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.
npx skills add mubit-ai/claude-plugins --skill memory-healthgit clone --depth 1 https://github.com/mubit-ai/claude-pluginsWrote 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/skills/mubit-ai/claude-plugins/memory-health)<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.
<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>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 | $0.00051 | $0.00717 |
| Opus 5 | $0.00026 | $0.00358 |
| Sonnet 5 | $0.00010 | $0.00143 |
| Haiku 4.5 | $0.00005 | $0.00072 |
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 9d 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 — 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_statusdials the instance. It tells you whether there is something at the other end, whether the key is accepted, and which typedConnStateapplies. It knows nothing about what is stored.mubit_memory_healthasks 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:doctorstep 1 and readrecall.empty_reasonfrom 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_outcomeon the one that turned out false, or/mubit-memory:forgetif 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.
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.
- 9d ago First seen · 51 lines · 51 tokens per session scan A f3cca2feeb33
memory-health is a skill published in the GitHub repository mubit-ai/claude-plugins (13 stars, last pushed today), licensed Apache-2.0. It adds 51 tokens to every session and 717 once invoked, about $0.0003 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 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.
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.…
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…
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.
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…
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.