Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add mubit-ai/claude-plugins/plugin install mubit-memoryWrote 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/auth)<a href="https://agentmods.dev/skills/mubit-ai/claude-plugins/auth"><img src="https://agentmods.dev/badge/skills/mubit-ai/claude-plugins/auth/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/auth"><img src="https://agentmods.dev/badge/skills/mubit-ai/claude-plugins/auth.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 | $0.00026 | $0.01566 |
| Opus 5.5 | $0.00010 | $0.00626 |
| Sonnet 5.5 | $0.00005 | $0.00313 |
| Haiku 4.5 | $0.00003 | $0.00157 |
Grade A, and why
auth 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.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This skill never installs anything. It opens a browser, receives a key, checks it against the instance, and writes it to one file. It does not install packages, start services, or touch the user's shell profile. A memory plugin that runs installers is a trust failure.
What it produces
Two values, which are the whole of the plugin's setup:
| Setting | Value |
|---|---|
endpoint |
the user's Mubit instance URL, e.g. https://api.mubit.ai |
apiKey |
a key of the form mbt_... |
They land in ${CLAUDE_PLUGIN_DATA}/credentials.json, owner-only (mode 600). That path
survives plugin updates, so this is a once-per-machine step, not a once-per-release one.
--data-dir "${MUBIT_CC_DATA_DIR:-${CLAUDE_PLUGIN_DATA}}" is not optional, on any of the
commands below. A Bash tool call does not inherit CLAUDE_PLUGIN_DATA — it arrives empty —
so without the flag the command has to guess which of several mubit-memory* directories the
host is using, and a key written to the wrong one is indistinguishable, from the user's side,
from a sign-in that never happened. The host substitutes ${CLAUDE_PLUGIN_DATA} into this file
before you read it, and the shell default around it lets a session that pins
MUBIT_CC_DATA_DIR keep its pin — the same order every hook and the MCP launcher resolve in,
so the sign-in lands where they read. Pass the whole expression straight through. Do not turn
it into an ENV=… node … prefix: that is no longer a node command and will stop for a
permission prompt.
Step 1 — run it
Say what is about to happen before you run it. This command opens a browser and then blocks with no output until it finishes — a Bash tool call does not stream, so there is nothing to print in the meantime. Tell the user: a browser tab is opening; sign in or create an account there; a first-ever workspace takes a minute or two to provision and the page waits for it; then come back here.
Run it with a Bash timeout of 600000. The default is 120000, and the harness kills the
command at that point — in the middle of a sign-up that was going fine.
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.
- 1mo ago Changed · -13 tokens per session 46c040ed8b1c
- 2mo ago Changed · +20 lines 879b69d6aa1f
- 2mo ago First seen · 87 lines · 39 tokens per session scan A c3327825d485
auth is a skill published in the GitHub repository mubit-ai/claude-plugins (12 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 26 tokens to every session and 1,566 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.
auth compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| authmubit-ai/claude-plugins | Skill | 12 | 1mo ago | Apache-2.0 | A | 26 | Claude Code |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 68k | 2d ago | Apache-2.0 | A | 217 | Claude Code, Codex |
| azure-mgmt-botservice-dotnetmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 78 | Claude Code |
| fastapi-router-pymicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 46 | Claude Code |
| dev-runtimelangwatch/langwatch | Skill | 5.0k | yesterday | Apache-2.0 | A | 172 | Claude Code |
| api-designericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 105 | Claude Code, Codex |
| migrate-segw-to-raparc-mcp/arc-1 | Skill | 252 | yesterday | MIT | A | 106 | Claude Code |