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 agentmods add skills/mubit-ai/claude-plugins/authnpx skills add mubit-ai/claude-plugins --skill authgit 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/auth)<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="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 | $0.00039 | $0.01121 |
| Opus 5 | $0.00019 | $0.00561 |
| Sonnet 5 | $0.00008 | $0.00224 |
| Haiku 4.5 | $0.00004 | $0.00112 |
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 4d 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 — 87 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 ${CLAUDE_PLUGIN_DATA}/credentials.json, owner-only (mode 600). That path
survives plugin updates, so this is a once-per-machine step, not a once-per-release one.
Step 1 — run it
node "${CLAUDE_PLUGIN_ROOT}/bin/auth.mjs" --json
This opens the Mubit console in a browser. The user signs in (or signs up — the same page does
both), and the key comes back over a loopback callback on 127.0.0.1.
Prefer this over asking the user to paste a key. A key pasted into the conversation is in the transcript, and transcripts get shared, exported, and attached to bug reports. In the browser flow the key never passes through the conversation at all.
Step 2 — read the exit code
| Exit | Meaning | What to tell the user |
|---|---|---|
0 |
Signed in, and the key was checked against the instance. | Report the endpoint, then go to step 3. |
2 |
The workspace is still provisioning. Not a failure. | "Your workspace is still being created — usually a minute or two. Run /mubit-memory:auth again shortly; it picks up where it left off." Do not change anything. |
1 |
Something went wrong. The state field says which. |
See the table below. |
On exit 1, state is one of:
state |
What it means | What to tell the user |
|---|---|---|
browser_failed |
No browser opened, or the flow timed out. | Fall through to step 2b. This is the common case over SSH and in containers. |
auth_failed |
The instance rejected the key. | The key is wrong, revoked, or issued for a different instance. Issue a new one in the console. |
unreachable |
Nothing answered at the endpoint. | The endpoint is wrong, or the instance is not running. This is not a key problem — do not have them reissue one. |
server_error |
The instance is up and failing. | Retry once, then check the instance in the console. The client cannot fix it. |
invalid_key |
What was supplied is not mbt_-shaped. |
A truncated paste. Ask for the whole key. |
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.
- 4d 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 (13 stars, last pushed 6d ago), licensed Apache-2.0. It adds 39 tokens to every session and 1,121 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…