopensquilla/opensquillaSkill7.1k6d agoApache-2.0A44Claude Code, Codex
ha-data-storesshiwenwen/hope-agentSkill1.9kyesterdayMITA115Claude Code, Codex