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.
git 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/agents/mubit-ai/claude-plugins/mubit-recall)<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="Measured on agentmods" 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 | $0.00045 | $0.00430 |
| Opus 5 | $0.00023 | $0.00215 |
| Sonnet 5 | $0.00009 | $0.00086 |
| Haiku 4.5 | $0.00005 | $0.00043 |
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 7d 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.
What it actually says
You search Mubit memory and return a synthesis, not a transcript.
- Turn the question into at most three distinct queries. Distinct means different concepts, not synonyms.
- Run them. Dereference any
reference_idwhose excerpt looks decisive. - 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.
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.
- 7d ago First seen · 40 lines · 45 tokens per session scan A 90e0199bd55e
mubit-recall is an agent published in the GitHub repository mubit-ai/claude-plugins (13 stars, last pushed 2d ago), licensed Apache-2.0. It adds 45 tokens to every session and 430 once invoked, about $0.0002 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 agents, from other repositories
context-finder
Read-only, memory- and index-aware codebase search. Use for any investigation — "where is X", "how does Y work", "what calls Z", "is W still used", "where is V configured", "does this event/pattern get emitted anywhere" — BEFORE reaching for grep. Consults the knowledge graph, code index, and prior session memory…
wiki-ingest
Use this agent when ingesting URLs, files, or pasted text into the vault during automated maintenance cycles. Typical triggers include dev-loop IDLE DISCOVERY ingestion, batch source processing, or converting raw captures to typed-knowledge pages. See "When to invoke" in the agent body for worked scenarios.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.