mubit-recall

mubit-recall is an agent for Claude Code from mubit-ai/claude-plugins. It costs 45 tokens per session (430 once invoked), scanned A, original, Apache-2.0.

Instructions for searching Mubit’s stored memory from several angles and returning a short synthesis with supporting reference IDs. Mubit is a memory system for saved project or conversation knowledge.

In plain words
What is it for?
Investigating remembered facts, combining supporting entries, handling conflicting evidence, and clearly reporting when memory contains nothing useful.
Why use it?
They help an agent answer “what do we know?” questions from multiple searches without dumping raw search results into the main conversation.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

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

Good fit Investigating remembered facts, combining supporting entries, handling conflicting evidence, and clearly reporting when memory contains nothing useful.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/mubit-ai/claude-plugins/mubit-recall
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.

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 mubit-recall

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/mubit-ai/claude-plugins/mubit-recall"><img src="https://agentmods.dev/badge/agents/mubit-ai/claude-plugins/mubit-recall.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 430 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 $0.00045 $0.00430
Opus 5.5 $0.00018 $0.00172
Sonnet 5.5 $0.00009 $0.00086
Haiku 4.5 $0.00005 $0.00043

Measured 2mo ago against content hash 90e0199bd55e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mubit-recall 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 2mo 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/agents/mubit-recall.md · 40 lines

What it actually says

You search Mubit memory and return a synthesis, not a transcript.

  1. Turn the question into at most three distinct queries. Distinct means different concepts, not synonyms.
  2. Run them. Dereference any reference_id whose excerpt looks decisive.
  3. Return the answer, then a short list of supporting reference_ids with a one-line gloss each.

Never return raw evidence blobs. The caller wants the conclusion; the whole point of running you in a separate context is that the evidence does not land in theirs.

What a good answer looks like

<Two to six sentences answering the question directly. Say what memory establishes, and
say plainly where it is silent — an honest gap is more useful than a confident guess.>

Evidence:
- <reference_id> — <one line: what this entry says and why it mattered>
- <reference_id> — <one line>

Nothing else. No query log, no per-result dumps, no "I searched for X and found Y" narration. If two entries disagree, say so in one sentence and prefer the more recent or the one with more reinforcement — do not paste both and leave the caller to arbitrate.

If all three queries come back empty, say exactly that in one line. Empty is a real answer and the caller needs it quickly; do not spend your remaining turns rephrasing the same query.

You have three turns. Spend them on retrieval and one dereference pass, not on deliberation.

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. 2mo ago First seen · 40 lines · 45 tokens per session scan A 90e0199bd55e

Subscribe to this mod's changes

mubit-recall is an agent published in the GitHub repository mubit-ai/claude-plugins (12 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 45 tokens to every session and 430 once invoked, about $0.0002 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

mubit-recall compared with agents from other repositories

mubit-recall next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mubit-recallmubit-ai/claude-pluginsAgent121mo agoApache-2.0A45Claude Code
context-finderfuturegerald/futuregerald-claude-pluginAgent72d agononeA107Claude Code
wiki-ingestkarlorz/llm-wikiAgent5yesterdaynoneA64Claude Code
memory-curatorwbind-core/termpipe-mcpAgent04d agononeA45Claude Code
data scientistkhalilbenaz/MDANAgent023d agoMITA8Claude Code
playwright-test-generatormicrosoft/playwrightAgent99kyesterdayApache-2.0A151Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginnersAgent79k4d agoMITA33Claude Code